Sorting of aluminum alloys

Abstract

The material handling system utilizes a combination of a vision system implementing a spectroscopic sensor (e.g., X-ray fluorescence) and an artificial intelligence system to sort mixed scrap materials, identifying or classifying each material, which is then sorted into separate groups based on such identification or classification. The system can typically sort materials found in the Zorba, such as drawn, cast, and extruded aluminum alloys.

Description

Technical Field

[0001] This application claims the priority of U.S. Provisional Patent Application No. 63 / 487,583, which is incorporated herein by reference. This application is a continuation-in-part of U.S. Patent Application No. 17 / 495,291 (issued as U.S. Patent No. 11,975,365), which is a continuation-in-part of U.S. Patent Application No. 17 / 491,415 (issued as U.S. Patent No. 11,278,937), which is a continuation-in-part of U.S. Patent Application No. 17 / 380,928, which is a continuation-in-part of U.S. Patent Application No. 17 / 227,245 (issued as U.S. Patent No. 11,964,304), which is a continuation-in-part of U.S. Patent Application No. 16 / 939,011 (issued as U.S. Patent No. 11,471,916), which is a continuation of U.S. Patent Application No. 16 / 375,675 (issued as U.S. Patent No. 10,722,922), which is a continuation-in-part of U.S. Patent Application No. 15 / 963,755 (issued as U.S. Patent No. 10,710,119), which is a continuation-in-part of U.S. Patent Application No. 15 / 213,129 (issued as U.S. Patent No. 10,207,296), which claims the priority of U.S. Provisional Patent Application No. 62 / 193,332, and all of those documents are incorporated herein by reference. U.S. Patent Application No. 17 / 491,415 (issued as U.S. Patent No. 11,278,937) is a continuation-in-part of U.S. Patent Application No. 16 / 852,514 (issued as U.S. Patent No. 11,260,426), which is a divisional application of U.S. Patent Application No. 16 / 358,374 (issued as U.S. Patent No. 10,625,304), which is a continuation-in-part of U.S. Patent Application No. 15 / 963,755 (issued as U.S. Patent No. 10,710,119), which claims the priority of U.S. Provisional Patent Application No. 62 / 490,219, and all of those documents are incorporated herein by reference.

[0002] Government Licensing Rights This disclosure was made with the support of the U.S. Government under license number DE-AR0000422 issued by the U.S. Department of Energy. The U.S. Government may have certain rights in this disclosure.

[0003] This disclosure relates in general to the classification and sorting of mixtures of materials, and in particular to the classification and sorting of aluminum alloys from mixtures of Zorba materials. [Background technology]

[0004] This chapter is intended to introduce various aspects of the art that may be associated with exemplary embodiments of the present disclosure. This discussion is intended to help provide a framework to facilitate a better understanding of particular aspects of the present disclosure. Therefore, it should be understood that this chapter should be read in this sense and not necessarily as an acknowledgment of prior art.

[0005] Recycling benefits local communities and the environment because it reduces the amount of waste sent to landfills and incinerators, conserves natural resources, increases economic stability by utilizing domestic material sources, prevents pollution by reducing the need to collect new raw materials, and saves energy.

[0006] Recycling aluminum (Al) scrap is a very attractive proposition, as it can reduce the energy costs associated with production by up to 95% compared to the laborious extraction of more costly primary aluminum. Primary aluminum (or virgin aluminum) is defined as aluminum derived from aluminum-rich ores (such as bauxite). At the same time, the demand for aluminum is steadily increasing in markets such as automobile manufacturing due to its lightweight properties. As a result, there are certain economic advantages available to the aluminum industry by developing a well-planned yet simple recycling plan or system. The use of recycled material would result in a cheaper metallic resource than primary aluminum sources. As the amount of aluminum sold to the automotive industry (and other industries) increases, the use of recycled aluminum to supplement the supply of primary aluminum will become increasingly necessary.

[0007] Accordingly, it is particularly desirable to efficiently separate aluminum scrap metal into alloy families. This is because mixed aluminum scrap of the same alloy family is far more valuable than indiscriminately mixed alloys. For example, in blending methods used to recycle aluminum, any amount of consistent quality scrap composed of similar (or the same) alloys is more valuable than scrap composed of mixed aluminum alloys. In such aluminum alloys, aluminum will always be the majority of the material. However, components such as copper, magnesium, silicon, iron, chromium, zinc, manganese, and other alloying elements provide various properties to the alloyed aluminum, providing a means to distinguish one aluminum alloy from others.

[0008] The Aluminum Society is the body that defines the permissible limits for the chemical composition of aluminum alloys. Data on the chemical composition of wrought aluminum alloys is published by the Aluminum Society in "International Alloy Designations and Chemical Composition Limits for Wrought Aluminum and Wrought Aluminum Alloys," which was updated in January 2015 and is incorporated herein by reference. The International Alloy Designation System is the most widely accepted nomenclature for wrought alloys. Each alloy is assigned a four-digit number, where the first digit indicates the primary alloying element, the second digit, if not 0, indicates the variant of the alloy, and the third and fourth digits identify a specific alloy within the series. For example, in alloy 3105, the number 3 indicates that the alloy belongs to the manganese series, 1 indicates the first modification of alloy 3005, and 05 identifies it within the 3000 series. Generally, according to the Aluminum Association, the 1xxx series of wrought aluminum alloys consists essentially of pure aluminum with a minimum aluminum content of 99% by weight; the 2xxx series is wrought aluminum alloyed primarily with copper (Cu); the 3xxx series is wrought aluminum alloyed primarily with manganese (Mn); the 4xxx series is wrought aluminum alloyed with silicon (Si); the 5xxx series is wrought aluminum alloyed primarily with magnesium (Mg); the 6xxx series is wrought aluminum alloyed primarily with magnesium and silicon; the 7xxx series is wrought aluminum alloyed primarily with zinc (Zn); and the 8xxx series is the other category.

[0009] The Aluminum Association also has similar literature regarding the designation of cast aluminum alloys. The 1xx series of cast aluminum alloys consists essentially of pure aluminum with a minimum aluminum content of 99% by weight; the 2xx series is cast aluminum alloyed primarily with copper; the 3xx series is cast aluminum alloyed primarily with silicon plus copper and / or magnesium; the 4xx series is cast aluminum alloyed primarily with silicon; the 5xx series is cast aluminum alloyed primarily with magnesium; the 6xx series is the unused series; the 7xx series is cast aluminum alloyed primarily with zinc; the 8xx series is cast aluminum alloyed primarily with tin; and the 9xx series is cast aluminum alloyed with other elements. Examples of cast alloys used for automotive parts include 38x (e.g., 380, 383, 384, 356, 360, and 319).

[0010] Generally, wrought aluminum alloys have a higher magnesium concentration than cast aluminum alloys, and cast aluminum alloys have a higher silicon concentration than wrought aluminum alloys.

[0011] Furthermore, the presence of mixed pieces of different alloys within the main body of scrap limits the scrap's ability to be usefully recycled unless the different alloys (or at least alloys belonging to different compositional families, such as those designated by the Aluminum Association) can be separated before remelting. This is because when scrap containing multiple different alloy compositions or compositional families is remelted, the resulting molten mixture contains proportions of major alloys and elements (or different compositions) that are too high to meet the compositional limits required in any particular commercial alloy.

[0012] The automotive industry is a vital sector of the U.S. economy in terms of revenue generation and employment. For the past 50 years, Detroit's automotive industry has suffered many setbacks due to low-cost imports. The recent emergence of fuel-efficient, lightweight electric vehicles presents an opportunity for Detroit to regain global leadership in automotive manufacturing, particularly in terms of massive investments by Ford and General Motors to capture a significant market share. One consequence is that the materials used to manufacture automobiles are shifting from heavy steel to lightweight aluminum for the body and battery trays, and from copper for the electric motors. For example, a Tesla Model 3 electric vehicle (EV) contains approximately 660 pounds of aluminum compared to approximately 250 pounds in an average internal combustion engine ("ICE") vehicle. There is now a consensus that by 2025, there will be a shortage of 2 billion pounds of aluminum to manufacture electric vehicles. Currently, Russia and China are two of the world's largest suppliers of primary aluminum. A similar situation exists regarding the demand for copper in electric motors, which has led to a significant increase in copper prices. Therefore, there is a need to develop reliable and sustainable domestic supply chains for these critical materials.

[0013] Zorba is a mixed non-ferrous scrap, typically containing 90-95% metal, and is a by-product of the current steel manufacturing process. Currently, there are approximately 300 auto shredders in the United States, which shred 12-15 million end-of-life ("EOL") vehicles annually, in addition to white goods (e.g., washing machines, dryers, refrigerators, and other electrical appliances) and construction scrap (e.g., aluminum siding, windows, and door frames). Shredders typically operate continuously, producing steel (ferrous) scrap (which then produces steel rebar for use in the construction of buildings, bridges, and factories). After shredding, the steel scrap is removed by large electromagnets and sent to steel mills. The by-product of the shredders is the remaining mixed non-ferrous scrap, containing everything except magnetic steel. The next step has traditionally involved the use of eddy current sorters to separate the low-value non-metallic materials (typically half the weight of a car sent to a landfill) and recover the mixed metal scrap (i.e., Zorba). However, such eddy current sorters are inefficient and very expensive to operate. As a result, large quantities of Zorba remain unsorted. Currently, more than 10 billion pounds of Zorba are produced in the United States every year, with over 40% being shipped overseas and sorted manually.

[0014] Furthermore, as evidenced by the production and sale of the Ford F-150 pickup truck, which has a significant increase in its body and frame components made of aluminum instead of steel, it is additionally desirable to recycle sheet metal scrap (e.g., wrought aluminum of a specific alloy composition), including that which arises in the manufacture of automotive components from sheet aluminum (often referred to in this industry as "clips"). Recycling scrap involves remelting the scrap, providing a body of molten metal that can be cast and / or rolled to become aluminum parts useful for further production of such vehicles. However, automotive manufacturing scrap (and metal scrap from other sources, such as aircraft and commercial and household appliances) often contains a mixture of wrought and cast scrap pieces, as well as / or two or more aluminum alloys that are substantially different from each other in terms of composition. Therefore, those skilled in the art of aluminum alloys will recognize the difficulty of separating aluminum alloys, in particular processed alloys (e.g., cast, forged, extruded, rolled, and generally drawn alloys) into reusable or recyclable processed products.

[0015] Currently, the only existing technology for separating cast alloys from wrought alloys in a cost-effective manner is X-ray transmission ("XRT") technology. Cast alloys are denser than wrought alloys because cast alloys are heavier due to their higher silicon concentration. X-ray transmission technology can measure the denser cast aluminum alloys and then separate the cast alloys from the wrought alloys. However, this method is not perfect. For example, cast alloys 319 and 380 / 383 have relatively high zinc concentrations (e.g., about 3%), which gives these cast alloys their higher respective densities. However, cast alloy 360 has a lower relative zinc concentration (e.g., about 0.5%) and therefore has a lower density. The lower density of cast alloy 360 causes the X-ray transmission method to classify this alloy as a wrought alloy rather than a cast alloy. Thus, X-ray transmission technology does not correctly classify all cast alloys due to the large variation in the density of each cast alloy. Therefore, such cast alloys end up being separated from the wrought aluminum alloys, which results in an excess of relative silicon in the molten mixture. [Prior art documents] [Patent Documents]

[0016] [Patent Document 1] U.S. Patent Application Publication No. 2022 / 0161298 [Patent Document 2] U.S. Patent No. 10,207,296 [Patent Document 3] U.S. Patent Application No. 18 / 491,692 [Patent Document 4] U.S. Patent Application Publication No. 2022 / 0371057 [Patent Document 5] U.S. Patent No. 11,471,916 [Patent Document 6] U.S. Patent No. 11,278,937 [Patent Document 7] U.S. Patent Application Publication No. 2021 / 0346916 [Patent Document 8] U.S. Patent Application Publication No. 2021 / 0229133 [Patent Document 9] U.S. Patent Application Publication No. 2022 / 0016675 [Brief Description of the Drawings]

[0017] [Figure 1] Schematic diagram of a material handling system configured according to various embodiments of the present disclosure. [Figure 2] Flowchart diagram configured according to a specific embodiment of the present disclosure. [Figure 3] Flowchart diagram configured according to a specific embodiment of the present disclosure. [Figure 4] Diagram schematically illustrating various sorting operations that can be performed on scrap. [Figure 5] Diagram schematically illustrating an exemplary technique that can be utilized to classify and sort zebra materials. [Figure 6] Diagram schematically illustrating an exemplary technique that can be utilized to classify and sort twitch materials. [Figure 7A] Flowchart diagram configured according to various embodiments of the present disclosure. [Figure 7B] Flowchart diagram configured according to various embodiments of the present disclosure. [Figure 7C] Flowchart diagram configured according to various embodiments of the present disclosure. [Figure 8] Diagram illustrating a system and process for sorting materials according to a specific embodiment of the present disclosure. [Figure 9A] Diagram illustrating a system and process for sorting materials according to a specific embodiment of the present disclosure. [Figure 9B] Diagram illustrating a system and process for sorting materials according to a specific embodiment of the present disclosure. [Figure 10] This figure illustrates a link connection of a continuous material handling system according to a particular embodiment of the present disclosure. [Figure 11] This is a block diagram of a data processing system configured according to various embodiments of the present disclosure. [Figure 12A] This is a flowchart diagram configured according to various embodiments of the present disclosure. [Figure 12B] This is a flowchart diagram configured according to various embodiments of the present disclosure. [Modes for carrying out the invention]

[0018] Various detailed embodiments of the present disclosure are disclosed herein. However, it should be understood that the disclosed embodiments are merely illustrative of the present disclosure and can be embodied in various and alternative forms. The figures are not necessarily to scale, and some features may be exaggerated or minimized to illustrate details of particular components. Accordingly, certain structural and functional details disclosed herein should not be construed as restrictive, but merely as representative grounds to teach those skilled in the art to use the various embodiments of the present disclosure.

[0019] High robustness, throughput, efficiency, accuracy, and precision are desired for recovering high-value materials from solbers. As will be further described herein, after removing low-value steel by a magnetic separator, a variety of higher-value non-ferrous materials (e.g., aluminum, copper, brass, zinc, stainless steel, PCBs, lead, etc.) are sorted according to various embodiments of this disclosure to generate high-purity “specification raw materials” that can be used to manufacture products.

[0020] Sorting / recovering various high-value materials from a Zorba is more complex and requires both spectroscopic and vision (implementing AI systems) based sensors. Embodiments of this disclosure accomplish such a task by essentially measuring the chemical composition of each type of material found in the Zorba. Signals from vision and sensor systems (e.g., spectroscopic systems (e.g., XRF, LIBS, etc.)) are combined with respect to each individual material to generate a "fingerprint" representing the image and compositional data within the material, which is then used to sort among the various materials in the Zorba.

[0021] As used herein, “Materials” can include any item or object, including but not limited to metals (ferrous and / or nonferrous), metal alloys (including but not limited to aluminum alloys), heavy, solba, zebra, twitch, pieces of metal embedded in another different material, plastics / polymers (including but not limited to any plastics / polymers disclosed herein, known in the industry, or newly created in the future), rubber, foam, printed circuit boards ("PCBs"), glass (including but not limited to borosilicate glass or soda-lime glass, and various colored glasses), ceramics, paper, cardboard, Teflon®, PE, bundled wire, insulated wire, rare earth elements, leaves, wood, plants, plant parts, fibers, biowaste, packaging, electronic waste This includes waste, batteries and accumulators, scrap from end-of-life ("EOL") products (e.g., vehicles, aircraft, and / or electrical appliances), mining, construction, and demolition waste, crop waste, forest residues, grasses grown for specific purposes, woody energy crops, microalgae, food waste, hazardous chemical and biomedical waste, construction waste, agricultural waste, biogenic items, non-biogenic items, objects having a specific carbon content, any other objects that may be found in municipal solid waste, as well as any other objects, items, or materials disclosed herein (including, but not limited to, any of the aforementioned types or classes that may be distinguished from each other (including, but not limited to, being distinguished by one or more sensor systems (including, but not limited to, any of the sensor technologies disclosed herein)).

[0022] In a more general sense, “material” can include chemical elements, compounds or mixtures of chemical elements, or any item or object composed of compounds or mixtures of chemical elements, the complexity of the compounds or mixtures can range from simple to complex (all of which may also be referred to herein as materials having a particular “chemical composition” (or a particular “material composition”). “Chemical elements” means chemical elements of the periodic table of chemical elements, including chemical elements that may be discovered after the filing date of this application. In this disclosure, the terms “scrap,” “scrap piece,” “material,” “material piece,” and “material scrap piece” may be used interchangeably. A material piece or scrap piece referred to as having a metallic alloy composition, as used herein, is a metallic alloy having a particular chemical composition that distinguishes it from other metallic alloys. As used herein, “contaminant” is any material (or component of a material piece) that will be excluded from a group of sorted materials.

[0023] As used herein, the term “predetermined” means something that is established or determined in advance (for example, by a user of an embodiment of this disclosure).

[0024] As used herein, the term “chemical signature” refers to a unique pattern (e.g., a fingerprint spectrum) that will be produced by one or more analytical instruments, which indicates the presence of one or more specific elements or molecules (including polymers) in a sample. These elements or molecules may be organic and / or inorganic. Such analytical instruments include any of the sensor systems disclosed herein (and also disclosed in U.S. Patent Application Publication No. 2022 / 0161298), which are incorporated herein by reference. According to embodiments of this disclosure, one or more such sensor systems may be configured to produce a chemical signature of a material piece.

[0025] As defined in the guidelines on non-ferrous scrap published by the Institute of Scrap Recycling Industries, Inc. ("ISRI"), the term "Zorba" is a collective term for shredded non-ferrous metals, including, but not limited to, those resulting from EOL products (e.g., vehicles, aircraft, electrical appliances) or waste electrical and electronic equipment ("WEEE"). ISRI has established specifications for Zorba, in which each scrap piece may consist of a combination of non-ferrous metals (aluminum, copper, lead, magnesium, stainless steel, nickel, tin, and zinc) in elemental or alloyed (solid) form. Furthermore, the term "Twitch" shall mean fragmented aluminum scrap. Twitch is traditionally produced by medium separation techniques (e.g., float processes), thereby causing the aluminum scrap to float to the top as heavier metal scrap pieces sink (for example, in some processes, sand may be mixed in to change the density of the water in which the scrap is immersed). The term "zebra" shall refer to high-density nonferrous metals typically produced by such processes.

[0026] As is well known in this industry, a "polymer" is a substance or material composed of very large molecules (or macromolecules) made up of many repeating subunits. Polymers can be natural polymers found in nature or synthetic polymers. A "multilayer polymer film" is composed of two or more different compositions and has a maximum density of approximately 7.5-8 × 10⁻¹⁶. -4 It is possible to have a thickness of m. The layers are at least partially adjacent and preferably (but optional) have the same extent. As used herein, the terms “plastic,” “plastic piece,” and “piece of plastic material” (all of which can be used interchangeably) refer to any object containing or composed of one or more polymer and / or multilayer polymer film polymer compositions.

[0027] As used herein, “fraction” refers to any identified combination of organic and / or inorganic elements or molecules, polymer type, plastic type, polymer composition, chemical signature of the plastic, physical properties of the plastic piece (e.g., color, transparency, strength, melting point, density, shape, size, manufacturing type, uniformity, response to stimuli, etc.), and it includes any and all of the various classifications and types of plastics disclosed herein. Non-limiting examples of fractions include one or more different types of plastic pieces containing: LDPE with a relatively high percentage of aluminum; LDPE and PP with a relatively low percentage of iron; PP with zinc; combinations of PE, PET, and HDPE; any type of red LDPE plastic piece; any combination of plastic pieces excluding PVC; black plastic pieces; combinations of #3 to #7 type plastics containing specified combinations of organic and inorganic molecules; combinations of one or more different types of multilayer polymer films; specified combinations of plastics that do not contain specified contaminants or additives; any type of plastic with a melting point greater than the specified threshold; any thermosetting plastics of multiple specified types; specified plastics that do not contain chlorine; combinations of plastics with similar densities; combinations of plastics with similar polarity; plastic bottles without or without attached caps.

[0028] As used herein, the term “image data” refers to packets of digital data relating to captured visual images of individual material pieces.

[0029] As used herein, the term “sort” and any derivative thereof refers to the physical separation of a particular piece of material (e.g., a piece of material specifically classified) from other pieces of material.

[0030] As used herein, the terms “identify” and “classify,” the terms “identify” and “classify,” and any derived terms thereof are interchangeable. As used herein, “classifying” a material piece means assigning or determining (i.e., identifying) the type or class of material to which the material piece belongs. For example, according to certain embodiments of the present disclosure, a vision system and / or a sensor system (as further described herein) can be configured to capture (collect) and analyze any type of information for classifying materials and distinguishing such classified materials from other materials, the classification can be utilized in a material handling system to selectively sort material pieces according to one or more sets of physical and / or chemical properties (for example, it can be user-defined) (including, but not limited to, color, texture, hue, shape, brightness, weight, density, chemical composition, size, uniformity, type of manufacture, chemical signature, predetermined fraction, radioactive signature, transmittance to light, sound or other signals, and response to stimuli (for example, various fields, etc.) (including emitted and / or reflected electromagnetic radiation ("EM") of the material piece).

[0031] The type or class (i.e., classification) of the material piece can be user-definable (e.g., predetermined) and is not limited to any known classification of the material. The granularity of that type or class can range from very coarse to very fine. For example, the type or class may include plastics, ceramics, glass, metals, foams, wood, and other materials (where the particle size of such type or class is relatively coarse); different metals and metal alloys (e.g., zinc, copper, brass, lead, chromium plate, nickel plate, stainless steel, and aluminum, etc.) (where the particle size of such type or class is finer); or between certain types of aluminum alloys (where the particle size of such type or class is relatively fine). Thus, the type or class may be configured to distinguish between materials with significantly different chemical compositions (e.g., plastics and metal alloys, etc.) or between materials with nearly identical chemical compositions (e.g., different types of aluminum alloys, etc.). It should be recognized that the methods and systems discussed herein can be applied to accurately identify / classify material pieces whose chemical composition is completely unknown before classification.

[0032] As used herein, “manufacturing type” refers to the type of manufacturing process by which a material piece is produced, such as, for example, a metal part being formed by a drawing process, being cast (including, but not limited to, consumable casting, permanent casting, and powder metallurgy), being extruded, being forged, or a material removal process.

[0033] As referred to herein, “conveyor system” can be any known piece of mechanical handling equipment that moves material from one place to another, including but not limited to aeromechanical conveyors, automobile conveyors, conveyor belts, belt-driven live roller conveyors, bucket conveyors, chain conveyors, chain-driven live roller conveyors, drag conveyors, dustproof conveyors, electric track vehicle systems, flexible conveyors, gravity conveyors, gravity skate wheel conveyors, line shaft roller conveyors, electric drive roller conveyors, overhead I-beam conveyors, overland conveyors, pharmaceutical conveyors, plastic belt conveyors, pneumatic conveyors, screw or auger conveyors, spiral conveyors, tubular gallery conveyors, vertical conveyors, vibrating conveyors, wire mesh conveyors, as well as conveying material pieces in a fluid through vision and / or sensor systems (including, but not limited to, very small particles suspended in a fluid).

[0034] The systems and methods described herein in accordance with specific embodiments of the present disclosure accept heterogeneous mixtures of multiple material pieces (e.g., EOL scrap, Zorba, Heavy, Zebra, and / or Twitch), wherein at least one material piece in the heterogeneous mixture has a different chemical composition from one or more other material pieces, and / or is physically distinguishable from the other material pieces, and / or is a different class or type of material from the other material pieces in the mixture, and the systems and methods are configured to identify / classify / distinguish / sort this one material piece into a separate group from such other material pieces. Embodiments of the present disclosure can be used to sort any type or class of material as defined herein. In contrast, a homogeneous set or group of material all fall into the same distinguishable class or type of material.

[0035] Certain embodiments of the present disclosure will be described herein as classifying and sorting material pieces into separate groups or aggregates by sorting the material pieces according to user-defined or predetermined groupings or aggregates (e.g., material piece classification) (e.g., physically depositing the material pieces into separate receiving units or bins or onto a separate conveyor system (e.g., discharging or redirecting)). As an example, in certain embodiments of the present disclosure, material pieces are sorted into separate receiving units in order to separate material pieces of a particular material composition or composition from other material pieces of a different material composition.

[0036] It should be noted that the materials to be sorted may have irregular sizes and shapes. For example, such materials (e.g., Zorba, Zebra, and / or Twitch) may have previously passed through some kind of shredding mechanism that cuts the material into such irregularly shaped and sized pieces (creating scrap pieces), which can then be fed or redirected onto a conveyor system.

[0037] Certain embodiments of the present disclosure can be configured to sort aluminum alloy material pieces into separate receptacles, so that substantially all aluminum alloy material pieces having a material composition that falls within one of the aluminum alloy series published by the Aluminum Society are sorted into a single receptacle (for example, the receptacle may correspond to one or more specific aluminum alloy series (e.g., 1xxx, 2xxx, 3xxx, 4xxx, 5xxx, 6xxx, 7xxx, 8xxx, 1xx, 2xx, 3xx, 4xx, 5xx, 6xx, 7xx, 8xx, 9xx)). Furthermore, as will be described herein, certain embodiments of the present disclosure can be configured to sort metal alloys into separate receptacles according to the classification of their metal alloy composition, even if such metal alloy compositions fall within the same alloy series (e.g., as defined by the Aluminum Society). As a result, a material handling system configured according to a particular embodiment of the present disclosure can classify and sort aluminum alloy material pieces having compositions that would all be classified into a single aluminum alloy series (e.g., the 3xx series or the 5xx series) into separate receiving compartments according to their aluminum alloy composition. For example, a particular embodiment of the present disclosure can classify and sort aluminum alloy material pieces classified as cast aluminum alloy 360 into separate receiving compartments, separately from aluminum alloy material pieces classified as cast aluminum alloy 380 (or other similar cast aluminum alloys (e.g., 383, etc.)).

[0038] Figure 1 illustrates a non-limiting example of a material handling system 100 configured according to various embodiments of the present disclosure. A conveyor system 103 can be implemented to transport individual material pieces 101 through the material handling system 100, so that each individual material piece 101 can be tracked, classified, distinguished, and / or sorted into a predetermined desired group (e.g., material classification). Such a conveyor system 103 can be implemented comprising one or more conveyor belts, the material pieces 101 moving on one or more conveyor belts at a typically predetermined constant speed. However, certain embodiments of the present disclosure can be implemented comprising other types of conveyor systems, including systems in which material pieces free-fall through one or more of the various components of the material handling system 100 (or any other type of vertical sorter), or any other conveyor systems disclosed herein. Hereafter, where applicable, the conveyor system 103 may also be referred to as the conveyor belt 103. In one or more embodiments, some or all of the acts or functions of conveying, capturing, stimulating, detecting, classifying, distinguishing, and sorting can be performed automatically (i.e., without human intervention). For example, in the material handling system 100, one or more cameras, one or more vision systems, one or more sensor systems, one or more stimulus sources, one or more emission detectors, one or more classification modules, sorting devices, one or more sorting devices, and / or other system components can be configured to perform these and other operations automatically.

[0039] Furthermore, while the simplified diagram in Figure 1 shows a single stream of material pieces 101 on a conveyor belt 103, embodiments of the present disclosure can also be implemented in which multiple such streams of material pieces pass through various components of the material handling system 100 in parallel to one another. According to certain embodiments of the present disclosure, some suitable feeder mechanism (e.g., another conveyor system, bowl feeder, or hopper 102) can be used to feed the material pieces 101 onto the conveyor system 103, thereby allowing the conveyor system 103 to transport the material pieces 101 through various components of the material handling system 100. According to certain embodiments of the present disclosure, tumblers and / or vibrators can be used to separate individual material pieces from aggregates of material pieces (e.g., physical stacks). According to certain embodiments of the present disclosure, material pieces can be positioned into one or more singulated (i.e., single-row) streams, which can be carried out by active or passive singulators 106. An example of a passive singularity is further described in U.S. Patent No. 10,207,296.

[0040] Therefore, certain embodiments of the present disclosure can simultaneously track, classify, distinguish, and / or sort such a moving stream of material pieces. Alternatively, a conveyor system (e.g., a conveyor belt 103) can simply transport the aggregate of material pieces piled on the conveyor belt 103 in a random manner. Therefore, according to certain embodiments of the present disclosure, singulation of material pieces 101 is not required to track, classify, distinguish, and / or sort the material pieces.

[0041] In certain embodiments of the present disclosure, the conveyor system 103 is operated to move at a predetermined speed by a conveyor system motor 104. This predetermined speed may be programmable and / or adjustable by an operator in any known manner. In certain embodiments of the present disclosure, control of the conveyor system motor 104 and / or position detector 105 may be carried out by an automated control system 108. Such an automated control system 108 may operate under the control of a computer system 107, and / or the functions for carrying out automated control may be implemented in software within the computer system 107. If the conveyor system 103 is a conveyor belt, it may be a conventional endless belt conveyor with a conventional drive motor 104 suitable for moving the conveyor belt 103 at a predetermined speed.

[0042] The position detector 105 (e.g., a conventional encoder) is operably connected to the conveyor belt 103 and the automated control system 108 and is capable of providing information corresponding to the movement (e.g., speed) of the conveyor belt 103. Thus, as will be further described herein, when each of the material pieces 101 moving on the conveyor belt 103 is identified through the use of control to the conveyor belt drive motor 104 and / or the automated control system 108 (and alternatively, including the position detector 105), they can be tracked by location and time (for various components of the material handling system 100), and the various components of the material handling system 100 can be activated / deactivated when each material piece 101 passes near them. As a result, the automated control system 108 can track the location of each material piece 101 as it moves along the conveyor belt 103.

[0043] The vision system 110 can be configured to perform specific type identification (e.g., classification) (also referred to herein as “vision check”) of all or part of the material piece 101, as will be further described herein. For example, such a vision system 110 can be used to capture or acquire information about each of the material piece 101. For example, the vision system 110 can be configured to capture or collect any type of information from the material piece (e.g., with an artificial intelligence ("AI") system, as will be further described herein), and this information can be used in the material handling system 100 to classify the material piece 101 according to a set of one or more properties (e.g., physical properties and / or chemical properties and / or radioactive properties), as will be further described herein. According to certain embodiments of this disclosure, the vision system 110 can be configured to capture a visual image (including one-dimensional, two-dimensional, three-dimensional, or holographic imaging) of each of the material piece 101 by using an optical sensor, for example, such as those used in typical digital cameras and video equipment. Such visual images captured by an optical sensor are then stored in a memory device as image data (for example, formatted as image data packets). According to certain embodiments of this disclosure, such image data can represent images captured within the optical wavelengths of light (i.e., wavelengths of light observable by the typical human eye). However, alternative embodiments of this disclosure may utilize a vision system configured to capture images of materials composed of wavelengths of light outside the visible wavelength range of the human eye.

[0044] According to alternative embodiments of the present disclosure, the vision system 110 may also be used as a means for tracking each of the material pieces 101 as they move along the conveyor system 103, and it may utilize one or more still cameras or live-action cameras 109 to record the position (i.e., location and timing) of each of the material pieces 101 on the moving conveyor system 103.

[0045] According to alternative embodiments of the present disclosure, the vision system 110 may implement a machine vision system (for example, one that may be implemented in LabVIEW) for analyzing and / or determining the shape (or relative shape) of each material piece 101.

[0046] According to certain embodiments of the present disclosure, the material handling system 100 may be implemented comprising one or more sensor systems 120 which can be used alone or in combination with a vision system 110 to classify / identify / distinguish material pieces 101 (as described, for example, with respect to Figures 7A-7C and Figures 12A-12B). The sensor system 120 utilizes any type of sensor technology (using irradiated or reflected electromagnetic radiation (e.g., infrared ("IR"), Fourier transform IR ("FTIR"), forward-looking infrared ("FLIR"), extremely near-infrared ("VNIR"), near-infrared ("NIR"), short-wavelength infrared ("SWIR"), long-wavelength infrared ("LWIR"), mid-wavelength infrared ("MWIR" or "MIR"), ultraviolet ("UV"), X-ray transmission ("XRT") spectroscopy, X-ray fluorescence ("XRF") spectroscopy, laser-induced breakdown spectroscopy ("LIBS"), laser spark spectroscopy ("LSS"), laser-induced emission spectroscopy ("LIOES"), Raman spectroscopy, coherent anti-Stoke Raman spectroscopy, gamma-ray spectroscopy, hyperspectral spectroscopy (e.g., wavelengths beyond visible wavelength) It may be comprised of sensors (including those utilizing one-dimensional, two-dimensional, or three-dimensional imaging by any of the aforementioned methods), including acoustic spectroscopy, NMR spectroscopy, microwave spectroscopy, terahertz spectroscopy, differential scanning calorimetry ("DSC"), thermogravimetric analysis ("TGA"), optical microscopy and scanning electron microscopy ("SEM"), and chromatography (e.g., LC-PDA, LC-MS, LC-LS, GC-MS, GC-FID, HS-GC), or any other type of sensor technology (including, but not limited to, chemical or radioactive sensors), all of which are distinguished herein from implementations of vision systems that utilize AI technology (e.g., AI models) to analyze visual images. An exemplary implementation of an XRF spectroscopy system (for example, for use as sensor system 120 herein) is further described in U.S. Patent No. 10,207,296.Furthermore, XRF can also be used in alternative embodiments of this disclosure to identify inorganic materials within a plastic piece (for example, to be included in a chemical signature).

[0047] As used herein, the terms “sensor system” and “sensor technology” refer to any implementation of a sensor system disclosed herein for classifying / identifying / distinguishing material pieces (also referred to herein as “sensor system classification”), to distinguish it from the use of a vision system that utilizes AI technology for classifying / identifying / distinguishing material pieces.

[0048] Furthermore, the following sensor systems may also be used in certain embodiments of this disclosure to determine the chemical signature of plastic pieces and / or to classify plastic pieces for sorting. Various forms of infrared spectroscopy previously disclosed (e.g., IR, FTIR, FLIR, VNIR, NIR, SWIR, LWIR, MWIR, and / or MIR) can be used to obtain a chemical signature specific to each plastic piece, which provides information about the base polymer of any plastic material and other components present in the material (mineral fillers, copolymers, polymer blends, etc.). DSC is a thermal analysis technique that obtains thermal transitions produced during heating of the material being analyzed, which are specific to each material. TGA is another thermal analysis technique that results in quantitative information about the composition of plastic materials, including polymer percentage, other organic components, mineral fillers, carbon black, etc. Capillary and rotational rheometry can determine the rheological properties of polymer materials by measuring the creep and deformation resistance of the polymer material. Optical microscopes and scanning electron microscopes (SEMs) can provide information about the structure of the material being analyzed, such as the number and thickness of layers in multilayer materials (e.g., multilayer polymer films), the dispersion size of pigment or filler particles in the polymer matrix, coating defects, and interphase morphology between components. Chromatography can quantify trace components of plastic materials, such as UV stabilizers, antioxidants, plasticizers, anti-slip agents, and residual monomers, residual solvents from inks or adhesives, and degradation substances.

[0049] Figure 1 is illustrated to include one or more sensor systems 120, but the implementation of such sensor systems is optional in the particular embodiments of this disclosure. In the particular embodiments of this disclosure, a combination of one or more vision systems and one or more sensor systems can be used to classify material pieces 101. In the particular embodiments of this disclosure, one or any combination of the different sensor technologies disclosed herein can be used to classify material pieces 101 without the use of a vision system 110.

[0050] According to certain embodiments of the present disclosure, one or more vision systems and / or one or more sensor systems can be configured to identify which of the material pieces 101 contain a contaminant (e.g., a steel or iron piece containing copper; a plastic piece containing a specific contaminant, additive, or undesirable physical feature (e.g., an attached container cap formed from a different type of plastic than the container)) and to send a signal to separate (sort) such material pieces (e.g., from those that do not contain the contaminant). In such a configuration, the identified material pieces 101 can be redirected / discharged (sorted) using one of the mechanisms described later for physically separating the material pieces into individual receptacles.

[0051] In certain embodiments of this disclosure, a material piece tracking device 111 (or a commercially available profilometer) and an associated control system 112 can be utilized and configured to measure the size and / or shape of each material piece 101 as it passes near the material piece tracking device 111, along with the position (i.e., location and timing) of each material piece 101 on a moving conveyor system 103. Exemplary operation of such a material piece tracking device 111 and control system 112 is further described in U.S. Patent No. 10,207,296. Exemplary operation of a profilometer and similar devices is described in U.S. Patent Application No. 18 / 491,692, which is incorporated herein by reference.

[0052] Alternatively, as disclosed herein, the vision system 110 can be used to track the position (i.e., location and timing) of each material piece 101 as it is transported by the conveyor system 103. Thus, certain embodiments of the present disclosure can be implemented without a material piece tracking device (e.g., material piece tracking device 111) for tracking the material pieces.

[0053] In certain embodiments of the present disclosure that implement one or more sensor systems 120, the sensor system 120 can be configured to identify the chemical composition of each material piece 101, the relative chemical composition (including, but not limited to, measuring the amount of a particular element in the material piece), and / or the type of manufacture of the material piece 101 as the material piece passes near the sensor system 120. The sensor system 120 can include, for example, an energy release source 121 (which may be powered by a power supply 122) to stimulate a response from each of the material pieces 101. In certain embodiments of the present disclosure, the sensor system 120 can emit a suitable sensing signal toward the material piece 101 as each material piece 101 passes near the release source 121. One or more detectors 124 can be positioned and configured in a form appropriate for the type of sensor technology used to sense / detect one or more properties from the material piece 101. One or more detectors 124 and associated detector electronics 125 capture these received sensed characteristics, perform signal processing thereon to produce digitized information representing the sensed characteristics (e.g., spectroscopic data (e.g., XRF spectral data)), which is then analyzed to classify each of the material pieces 101.

[0054] Figure 1 illustrates a combination of a vision system 110 and one or more sensor systems 120, but it should be noted that embodiments of the present disclosure can be implemented using any combination of sensor systems utilizing any of the sensor technologies disclosed herein or any other sensor technologies currently available or to be developed in the future.

[0055] In certain embodiments of this disclosure, a material piece tracking device 111 and an associated control system 112 can be utilized and configured to determine the size and / or shape of each material piece 101 as it passes near the material piece tracking device 111, along with the position (i.e., location and timing) of each material piece 101 on a moving conveyor system 103. Exemplary operation of such a material piece tracking device 111 and control system 112 is further described in U.S. Patent No. 10,207,296.

[0056] According to certain embodiments of the present disclosure, the material tracking device 111 can be implemented before the vision system 110 and / or sensor system 120 (for example, upstream on the conveyor system), and it is configured to trigger the material handling system 100 when the vision system 110 and / or sensor system 120 should capture the characteristics of the material piece when the material tracking device 111 detects the material piece. Furthermore, the order in which the vision system 110 and sensor system 120 are implemented within the material handling system 100 can be interchanged.

[0057] The classification of material pieces (which can be performed within the computer system 107) is then utilized by the automated control system 108 to activate one of the N(N>1) sorting devices 126…129 of the sorting apparatus to sort (e.g., redirect / discharge) the material pieces 101 (e.g., into one or more N(N>1) sorting receiving sections 136…139 or onto one or more other conveyor belts) according to the determined classification. Four sorting devices 126…129 and four sorting receiving sections 136…139 associated with the sorting devices are illustrated in Figure 1 as merely an unrestricted example.

[0058] The sorting device may include any known mechanism for reorienting selected material pieces 101 toward a desired location (including, but not limited to, redirecting the material pieces 101 from the conveyor belt system into one of several sorting receiving units). For example, the sorting device may utilize air jets, each of which is assigned to one or more of the classifications. When one or more of the air jets (e.g., 127) receive a signal from the automated control system 108, the air jet releases a stream of air, which causes the material pieces 101 to be redirected / discharged from the conveyor system 103 into a sorting receiving unit (e.g., 137) corresponding to that air jet (or onto another conveyor system).

[0059] The example illustrated in Figure 1 uses an air jet to deflect / discharge a material piece, but other mechanisms may also be used to deflect / discharge a material piece, such as removing the material piece from the conveyor belt with a robot, pushing the material piece from the conveyor belt (e.g., by a paintbrush-type plunger), creating an opening (e.g., a trapdoor) in the conveyor system 103 from which the material piece can fall, or using an air jet to separate the material piece into a separate receiving section as the material piece is thrown / falls from the edge of the conveyor belt. When the term pusher device is used herein, it may refer to any form of device that can be activated (using pneumatic, mechanical, or other means to do so (e.g., any suitable type of mechanical extrusion mechanism (e.g., ACME screw drive), pneumatic extrusion mechanism, or air jet extrusion mechanism, etc.)) on or from a conveyor system / device to dynamically displace an object.

[0060] In addition to the N sorting receiving sections 136…139 into which material pieces 101 are turned / discharged, the material handling system 100 may also include a receiving section 140, which receives material pieces 101 that have not been turned / discharged from the conveyor system 103 into any of the N sorting receiving sections 136…139. For example, material pieces 101 may not be turned / discharged from the conveyor system 103 into one of the N sorting receiving sections 136…139 when the classification of material piece 101 cannot be determined (or simply because the sorting device could not accurately turn / discharge the piece). Thus, the receiving section 140 can serve as a default receiving section into which unclassified or unsorted material pieces are thrown. Alternatively, the receiving section 140 can be used to receive material pieces of one or more classifications that have not been deliberately assigned to any of the N sorting receiving sections 136…139. These material pieces can then be further sorted according to other properties and / or by a different material handling system.

[0061] Depending on the desired classification of material pieces, multiple classifications can be mapped to a single sorting device and / or associated sorting receiving section. In other words, a one-to-one correlation between the classification and the sorting device and / or receiving section is not required. For example, a user may desire to sort materials of a particular classification into the same sorting receiving section. To achieve this sorting, when material pieces 101 are classified to fall into a predetermined classification grouping, the same sorting device can be activated to sort them into the same sorting receiving section (or onto a different conveyor belt). Such combination sorting can be applied to produce any desired combination of sorted material pieces. The classification mapping can be programmed by the user (for example, using one of the sorting algorithms described herein, operated by a computer system 107) to produce such desired combinations. Additionally, the classification of material pieces is user-definable and is not limited to any particular known classification of material pieces.

[0062] The systems and methods described herein can be applied to classify and / or sort individual material pieces having any of various sizes. While the systems and methods described herein primarily relate to sorting individual material pieces of a singularized stream one at a time, they are not limited thereto. Such systems and methods can be used to simultaneously stimulate and / or detect emissions from multiple materials. For example, multiple singularized streams can be transported in parallel, as opposed to streams of singularized material transported in series along one or more conveyor belts. Each stream can be on the same belt or on different belts arranged in parallel. Furthermore, pieces can be randomly distributed over one or more conveyor belts (e.g., across and along one or more conveyor belts). Thus, the systems and methods described herein can be used to simultaneously stimulate and / or detect emissions from multiple of these material pieces. In other words, multiple material pieces can be treated as a single piece, as opposed to each material piece being considered individually. Therefore, multiple material pieces can be sorted and separated together (for example, turned off / discharged from a conveyor system).

[0063] The conveyor system 103 may include a recycling loop (not shown) to reroute unclassified material pieces through the material handling system 100 for rescanning and re-sorting into predetermined categories. Furthermore, since the material handling system 100 can specifically track each material piece 101 as it moves along the conveyor system 103, some sorting device (e.g., sorting device 129) can be implemented to orient / discharge material pieces 101 (or those material pieces 101 collected in the receiving section 140) that the material handling system 100 was unable to classify after a predetermined number of cycles through the material handling system 100.

[0064] With the material handling system 100 implementing the XRF system for the sensor system 120, the signal representing the detected / captured XRF spectrum can be converted into a discrete energy histogram, for example, on a per-channel (i.e., element) basis, as further described herein, which can be used to determine the amount of a particular element in the material piece. Such a conversion process can be implemented in a control system 123 or a computer system 107. In certain embodiments of this disclosure, such a control system 123 or computer system 107 may include a commercially available spectrum acquisition module (e.g., a commercially available Amptech MCA 5000 acquisition card and software programmed to operate that card). Such a spectrum acquisition module (or other software implemented in the material handling system 100) can be configured to implement multiple channels for dispersing X-rays into a discrete energy spectrum (i.e., a histogram) having multiple energy levels, where each energy level corresponds to an element configured to be detected by the material handling system 100. The material handling system 100 can be configured to have sufficient channels corresponding to specific elements in the periodic table that are important for distinguishing between different materials. Energy counts for each energy level can be stored in separate collection memory registers. The computer system 107 then reads each collection register, determines the number of counts for each energy level during the collection interval, and constructs an energy histogram.As will be described in more detail herein, a sorting algorithm configured according to a particular embodiment of this disclosure (e.g., a PCA algorithm) can then utilize this collected energy level histogram to classify (and / or assist the vision system 110 in classifying the material pieces 101).

[0065] As previously stated, certain embodiments of the present disclosure can implement one or more vision systems (e.g., vision system 110) configured (e.g., in combination with an AI system) to classify and / or distinguish material pieces. Such an AI system could be any well-known AI system (e.g., specialized artificial intelligence ("ANI"), general artificial intelligence ("AGI"), artificial superintelligence ("ASI")), machine learning systems including those that implement neural networks (e.g., artificial neural networks, deep neural networks, convolutional neural networks, recurrent neural networks, autoencoders, reinforcement learning, etc.), supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, self-learning, feature representation learning, sparse dictionary learning, anomaly detection, robot learning, association rule learning, fuzzy logic, deep learning algorithms, deep structured learning hierarchical learning algorithms, decision tree learning (e.g., classification and regression), etc. It is possible to implement machine learning systems that implement trees ("CART"), ensemble methods (e.g., ensemble learning, random forest, bagging and pasting, patch and subspace, boosting, stacking, etc.), dimensionality reduction (e.g., projection, manifold learning, principal component analysis, etc.), and / or deep machine learning algorithms (e.g., those listed on and publicly available on the deeplearning.net website (including all software, publications, and hyperlinks to available software referenced within this website)) (the deeplearning.net website is incorporated herein by reference).Some of the publicly available machine learning software and libraries that may be used in embodiments of this disclosure include, but are not limited to, Python, OpenCV, Inception, Theano, Torch, PyTorch, Pylearn2, Numpy, Blocks, TensorFlow, MXNet, Caffe, Lasagne, Keras, Qt, Ubuntu, NVIDIA drivers, Pandas, Matplotlib, github, Chainer, Matlab® Deep Learning, CNTK, MatConvNet (MATLAB® toolbox implementing convolutional neural networks for computer vision applications), DeepLearn Toolbox (MATLAB® toolbox for deep learning (from Rasmus Berg Palm)), BigDL, Cuda-Convnet (fast C++ / CUDA implementation of convolutional (or more generally, feed-forward) neural networks), Deep Belief Networks include RNNLM, RNNLIB-RNNLIB, matrbm, deeplearning4j, Eblearn.lsh, deepmat, MShadow, Matplotlib, SciPy, CXXNET, Nengo-Nengo, Eblearn, cudamat, Gnumpy, 3-way factored RBM and mcRBM, mPoT (Python code that uses CUDAMat and Gnumpy to train models on natural images), ConvNet, Elektronn, OpenNN, NeuralDesigner, Theano Generalized Hebbian Learning, Apache Singa, Lightnet, and SimpleDNN.

[0066] According to certain embodiments of this disclosure, certain types of machine learning can be performed stepwise. For example, training can take place offline, in that the material handling system 100 (or similar apparatus) is not used to perform the actual classification / sorting of material pieces. For example, the material handling system 100 (or similar apparatus) can be used to train a machine learning system, in that control samples (e.g., homogeneous sets) of material pieces (i.e., having the same type or class of material, or falling into the same predetermined fraction) are passed through the material handling system 100 (e.g., by a conveyor system 103); and all such material pieces can be collected into a common receiving section (e.g., receiving section 140) rather than being sorted. Alternatively, training can be performed at a different location remote from the material handling system 100, which involves using some other mechanism to collect sensed information (characteristics) of the control set of material pieces. During this training phase, the algorithms within the machine learning system extract features from captured information (for example, using image processing techniques well known in the art). Non-exclusive examples of training algorithms include, but are not limited to, linear regression, gradient descent, feedforward, polynomial regression, learning curves, regularized learning models, and logistic regression. During the training phase, the algorithms within the machine learning system learn the relationships between materials and their features / properties (for example, those captured by vision and / or sensor systems), generating a knowledge base for the subsequent classification of heterogeneous mixtures of material pieces accepted by the material handling system 100, which can then be sorted according to the desired classification.Such a knowledge base may include one or more libraries, each containing parameters (e.g., neural network parameters) for use by a machine learning system when classifying material pieces. For example, one particular library may contain parameters configured through a training phase to recognize and classify one or more materials that fall into a particular type or class of material, or into a predetermined fraction. According to certain embodiments of the present disclosure, such a library may be input into a machine learning system, and a user of the material handling system 100 may then be able to adjust certain parameters to adjust the operation of the material handling system 100 (e.g., adjust the threshold effectiveness of how well the machine learning system recognizes (identifies, classifies) a particular material piece from a heterogeneous mixture of materials).

[0067] Additionally, including specific chemical elements in a material piece results in identifiable physical features (e.g., visually discriminable properties) within the material. Consequently, when multiple material pieces containing such specific chemical compositions are subjected to the training steps described above, a machine learning system can learn how to distinguish such material pieces from others. Consequently, a machine learning system (or any AI system) configured according to a particular embodiment of this disclosure can be configured to sort the material pieces according to their respective material / chemical compositions. It can be readily recognized that embodiments of this disclosure can be configured to utilize image data (e.g., visual images) of a material piece as a proxy for representing one or more different physical and / or chemical attributes of the material piece (e.g., ductility, malleability, brittleness, hardness, gloss, tensile strength, reactivity with various materials, etc.).

[0068] For example, Twitch includes cast aluminum alloys and wrought aluminum alloys. These two alloys have the same color. The difference between these two alloys is their chemical composition. Cast aluminum alloys have a higher concentration of silicon as an alloying element, while wrought aluminum alloys do not have a high concentration of silicon as an alloying element, and therefore set a premium price. An AI system implemented in a vision system (e.g., vision system 110) can be configured to classify these pieces at high speed with an accuracy of over 95%. The AI ​​system can accurately classify these materials. The reason is that the difference in silicon content results in the alloys appearing physically different from one another. Cast aluminum alloys, due to their higher silicon concentration, shatter after shredding and do not bend or fold. However, wrought aluminum alloys, because they do not have a high silicon concentration, are much more malleable. Wrought aluminum alloys bend and fold during the shredding process and therefore have a visual appearance similar to torn cloth. These visual features can be trained in an AI system and ultimately attributed to the chemical properties of the alloy.

[0069] During the training phase, multiple material pieces of one or more specific types, classifications, or fractions of material (these are control samples) can be delivered through a vision system and / or one or more sensor systems (e.g., by a conveyor system) so that algorithms in the machine learning system can detect, extract, and learn what features represent such a type or class of material. For example, each of the material pieces in the control samples can first be subjected to such a training phase so that algorithms in the machine learning system can "learn" (be trained) how to detect, recognize, and classify such material pieces, and in the case of training a vision system (e.g., vision system 110), it can be trained to visually discriminate (distinguish) between material pieces. This generates a library of parameters specific to such homogeneous classes of material pieces. The same process can be carried out for images of material pieces of any classification so that a library of parameters specific to material pieces of such classification can be generated. For each type of material to be classified by the vision system, any number of exemplary material pieces of material of that classification can be passed alongside the vision system. Given captured and perceived information as input data, the algorithm within the machine learning system can use N classifiers, each of which tests one of N different material types. It should be noted that the machine learning system can be “trained” to detect any type, class, or fraction of material, including any of the material types, classes, or fractions disclosed herein.

[0070] After the algorithm is established and the machine learning system has sufficiently learned (trained) differences in material classification (e.g., visually discriminable differences) (e.g., within a user-defined level of statistical confidence), a library for different material classifications is then implemented into a material classification / sorting system (e.g., material handling system 100) to identify, distinguish, and / or classify material pieces from heterogeneous mixtures of material pieces, and then, if sorting is to be performed, to potentially sort such classified material pieces.

[0071] One point to note here is that, according to certain embodiments of this disclosure, the detected / captured features / properties (e.g., visual images) of a material piece do not necessarily have to be simply identifiable or discriminable physical properties, but could be abstract formulations that can only be expressed mathematically, or abstract formulations that cannot be expressed mathematically at all, and nevertheless, the AI ​​system can be configured to analyze spectral data to look for patterns that would allow control samples to be classified during the training phase. Furthermore, the AI ​​system can take subsections of the captured information of the material piece and attempt to find correlations between predefined classifications.

[0072] According to certain embodiments of this disclosure, instead of utilizing a training phase in which controlled (homogeneous) samples of material pieces are passed around a vision system, the training of the AI ​​system can be carried out using labeling / annotation techniques (or any other supervised learning techniques) so that when data / information of material pieces are captured by the vision system, the user inputs labels or annotations that identify each material piece, which are then used to generate a library for use by the AI ​​system when classifying material pieces in heterogeneous mixtures of material pieces. In other words, a previously generated knowledge base of properties captured from one or more samples of a class of material can be achieved by any of the techniques disclosed herein so that such a knowledge base is then used to automatically classify the materials.

[0073] Accordingly, as disclosed herein, certain embodiments of this disclosure provide identification / classification of one or more different materials to determine which material pieces should be redirected from a conveyor system or device. According to certain embodiments, machine learning techniques can be used to train (i.e., configure) a neural network to identify one or more different classes or types of materials. Images or other types of sensed information can be captured from the material (e.g., moving on the conveyor system), and based on such identification / classification of materials, the systems described herein can determine which material pieces should be allowed to remain on the conveyor system and which should be redirected / removed from the conveyor system (e.g., redirected into a collection receiving section or redirected onto another conveyor system).

[0074] Figure 2 illustrates a flowchart illustrating an exemplary embodiment of process 200 for classifying / sorting material pieces using a vision system according to a particular embodiment of the present disclosure. Process 200 can be performed to classify heterogeneous mixtures of material pieces into any combination of predetermined types, classes, and / or fractions. Process 200 can be configured to operate within any of the embodiments of the present disclosure described herein (including the material handling system 100 in Figure 1, and those relating to “vision checks” as described with respect to Figures 7A–7C and Figures 12A–12B). The operation of process 200 can be performed by hardware and / or software, including within a computer system (e.g., computer system 3400 in Figure 11) that controls the system (e.g., computer system 107 and / or vision system 110). In process block 201, material pieces are fed through the vision system (e.g., on a conveyor system). In process block 202, the location of each material piece on the conveyor system can be detected to track each material piece as it moves through the material handling system 100. This can be done by the vision system 110 (for example, by distinguishing the material piece from the conveyor system material below while communicating with a conveyor system position detector (e.g., position detector 105)). Alternatively, a material piece tracking device 111 can be used to track the piece. Or, any system can have a detector that can generate a light source (including but not limited to visible light, UV, and IR) and can be used to locate the material piece. In process block 203, when a material piece moves close to one or more of the vision systems, sensed information / characteristics of the material piece are captured / acquired.In process block 204, the vision system can perform preprocessing of the captured information, which can be used to detect (extract) information about each material piece (e.g., from the background (e.g., the conveyor belt); in other words, preprocessing can be used to identify differences between material pieces and the background). Well-known image processing techniques (e.g., dilation, thresholding, and contouring) can be used to identify material pieces as clearly distinguishable from the background. In process block 205, segmentation can be performed. For example, the captured information may include information about one or more material pieces. Additionally, a particular material piece may be positioned over a conveyor belt joint when its image is captured. Therefore, in such cases, it may be desirable to isolate the image of individual material pieces from the background of the image. In an exemplary technique for process block 205, the first step is to apply high contrast to the image, in which background pixels are reduced to substantially all black pixels and at least some of the pixels relating to the material piece are brightened to substantially all white pixels. The image pixels of the white material piece are then expanded to cover the entire size of the material piece. After this step, the location of the material piece is a high-contrast image of all white pixels on a black background. A contouring algorithm can then be used to detect the boundaries of the material piece. The boundary information is saved and then the boundary locations are transferred to the original image. Segmentation is then performed on the original image in areas larger than the previously defined boundaries. In this technique, the material piece is identified and separated from the background.

[0075] In an optional process block 206, material pieces can be transported along a conveyor system in the vicinity of a material piece tracking device (or profilometer) to determine the size and / or shape of the material pieces (which may be useful in assisting the classification of specific materials due to their shape or size, or if an XRF system or some other spectroscopic sensor is implemented in the material handling system). In process block 207, post-processing can be performed. Post-processing may involve resizing the captured information / data and preparing it for use in a neural network. This may also include modifying specific properties (e.g., enhancing image contrast, changing the image background, or applying filters) in a manner that produces an enhancement to the AI ​​system's ability to classify material pieces. After image post-processing, normalization can be performed in process block 208. In process block 209, the data can be resized. Data resizing may be desired under certain circumstances to meet the data input requirements for a particular AI system (e.g., a neural network). For example, a neural network may require an image size much smaller than that of an image captured by a typical digital camera (e.g., 225 x 255 pixels or 299 x 299 pixels). Furthermore, the smaller the input data size, the less processing time is required to perform classification. Therefore, smaller data sizes can ultimately increase the throughput of the material handling system 100 and thus increase its value.

[0076] In process blocks 210 and 211, identification / classification is performed for each material piece based on perceived / detected features. For example, process block 210 can be configured with a neural network using one or more algorithms that compare extracted features with those stored in a previously generated knowledge base (e.g., generated during the training phase), and assign the classification with the highest degree of match to each material piece based on such comparisons. The algorithms can process the captured information / data in a hierarchical manner by using automatically trained filters. The filter responses are then successfully combined at the next level of the algorithm until probabilities are obtained in the final step. In process block 211, these probabilities can be used for each of the N classifications to determine how each material piece should be sorted. For example, each of the N classifications can be assigned to one sorting receiver (or on another identified conveyor belt), and the material piece under consideration is sorted into that receiver (or another identified conveyor belt) corresponding to the classification that returns the highest probability greater than a predefined threshold. In embodiments of the present disclosure, such predefined thresholds can be pre-set by the user. A particular material piece can be sorted into an outlier receiving section (or onto another identified conveyor belt) if none of the probabilities are greater than a predetermined threshold.

[0077] Next, in process block 212, sorting devices corresponding to one or more classifications of material pieces can be activated (for example, an instruction is sent to a sorting device to sort the material pieces). As will be described in relation to various aspects of Figures 7A-7C and 12A-12B, such sorting instructions can be based solely on classification by a vision system (also referred herein as “vision check”) or on a combination of classification from the vision system and a sensor system (also referred herein as “sensor system classification”). Between the time an image of a material piece is captured and the time the sorting device is activated, the material piece has moved from the vicinity of the vision system to a downstream location on the conveyor system (for example, at the conveying rate of the conveyor system). In embodiments of the present disclosure, the activation of a sorting device is timed to occur when a material piece passes a sorting device mapped to the classification of the material piece, so that the material piece is redirected / discharged (sorted) from the conveyor system into its associated sorting receiving section (or, optionally, onto another conveyor belt). In embodiments of the present disclosure, the activation of a sorting device can be timed by a position detector that detects when a material piece passes in front of the sorting device and sends a signal to enable the activation of the sorting device. In process block 213, a sorting receiving section (or another conveyor belt) corresponding to the activated sorting device receives the sorted material piece.

[0078] According to alternative embodiments of the present disclosure, an AI system used to classify material pieces can be periodically or even continuously updated with newly acquired image data collected by a vision system as it classifies the material pieces. In other words, when new image data is collected by the vision system, it is used to update one or more AI models in the AI ​​system, for example, if the classification accuracy is increased.

[0079] Figure 3 illustrates a flowchart illustrating an exemplary embodiment of a process 300 for classifying and / or sorting material pieces using a sensor system 120 according to a particular embodiment of the present disclosure. Process 300 can be configured to operate in any of the embodiments of the present disclosure described herein, including the material handling system 100 of Figure 1, and embodiments of process 700 described with respect to Figures 7A–7C, or embodiments of process 1200 described with respect to Figures 12A–12B. According to a particular embodiment of the present disclosure, process 300 can be configured to operate in conjunction with process 200. For example, process blocks 303–305 can be incorporated into process 200 to combine the work of one or more vision systems (e.g., vision system 110) with one or more sensor systems (e.g., sensor system 120) (for example, operating in series or in parallel with process blocks 203–210).

[0080] The operation of process 300 can be carried out by hardware and / or software, including within a computer system (e.g., computer system 3400 in Figure 11) that controls the system (e.g., sensor control unit 123 and / or computer system 107 in Figure 1). In process block 301, material pieces are fed along a conveyor system. Next, in an optional process block 302, the material pieces can be transported along the conveyor system in the vicinity of material piece tracking devices, profilometers, and / or optical imaging systems in order to track each material piece and / or to determine the size and / or shape of the material pieces. In process block 303, when the material pieces have moved in the vicinity of a sensor system, the material pieces can be examined (or stimulated) by EM energy (waves) or some other type of stimulus appropriate for a particular type of sensor technology utilized by the sensor system. In process block 304, the physical properties of the material pieces (e.g., captured XRF spectrum) are sensed / detected and captured by the sensor system. In process block 305, the material type is identified / classified based on captured properties, which can be combined with classification by an AI system in conjunction with the vision system 110 (as described, for example, with respect to various aspects in Figures 7A-7C and Figures 12A-12B).

[0081] Next, when sorting of material pieces is to be performed, a sorting device corresponding to the classification of the material piece is activated in process block 306. Between the time the material piece is sensed and the time the sorting device is activated, the material piece moves at the conveying rate of the conveyor system from the vicinity of the sensor system to a downstream location on the conveyor system. In certain embodiments of the disclosure, the activation of the sorting device is timed so that the sorting device is activated when the material piece passes a sorting device mapped to the classification of the material piece, and the material piece is turned / discharged from the conveyor system into its associated sorting receiving section (or onto another conveyor belt). In certain embodiments of the disclosure, the activation of the sorting device can be timed by a position detector that detects when a material piece passes in front of the sorting device and sends a signal to enable the activation of the sorting device. In process block 307, a sorting receiving section (or another conveyor belt) corresponding to the activated sorting device receives the turned / discharged material piece.

[0082] As can be easily recognized and as will be further disclosed in relation to Figures 7A-7C and 12A-12B, process blocks 203-211 are implemented in parallel with process blocks 303-305 (and process block 302, if necessary) within the material handling system 100, enabling the achievement of various classifications / sortings as described in relation to Figures 7A-7C and 12A-12B.

[0083] Referring to Figures 4–6, systems and processes configured according to specific embodiments of this disclosure are illustrated in which material (e.g., scrap pieces) can be sorted. Such material may result from shredded EOL products (e.g., vehicles, aircraft, and / or electrical appliances). Referring to Figure 4, the material (which may have been shredded into scrap) can be sorted into ferrous and non-ferrous materials. For example, magnets can be used to remove ferrous material pieces. The remaining non-ferrous materials can typically include non-ferrous metals (often referred to as solber) and other “junk” or “fluff” materials (e.g., fabrics, leather, foamed rubber, rubber, plastics, wood, PCBs, glass, coins, and any other non-metallic materials).

[0084] According to certain embodiments of this disclosure, for example, as disclosed with reference to Figures 7A–7C and 12A–12B, the solber can then be separated (sorted / sorted) from the junk material (see, for example, process blocks 701–703). The solber can contain one or more of various metals or metal alloys (e.g., copper, brass, zinc, stainless steel, lead, nickel alloys, gold or silver (e.g., located in PCBs)), aluminum (including, but not limited to, cast, wrought, and / or extruded alloys, high-Z (high zinc concentration) cast aluminum alloys (e.g., cast aluminum alloys 319 and 380 / 383) and / or low-Z (low zinc concentration) cast aluminum alloys (e.g., cast aluminum alloys 356 and 360)).

[0085] According to certain embodiments of the present disclosure, the Zorba can be sorted / sorted to separate heavier metals (also referred to as zebra or "heavy") from lighter metals (e.g., twitch) (see, for example, process blocks 704-721 in Figures 7A-7B).

[0086] Certain alternative embodiments of this disclosure may be configured to separate “meatballs” and / or airbag canisters from a material stream. See, for example, U.S. Patent Application Publication 2022 / 0371057, which is incorporated herein by reference.

[0087] According to certain embodiments of this disclosure, Figure 5 schematically illustrates how one or more different combinations of one or more vision systems (e.g., implementing an AI system) and / or one or more sensor systems (e.g., an XRF system) may be utilized so that zebras can be sorted / sorted to extract different metals (e.g., copper, zinc, brass, stainless steel, nickel-plated, lead, etc.) separately from a stream of material pieces being transported. Alternatively, any other of the disclosed sensor systems 120 (e.g., LIBS, XRT, etc.) may be utilized instead of the XRF system.

[0088] According to certain embodiments of this disclosure, Figure 6 schematically illustrates how one or more different combinations of one or more vision systems (e.g., implementing an AI system) and / or one or more sensor systems (e.g., an XRF system) may be utilized, such that the twitch can be separated into various desired classifications of cast, extruded, and / or wrought aluminum alloys. Alternatively, any other of the disclosed sensor systems 120 (e.g., LIBS, XRT, etc.) may be utilized instead of the XRF system.

[0089] Figures 7A–7C illustrate flowcharts of a process 700 configured according to one or more embodiments of the present disclosure, in which a material handling system classifies and sorts various materials (e.g., a stream of material pieces transported by a conveyor system) using a unique combination of classification by one or more vision systems (e.g., implementing an AI system) and classification by one or more sensor systems (e.g., an XRF or LIBS system). Process 700 (or any aspect or part thereof) can be implemented in any material handling system (including, but not limited to, the material handling systems described with respect to Figures 1–3, 8, 9A–9B, and 10) appropriately configured to perform one or more of the various classification and sorting operations described, utilizing the classification and / or sorting functions, operations, systems, apparatus, and devices described with respect to Figures 1–3. While certain process blocks are described as utilizing an XRF system, any one or more of such process blocks can be implemented by any of the sensor systems described herein (e.g., LIBS, XRT, etc.). It should be noted that one or more of the various process blocks in process 700 can be optional or omitted according to the particular embodiment of this disclosure.

[0090] In the flowcharts of Figures 7A–7C (and also relating to specific aspects of Figures 12A–12B), the following legend applies to the measurements performed by the XRF system (resulting in captured XRF spectra for each material piece):

[0091] Variable legend M-Total = Sum of raw counts from measured values ​​of Ti, Cr, Mn, Fe, Ni, Cu, Zn, Sn, and Pb. N-Total = Total count after normalization by the length and height (or mass) of the material pieces. Calculated XRF elemental percentages for each material piece: TI = 100 × raw titanium count / M-Total CR = 100 × raw chromium count / M-Total MN = 100 × raw count of manganese / M - Total FE = 100 × raw iron count / M-Total NI = 100 × raw nickel count / M - Total CU = 100 × raw copper count / M - Total ZN = 100 × raw zinc count / M - Total SN = 100 × raw count of tin / M-Total PB = 100 × raw lead count M-Total Predetermined setpoints (values) for the XRF elemental percentage for each material piece: TIK, CRK, MNK, FEK, NIK, CUK, ZNK, SNK, and PBK represent the XRF classification percentage constants for each element (these can be any predetermined value set between 0.0 and 100.0). Other predetermined setting points (values): AK = 0.4 × N-Total for 319 standard cast alloys (a constant value for N-Total calculated from the 319 standard to determine the casting category versus the wrought category; 1 to 100,000) BK = 0.1 × CU / ZN ratio relative to the 319 standard (a ratio value calculated from the 319 standard to determine the casting category versus the die-cast zinc category; ratio 0.0 to 1.0) CURB = The ratio chosen to select between copper and brass (it can be a value between 0.8 and 1.0 fractions; it can be set to a non-limiting exemplary default value of 0.9 (predetermined)). CUYB = the ratio chosen for yellow brass versus red brass (it can be a value between 0.3 and 0.8 fractions; it can be set to a non-limiting exemplary default value of 0.5 (predetermined)). MNSS = A set (predetermined) value for classifying the manganese content in 2xx series stainless steel (it can be a value between 10 and 30).

[0092] The spectral data resulting from the XRF system can be normalized with respect to the piece size. This step can be optional. This can be done by determining the XRF signal level according to the piece size, and then calibrating the classification to normalize with respect to the piece size.

[0093] Process 700 is described as operating on a piece-by-piece basis; naturally, when one material piece in the stream of material pieces being transported is operated by a particular process block, subsequent material pieces can then be handled by that process block (for example, when one material piece is analyzed / classified by a vision system and / or XRF system, subsequent material pieces can then be analyzed / classified by a vision system and / or XRF system). Note that the flowcharts in Figures 7A-7C show multiple process blocks where “Vision Check” is performed, and other diamond-shaped process blocks represent the analysis of material pieces by an XRF system. Note that “Vision Check” can be performed by any suitable vision system, including but not limited to a vision system implementing appropriately configured AI techniques. Each vision check classifies the material piece in accordance with processing the visual image captured from each material piece through the AI ​​system. Furthermore, it should be noted that one or more of the "vision checks" implemented in Process 700 can be performed on image data captured from a material piece by a single vision system implementing one or more different AI algorithms (models) for each vision check. Similarly, one or more of the XRF sensor system classifications implemented in Process 700 can be performed on spectral data captured from a material piece by a single XRF system.

[0094] To perform the operations within these process blocks, any number of vision systems and / or XRF systems can be implemented, but they can all be performed by a single vision system and / or a single XRF system (or any combination of one or more vision systems and one or more XRF systems) implemented within the material handling system (see, for example, Figure 8). For example, as each material piece passes by a single implemented vision system, the image data of the material piece captured by the single vision system can be analyzed (for example, substantially simultaneously or in parallel) according to one or more of the process blocks 701, 704, 718, and 721. In other words, algorithms associated with one or more of the process blocks 701, 704, 718, and 721 can process the captured image data (for example, substantially simultaneously or in parallel with one or more AI models), and the results are used for their respective classifications. Similarly, XRF spectral data captured by a single implemented XRF system can be analyzed according to one or more of the process blocks 705, 707, 709, 710, 712, 715, 717, 722, 725, 727, and 729 (for example, substantially simultaneously or in parallel by one or more algorithms).

[0095] Furthermore, note that each vision check described in process 700 represents an attempt by its specifically described algorithm to perform its classification for each material piece in the material stream, however, a vision check for a particular material piece may produce a “null” result, meaning that the particular vision check was unable to produce a classification (for example, a vision check by process block 718 or 721 may produce a “null” output because the material piece is neither cast aluminum alloy nor wrought aluminum alloy). Similarly, note that each classification using XRF spectral data described in process 700 represents an attempt by its specifically described algorithm to perform its classification for each material piece in the material stream, however, a classification for a particular material piece may produce a “null” result, meaning that the particular XRF sensor system classification was unable to produce a classification (for example, an XRF sensor system classification by any of process blocks 705, 707, or 722 may produce a “null” output because the material piece did not contain a measurable amount of zinc).

[0096] It should be noted that any of the vision checks described in Figures 7A to 7C can be performed according to process blocks 203 to 211 of process 200 described in relation to Figure 3. Any of the classifications performed by the XRF system (or any other suitable sensor system) in Figures 7A to 7C can be performed according to process blocks 303 to 305 of process 300 described in relation to Figure 4.

[0097] As will be further described herein, certain aspects of process 700 (i.e., classification and / or sorting implemented within one or more process blocks) may require to be carried out in one or more specific sequences in order to enable those aspects of process 700 to be carried out more efficiently and / or more accurately. Material pieces may be analyzed / classified by a single vision system and a single XRF system (including being analyzed / classified substantially simultaneously or in parallel), but it should be noted that the sorting of various material pieces may require to be carried out in specific sequences (e.g., along a conveyor belt), as will be further described herein.

[0098] Process 700 is described in relation to the classification and sorting of a stream of material being transported, including solbers, zebras, and / or twitches, but embodiments of Process 700 may also be applicable to the classification and / or sorting of other types of material pieces.

[0099] In process block 701, a vision check is performed on a material piece to determine whether it should be classified as some predetermined specific material (e.g., “junk” material associated with the Zorba). If the vision check classifies the material piece as a predetermined specific material, then in process block 702, process 700 sends an instruction to an identified sorting device to separate the material piece (e.g., from the stream of material pieces being transported) according to its classification (e.g., a material piece made of or containing PCBs). Process block 703 indicates that process blocks 700-702 can be performed for any other type of material piece (e.g., other “junk” material) that the user wishes to separate from the stream of material pieces, which can be classified by a vision system (e.g., a vision check using any of the vision-related techniques described herein, including but not limited to artificial intelligence ("AI") techniques). This can be achieved by a series of different vision systems, or a single vision system can be configured to perform classification in a substantially simultaneous or parallel manner with respect to any multiple predetermined types of material pieces (for example, image data captured by a vision system with respect to a single material piece is then analyzed (substantially simultaneously and / or in parallel with each other) by one or more AI algorithms to classify whether the material piece belongs to one of multiple predetermined types of material pieces (e.g., a predetermined set of "junk" materials)).

[0100] It should be noted that the implementation configuration of process blocks 701-703 within process 700 may be arbitrary. When process blocks 701-703 are implemented, it may be important to perform the sorting indicated by these process blocks before the sorting indicated by one or more of the other process blocks in process 700 in order to improve the efficiency of the subsequent sorting of material pieces. For example, sorting various materials from the material stream (as sorted in process blocks 701 and 703) may be important before performing the sorting of other metals and / or metal alloys (as sorted in one or more subsequent process blocks in process 700) (e.g., removing "junk" material before sorting the remaining Zorba). For example, removing "junk" material from the material stream before other materials can reduce the possibility of such "junk" material contaminating the material to be sorted later. In non-limiting examples, PCBs very often contain layers of copper, and XRF sensors may misclassify such PCBs as copper scrap pieces. However, vision systems can be configured to distinguish green PCBs from red copper metal with considerable accuracy. Consequently, since classification of such PCBs by XRF systems may result in them being sorted as copper scrap pieces, it may be advantageous to use vision checks to classify such PCBs so that they can be sorted out from the material stream.

[0101] Here, process blocks 704–731 will be described in relation to the classification and sorting of materials that may typically be found in a Zorba (also referred to herein as “Zorba material”). According to certain embodiments of this disclosure, process blocks 704–716 can be configured to classify / sort zebra material from a Zorba.

[0102] In process block 704, a vision check may be performed on a material piece to determine whether it should be classified as substantially composed of or containing copper and / or brass. This can be achieved by a vision system (for example, using any of the vision-related techniques described herein, including but not limited to AI techniques) because copper and brass pieces often have distinctive colors and / or shapes (for example, a vision system can be trained to classify a particular pipe-shaped material as composed of or containing copper).

[0103] If a material piece is classified by process block 704 as being composed of or containing copper and / or brass, then process 700 can further utilize the XRF sensor system classification of the material piece in process block 705 to distinguish between copper and brass pieces. Since brass typically contains a specific ratio of copper (Cu) to zinc (Zn) (e.g., about 60% Cu, about 40% Zn), a material piece will be classified as a copper piece when the ratio of the relative amount of copper to zinc is greater than a predetermined value (e.g., when the ratio of the value CU / Zn is greater than a predetermined value (CURB); CURB has been empirically determined to be between 0.8 and 1.0 according to certain non-limiting embodiments of this disclosure). In other words, if the ratio of the calculated CU value to the calculated Zn value in the captured XRF spectrum of a material piece is greater than the CURB value, then the material piece will be classified as copper rather than brass. Therefore, if CU / ZN > CURB, then in process block 706, process 700 instructs the identified sorting device to sort material pieces from the material stream as copper pieces.

[0104] However, if the material piece is classified as a brass piece by process block 705, then in process block 707, process 700 can make a further determination as to whether the material piece is composed of yellow brass or red brass based on the captured XRF spectrum of the material piece. This can be done by analyzing whether the ratio of the relative amount of copper to zinc is greater than a second predetermined value (for example, the value CU / ZN against a predetermined CUYB value; the CUYB value has been empirically determined to be between 0.3 and 0.8 according to certain non-limiting embodiments of this disclosure). If the material piece is classified as being composed of or containing red brass, then in process block 708, process 700 sends an instruction to the identified sorting device to sort the material piece as red brass material. If the material piece is classified as being composed of or containing yellow brass, then in process block 790, process 700 sends an instruction to the identified sorting device to sort the material piece as yellow brass material.

[0105] The combination of process blocks 705-708 and 790 makes it readily apparent that a material piece can be classified as being composed of yellow brass if it contains a certain amount of zinc relative to copper. Red brass is typically composed of approximately 85% Cu and 15% Zn, while yellow brass is typically composed of approximately 60-70% Cu and 30-40% Zn.

[0106] It can be more easily recognized that (1) the combination of the vision check of process block 704 and the XRF sensor system classification of process block 706 can be used to separate copper scrap pieces from the material stream, (2) the combination of the vision check of process block 704 and the XRF sensor system classification of process block 706 can be used to separate copper and brass scrap pieces from the material stream, (3) the combination of the vision check of process block 704 and the XRF sensor system classification of process block 707 can be used to separate brass scrap pieces from the material stream, (4) the combination of the vision check of process block 704 and the XRF sensor system classification of process blocks 706 and 707 can be used to separate red and yellow brass scrap pieces from the material stream, and (5) the combination of the vision check of process block 704 and the XRF sensor system classification of process blocks 706 and 707 can be used to separate copper and red / yellow brass scrap pieces from the material stream.

[0107] It should be noted that process blocks 705-708, 790 can be optionally implemented in process 700 (for example, when it is known that the material pieces to be sorted do not contain copper and / or brass). Furthermore, one or more of process blocks 705-708, 790 can be optionally omitted (or appropriately modified in a manner consistent with embodiments of the present disclosure as described herein) if it is known that the material pieces to be sorted do not contain any one or more of copper, red brass, or yellow brass. Furthermore, it should be noted that process 700 can be configured so that non-copper / brass materials having a copper or brass color (or being shaped like a copper tube) are not classified / sorted as copper / brass pieces (for example, process block 704 is modified accordingly), because they would not be classified as such as a result of implementing process blocks 705-708, 790, which utilize XRF sensor system classification to achieve the classification of copper / brass pieces for sorting from Zorba.

[0108] Furthermore, it may be important to perform the sorting of material from the material stream indicated by process blocks 706, 708, and / or 790 before the sorting indicated by one or more of process blocks 723-724, for the reason that these process blocks also rely on the classification of material pieces as a function of the CU / ZN ratio (process block 722), so that such material pieces do not contaminate the sorted material resulting from either or both of process blocks 723 and 724. Also, for similar reasons (for example, since a copper-containing material piece is likely to contaminate 2xxx pieces sorted by process block 727, and a zinc-containing material piece is likely to contaminate 7xxx pieces sorted by process block 728), it may be important to perform the sorting indicated by process blocks 706, 708, and / or 790 before the sorting indicated by either or both of process blocks 726 and / or 728.

[0109] According to certain embodiments of this disclosure, various combinations of process blocks 709–714 can be implemented to sort and separate nickel (Ni) plated materials and / or stainless steel ("SS") materials from a stream of material pieces. Process 700 can be configured to do so because these materials have a relatively higher concentration of nickel than the aluminum alloys to be subsequently sorted. It should be noted that process block 709 is implemented as sorting using a sensor system other than vision check (e.g., XRF) due to the possibility that nickel Ni plated material pieces and / or SS material pieces may look visually similar to certain types of aluminum materials (cast and / or drawn). Furthermore, because certain shredded pieces of such Ni plated or stainless steel material may look visually similar to certain cast and / or drawn aluminum pieces, it may be important to sort these material pieces before sorting the aluminum alloys so that such nickel plated and / or stainless steel materials do not contaminate the sorting / separation of one or more different aluminum alloys.

[0110] In process block 709, a determination is made as to whether the captured XRF spectrum of a material piece indicates that the material piece contains an amount of chromium (Cr) greater than a predetermined threshold. This can be carried out when it is known that the aluminum alloy to be sorted by process 700 has a chromium concentration lower than a known or predetermined value (e.g., a predetermined CRK value). Thus, based on a known or predetermined CRK value, a material piece can be sorted from the material stream when the value CR is greater than the value CRK. According to a particular embodiment of this disclosure, and depending on the material to be sorted downstream (and subsequently sorted), materials classified as having a predetermined amount (i.e., concentration) of chromium can be sorted from the stream of material pieces. It should be noted that this can be carried out with respect to any element known to be present in a particular material piece to be sorted.

[0111] If the results of process block 709 are positive, then process 700 can further utilize the XRF sensor system classification of the material piece by process block 710 to further distinguish between Ni-plated material and SS material. Process block 710 determines whether the relative content of nickel to chromium in the material piece is greater than a predetermined ratio, which in this non-limiting example is determined from the calculation NI / CR>1. This is because a typical XRF system is only effective at measuring X-ray fluorescence to a relatively small depth in the surface of the material piece, and therefore the XRF system will read a much larger content of nickel in the nickel plating on the surface of the material piece, and also because 2xx and 3xx stainless steels contain substantially less nickel than chromium.

[0112] If a material piece is classified as Ni-plated, then in process block 711, the instruction is sent to a specified sorting device to sort the material piece accordingly. Otherwise, process 700 then proceeds to process block 712, where it is possible to determine whether the manganese (Mn) content is greater than a predetermined or known amount, which in this non-limiting example is a value between 10 and 30, and which can be set to classify the manganese content (MN) in 2xx series stainless steel.

[0113] It should be noted that the determining factor for whether a material piece is composed of 2xx series stainless steel or 3xx series stainless steel is the amount of manganese. Therefore, if MN > MNSS, the material piece is then classified as 2xx series stainless steel (e.g., 201, 202); otherwise, the material piece is classified as 3xx series stainless steel (e.g., 301, 302, 304, 316). In process block 713, if the material piece is classified as 2xx series stainless steel, an instruction is then sent by process 700 to the identified sorting device to sort the material piece accordingly. In process block 714, if the material piece is classified as 3xx series stainless steel, an instruction is then sent by process 700 to the identified sorting device to sort the material piece accordingly.

[0114] (1) The combination of XRF sensor system classification of process blocks 709 and 710 can be used to separate Ni-plated pieces from the material stream, (2) The combination of XRF sensor system classification of process blocks 709 and 710 can be used to separate SS pieces from the material stream, (3) The combination of XRF sensor system classification of process blocks 709 and 710 can be used to separate Ni-plated pieces and SS pieces separately from the material stream, (4) The combination of XRF sensor system classification of process blocks 709, 710, and 712 can separate SS pieces It can be used to sort from the material stream, and (5) the combination of XRF sensor system classification of process blocks 709, 710, and 712 can be used to sort SS pieces from the material stream into separate groups of SS201 / 202 and SS301, 302, 304, and 316, and (6) the combination of XRF sensor system classification of process blocks 709, 710, and 712 can be used to sort Ni-plated pieces and SS pieces (further separated into groups of SS201 / 202 and SS301, 302, 304, and 316) separately from the material stream. In addition, all of the above combinations can also include (1) a vision check of process block 704, and / or (2) a vision check of process blocks 701 / 703.

[0115] In process block 715, a determination is made as to whether the captured XRF spectrum of the material piece indicates that the material piece contains an amount of lead (Pb) greater than a predetermined threshold. This can be done when it is known that the material piece to be sorted by process 700 has a lead concentration lower than a known or predetermined value (e.g., a predetermined PBK value). Thus, based on a known or predetermined PBK value, the material piece can be sorted when the value PB is greater than the value PBK. In process block 716, process 700 sends an instruction to an identified sorting device to sort the material piece (e.g., from a stream of material pieces being transported) according to its lead classification. Note that, according to certain embodiments of this disclosure, the sorting resulting from process blocks 704, 709, and 715 can be performed in different orders relative to each other (e.g., where it is known that doing so will improve the accuracy and / or efficiency of sorting one or more of the materials). According to embodiments of this disclosure, the implementation of process blocks 715-716 is optional.

[0116] Furthermore, a stream of materials to be classified / sorted may contain other materials that can be classified based on having a unique (specific) chemical composition or signature (e.g., containing a specific element, metal, and / or alloying element). In such cases, the sorting of these materials may be carried out before the sorting of materials composed of more complex chemical compositions or signatures, where such unique chemical compositions or signatures may contaminate the classification of materials composed of more complex chemical compositions or signatures (and thus reduce the accuracy or efficiency of the sorting of such materials). Therefore, it may be important to separate these materials with such unique chemical compositions or signatures so that they are not inadvertently sorted (not contaminated) into the receiving area for materials composed of more complex chemical compositions or signatures. For example, process 700 can be configured to sort out any material known to be present in the zebra before sorting the twich material (for example, if it is known that doing so in that order would improve the accuracy and / or efficiency of sorting one or more specific twich materials). Alternatively, according to certain embodiments of the present disclosure, process 700 can be configured to sort out any material known to be present in the twich before classification and sorting of specific zebra materials (for example, if it is known that doing so in that order would improve the accuracy and / or efficiency of sorting one or more specific zebra materials).

[0117] According to certain embodiments of this disclosure, it may be advantageous or desirable to perform sorting based on process blocks 717-731 after one or more of the previously described process blocks. This is because XRF technology is known to be very poor at distinguishing between specific aluminum alloys (for example, the presence of any one or more of the various zebra materials (e.g., the copper, brass, Ni-plated materials, and SS materials mentioned above) may negatively or adversely affect the XRF measurements in process blocks 717-731). For example, pieces of die-cast zinc look very similar to certain aluminum alloys and therefore cannot be visually distinguished from one another based solely on a visual check. However, XRF systems can easily distinguish between die-cast zinc and aluminum. Therefore, it may be advantageous to sort and separate the die-cast zinc (see process block 724) before processing other aluminum pieces (e.g., any one or more of the process blocks 725-731). Additionally, material pieces that are substantially larger than other material pieces in the stream (for example, in size and / or mass) may have relatively large zinc peaks in the captured XRF spectrum, which could result in such material pieces being misclassified as 7xxx series aluminum alloys. Therefore, it may be advantageous or desirable to perform sorting based on process blocks 721-724 before sorting based on process blocks 727-728.

[0118] It should be noted that the captured XRF spectra of wrought aluminum pieces (also known as sheet aluminum) will have a relatively lower total captured raw count than similarly sized cast aluminum pieces, because cast aluminum contains relatively large amounts of copper and zinc, resulting in a relatively large total captured raw count. An exception to the above is the 356 and 360 series cast aluminum alloys, which have relatively lower concentrations of copper and zinc. Therefore, process blocks 717-720 are configured to identify (classify) and sort 356 and / or 360 series cast aluminum pieces, which, like wrought aluminum, have relatively lower amounts of copper and zinc. Otherwise, 356 and / or 360 series cast aluminum pieces may be misclassified and therefore sorted as wrought aluminum (for example, in process block 721). Therefore, it may be advantageous to perform sorting based on process blocks 717-719 before sorting based on process block 721.

[0119] In process block 717, a determination is made as to whether the total captured XRF spectral count (N-Total) for the material piece (after being normalized by the length and height (or mass) of the piece) is greater than a predetermined constant value (AK). According to certain embodiments of the present disclosure, this constant value can be set as 0.4 × N-Total for 319 standard cast aluminum alloy (as determined, for example, by the Aluminum Association). According to certain embodiments of the present disclosure, process block 717 can determine whether the measured amounts of copper and zinc in the scrap piece are greater than a predetermined value. For classifications that do not meet the standards described by the classification of process block 717 (i.e., the total captured XRF count is relatively low, or the measured amounts of copper and zinc in the scrap piece are less than a predetermined value), process 700 can then utilize a vision check by process block 718 to determine whether the material piece is composed of wrought aluminum or cast aluminum. If a material piece is not classified as a wrought aluminum piece, then in process block 719 it will be classified as a 356 and / or 360 cast aluminum piece, and instructions will be sent to the identified sorting device to sort the material piece accordingly.

[0120] Accordingly, according to embodiments of the present disclosure, process 700 can be configured such that if process block 717 determines that N-Total ≤ AK and the vision check classifies the material piece as a cast aluminum piece, the instruction sent by process block 719 sorts the material piece so that it is classified as 356 / 360 cast aluminum material; otherwise, the material piece remains on the main conveyor belt for sorting / classification by subsequent process blocks 721-731. Thus, it can be readily recognized that process 700 can be configured by a combination of process blocks 717 and 719 so that the material piece is sorted so that it is classified as 356 / 360 cast aluminum material. In addition, the aforementioned combination can also include (1) a vision check by process block 704 and / or (2) a vision check by process blocks 701 / 703 and / or (3) XRF classification by process block 709.

[0121] According to alternative embodiments of the present disclosure, if a material piece is classified as a wrought aluminum piece by process block 718, then in process block 720, an instruction can be sent by process 700 to a specified sorting device to sort the material piece accordingly.

[0122] According to a further alternative embodiment of the present disclosure, such material pieces, classified as wrought aluminum pieces, can instead be redirected and / or returned to the main conveyor belt in some suitable manner at process block 720 for classification / sorting by subsequent process blocks in process 700. This can be carried out by accumulating and returning these material pieces on the starting point of the material handling system and then deactivating process block 717, or by a return conveyor belt or circular conveyor belt that returns these material pieces to a location on the conveyor belt downstream from the sorting location associated with process blocks 719 and 720.

[0123] According to alternative embodiments of the present disclosure, the AK value can be predetermined (including predetermined on an empirical basis) to sort (but not sort) specific wrought aluminum alloys in process block 717. In other words, the AK value can be adjusted as required to achieve a desired sorting / sorting result. According to certain embodiments of the present disclosure, the AK value can be set so that a predetermined percentage of wrought aluminum pieces are allowed to pass through process block 717 to process block 721.

[0124] It should be noted that, according to alternative embodiments of this disclosure, further classification and sorting (e.g., by an XRF or LIBS system) may be performed to classify / sort between 356 cast aluminum alloys and 360 cast aluminum alloys (e.g., as a modification and / or addition to process block 719 according to the embodiments disclosed herein). For example, process 700 may be modified to include process blocks 1216-1218 as described with respect to Figures 12A-12B (e.g., process block 719 may be modified by or replaced by process blocks 1216-1218).

[0125] Since 319 and 38x cast aluminum alloys have a material composition represented by a relatively large copper peak compared to zinc, as captured in the XRF spectrum (copper concentration approximately 3-4%; zinc concentration <1%), process blocks 721-724 are implemented in process 700 to separate these alloys from the die-cast zinc metal pieces (or all other cast aluminum alloys remaining in the stream of material pieces). Note that, according to alternative embodiments of the present disclosure, the material handling system can be configured so that all cast aluminum alloy pieces not classified as either 319 / 38x and / or die-cast zinc metal pieces are collected in a catch-all receiving section (for example, in response to classification by process block 722, the process sends an instruction to a sorting device to separate such cast aluminum alloy pieces from the 319 / 38x and / or die-cast zinc metal pieces).

[0126] In process block 721, the vision check can be configured to perform a classification between cast aluminum alloys and wrought aluminum alloys. With respect to those material pieces classified as cast aluminum, process 700 can be configured to perform a further classification of each such material piece by process block 722, thereby determining whether the captured XRF spectrum of the material piece indicates that the material piece has a copper concentration relatively higher than the zinc concentration (for example, as previously described with respect to process blocks 705 and 707). For example, it is possible to determine whether the ratio of the value CU / Zn is greater than a predetermined value BK, where the value BK can be predetermined to be 0.1 × CU / Zn in this non-limiting example.

[0127] If the answer is "yes," the material piece is then classified as a 319 / 38x cast aluminum piece, and in process block 723, process 700 sends an instruction to the identified sorting device to sort the material piece accordingly. Otherwise, the material piece is classified as a die-cast zinc piece, and in process block 724, process 700 sends an instruction to the identified sorting device to sort the material piece accordingly. Therefore, it can be readily recognized that (1) the combination of the vision check of process block 721 and the XRF sensor system classification of process block 722 can result in the sorting of die-cast zinc and 319 / 38x cast aluminum scrap pieces from the material stream; (2) the combination of the vision check of process block 721 and the XRF sensor system classification of process block 722 can result in the sorting of die-cast zinc pieces from the material stream; and (3) the combination of the vision check of process block 721 and the XRF sensor system classification of process block 722 can result in the sorting of 319 / 38x cast aluminum scrap pieces from the material stream. In addition, any of the aforementioned combinations can also include (1) any one or more of the vision checks of process blocks 701 / 703 and 704, and / or (2) any one or more of the XRF classifications by process blocks 709, 715, and 717.

[0128] According to alternative embodiments of the present disclosure, the process is capable of redirecting material pieces classified as cast aluminum alloy pieces in process block 721 onto another conveyor belt (or any suitable conveyor system; or onto different parts of a conveyor belt), thereby enabling the sorting / separation between 319 / 38x cast alloy pieces and die-cast zinc pieces.

[0129] It should be noted that, according to alternative embodiments of this disclosure, further classification and sorting (e.g., by an XRF or LIBS system) may be performed to classify / sort between 319 cast aluminum alloys and 38x cast aluminum alloys (e.g., as a modification and / or addition to process block 723 according to the embodiments disclosed herein). For example, process 700 may be modified to include process blocks 1221-1224 as described with respect to Figures 12A-12B.

[0130] According to alternative embodiments of this disclosure, the vision check implemented within process block 721 can be configured to classify between cast aluminum alloys, wrought aluminum alloys, and extruded aluminum alloys, such as those described in U.S. Patent No. 11,471,916, which is incorporated herein by reference.

[0131] According to alternative embodiments of the present disclosure, optional process blocks 740 are implemented in process 700 to perform negative classification / sorting on their material pieces and remove any cast aluminum alloy pieces classified as wrought aluminum by process block 721 from the material stream. Such classification can be implemented by appropriately configured vision checks (or any of the sensor technologies described herein).

[0132] According to embodiments of the present disclosure, material pieces classified as wrought aluminum alloy pieces by a vision check of process block 721 can be classified / sorted according to one or more combinations of process blocks 725-731. According to embodiments of the present disclosure, sorting these wrought aluminum alloy pieces into these various classifications is performed after one or more of the sorting previously described with respect to Figures 7A-7B. Note that according to certain embodiments of the present disclosure, any one or more of these classifications / sorting can be optional or omitted.

[0133] In process block 725, the captured XRF spectrum of the material piece is used to determine whether the percentage of copper in the material piece (CU value) is greater than a predetermined value (CUK). If so, the material piece is then classified by process block 725 as belonging to the 2xxx series of wrought aluminum alloys, and in process block 726, an instruction is sent by process 700 to the identified sorting device to sort the material piece accordingly. It should be noted that the 2xxx series of aluminum alloys is known to contain a certain amount more copper than other series of wrought aluminum alloys. Therefore, the CUK value can be set (predetermined) to effectively sort these 2xxx series aluminum alloys from other material pieces in the material stream (as predetermined by the user). It can be easily recognized that for the operation (or implementation) of process block 726, it may be beneficial to perform this sorting after the sorting of any other materials with relatively high copper content (e.g., process blocks 706, 708, 790, and / or 723).

[0134] In process block 727, the captured XRF spectrum of the material piece is used to determine whether the percentage of zinc in the material piece (ZN value) is greater than a predetermined value (ZNK). If so, the material piece is then classified by process block 727 as belonging to the 7xxx series of wrought aluminum alloys, and in process block 728, an instruction is sent by process 700 to the identified sorting device to sort the material piece accordingly. It should be noted that 7xxx series aluminum alloys are known to contain a specific amount more zinc than other wrought aluminum alloy series. Therefore, the ZNK value can be set (predetermined) to effectively sort these 7xxx series aluminum alloys from other material pieces in the material stream (as predetermined by the user).

[0135] In process block 729, the captured XRF spectrum of the material piece is used to determine whether the percentage of manganese in the material piece (MN value) is greater than a predetermined value (MNK), and whether the percentage of iron in the material piece (FE value) is less than a predetermined value (FEK). If so, the material piece is classified by process block 729 as belonging to the 3xxx series of wrought aluminum alloys, and in process block 730, an instruction is sent by process 700 to the identified sorting device to sort the material piece accordingly.

[0136] Process block 731 can represent that any material piece not classified / sorted as a 3xxx series wrought aluminum alloy will be classified as a 5xxx / 6xxx series wrought aluminum alloy. This can be achieved simply by allowing all such remaining material pieces in the material stream to be collected in the sorting receiving section. According to alternative embodiments of the present disclosure, further classification / sorting can be performed between 5xxx series aluminum alloys and 6xxx series aluminum alloys. As is known, 5xxx series wrought aluminum alloys are aluminum alloyed with magnesium, while 6xxx series wrought aluminum alloys are aluminum alloyed with magnesium and silicon. However, it should be noted that the concentrations of these aluminum alloy components are relatively very low, and therefore it may be important to configure process 700 so that the classification / sorting in process block 731 follows other classifications / sorting associated with larger peaks measured in the captured XRF spectrum (which could obscure the ability of process 700 to classify / sort 5xxx / 6xxx wrought aluminum alloy pieces).

[0137] According to alternative embodiments of the present disclosure, process block 731 may be configured to implement a principal component analysis ("PCA") algorithm (or any other appropriately configured algorithm) of captured XRF spectra to classify / sort between 5xxx series aluminum alloys and 6xxx series aluminum alloys.

[0138] According to certain embodiments of this disclosure, process blocks 726, 728, 730, and / or 731 can be carried out in any order, however the effectiveness of one or more such classifications / sortings may be affected thereby. Furthermore, these classifications / sortings can be swapped / reordered to achieve a particular effectiveness / efficiency for one or more of these classifications / sortings.

[0139] In addition, according to alternative embodiments of this disclosure, after any one or more of sorting 726, 728, 730, or 731, further classification / sorting may be performed and these may be further separated into finer alloy classifications (e.g., within that particular series of wrought aluminum) by utilizing any suitable sensor technology (e.g., XRF, LIBS, etc.), such as those described in U.S. Patent No. 11,278,937, U.S. Patent Application Publication No. 2021 / 0346916, and U.S. Patent Application Publication No. 2021 / 0229133, which are incorporated herein by reference.

[0140] According to certain embodiments of the present disclosure, process 700 can be configured such that material pieces classified as cast aluminum alloys are separated from a stream of material pieces, and any material pieces not classified as belonging to a wrought aluminum alloy as specified by process blocks 725, 727, and 729 are collected in a designated receiving section (see, for example, receiving section 140 in Figure 1). According to certain embodiments of the present disclosure, process 700 can be configured such that both classified cast aluminum alloys and wrought aluminum alloys are separated from a stream of material pieces after process block 721, and then process blocks 722-724 are performed on the separated cast aluminum alloys, and process blocks 725-731 are performed on the separated wrought aluminum alloys. According to certain embodiments of the present disclosure, process 700 can be configured such that both classified 3xxx series wrought aluminum alloys and classified 5xxx / 6xxx series wrought aluminum alloys are separated from the stream of material pieces after process block 729, and any unclassified material pieces are collected in a receiving section (see, for example, receiving section 140 in Figure 1).

[0141] It can be more easily recognized that (1) the combination of the vision check of process block 721 and the XRF sensor system classification of process block 725 can be used to sort 2xxx series wrought aluminum alloy pieces from the material stream, (2) the combination of the vision check of process block 721 and the XRF sensor system classification of process block 727 can be used to sort 7xxx series wrought aluminum alloy pieces from the material stream, (3) the combination of the vision check of process block 721 and the XRF sensor system classification of process block 729 can be used to sort 3xxx series wrought aluminum alloy pieces from the material stream, and (4) the combination of the vision check of process block 721 and the XRF sensor system classification of process block 729 can be used to sort 5xxx / 6xxx series wrought aluminum alloy pieces from the material stream. Additionally, any of the aforementioned combinations may also include (1) any one or more of the vision checks of process blocks 701 / 703 and 704, and / or (2) any one or more of the XRF classifications by process blocks 709, 715, and 717.

[0142] Figures 12A–12B illustrate flowcharts of process 1200 configured according to one or more alternative embodiments of the present disclosure, in which a material handling system classifies and sorts various materials (e.g., a stream of material pieces transported by a conveyor system) using a unique combination of classification by one or more vision systems (e.g., implementing an AI system) and classification by one or more sensor systems (e.g., a spectroscopic sensor system, e.g., an XRF or LIBS system). Process 1200 (or any aspect or part thereof) can be implemented in any material handling system (including, but not limited to, the material handling systems described with respect to Figures 1–3, 8, 9A–9B, and 10) appropriately configured to perform one or more of the various classification and sorting operations described, utilizing the classification and / or sorting functions, operations, systems, apparatus, and devices described with respect to Figures 1–3. While certain process blocks are described as utilizing an XRF system, any one or more of such process blocks can be implemented by any of the spectroscopic sensor systems described herein (e.g., LIBS, XRT, etc.). It should be noted that one or more of the various process blocks in process 1200 can be optional or omitted according to the particular embodiment of this disclosure.

[0143] Process 1200 is described as operating on a piece-by-piece basis; naturally, when one material piece in the stream of material pieces being transported is operated by a particular process block, subsequent material pieces can then be handled by that process block (for example, when one material piece is analyzed / classified by a vision system and / or XRF system, subsequent material pieces can then be analyzed / classified by a vision system and / or XRF system). Note that the flowcharts in Figures 12A and 12B show multiple process blocks in which “Vision Check” is performed, and the other diamond-shaped process blocks represent the analysis of material pieces by an XRF system (also referred to as XRF sensor system classification). Note that “Vision Check” can be performed by any suitable vision system, including but not limited to a vision system implementing appropriately configured AI techniques. Each vision check classifies the material piece in accordance with processing the visual image captured from each material piece through the AI ​​system.

[0144] To perform the operations within these process blocks, any number of vision systems and / or XRF systems can be implemented, but they can all be performed by a single vision system and / or a single XRF system (or any combination of one or more vision systems and one or more XRF systems) implemented within the material handling system (see, for example, Figure 8). Thus, one or more of the “vision checks” implemented within process 1200 can be performed on image data captured from a material piece by a single vision system implementing one or more different AI algorithms (models) for each vision check. In a similar manner, one or more of the XRF sensor system classifications implemented within process 1200 can be performed on spectral data captured from a material piece by a single XRF system. For example, as each material piece passes by a single implemented vision system, the image data of the material piece captured by the single vision system can be analyzed (for example, substantially simultaneously or in parallel) according to one or more of process blocks 1201, 1205, 1211, and 1213. In other words, algorithms associated with one or more of process blocks 1201, 1205, 1211, and 1213 can process captured image data (for example, substantially simultaneously or in parallel with one or more AI models), and the results are used for their respective classifications. Similarly, XRF spectral data captured by a single implemented XRF system can be analyzed (for example, substantially simultaneously or in parallel with one or more algorithms) according to one or more of process blocks 1206, 1208, 1215, 1216, 1219, 1221, and 1223.

[0145] It should be noted that any of the vision checks described in Figures 12A to 12B can be performed according to process blocks 203 to 211 of process 200 described in relation to Figure 3. Any of the classifications performed by the XRF system (or any other suitable sensor system) in Figures 12A to 12B can be performed according to process blocks 303 to 305 of process 300 described in relation to Figure 4.

[0146] As will be further described herein, certain aspects of process 1200 (i.e., classification and / or sorting implemented within one or more process blocks) may require to be carried out in one or more specific sequences in order to enable those aspects of process 1200 to be carried out more efficiently and / or more accurately. Material pieces may be analyzed / classified by a single vision system and a single XRF system (including being analyzed / classified substantially simultaneously or in parallel), but it should be noted that, as will be further described herein, it may be advantageous to sort the different material pieces in specific sequences (e.g., along a conveyor belt).

[0147] Process 1200 is described in relation to the classification and sorting of a stream of material being conveyed, including solbers, zebras, and / or twitches, but embodiments of Process 1200 may also be applicable to the classification and / or sorting of other types of material pieces.

[0148] In process block 1201, a vision check is performed on a material piece to determine whether it should be classified as some predetermined specific material (e.g., a “junk” or “fluff” material associated with a solber). If the vision check classifies the material piece as a predetermined specific material, then in process block 1202, process 1200 sends an instruction to an identified sorting device to separate the material piece (e.g., from a stream of material pieces being transported) according to its classification (e.g., a material piece composed of or containing PCBs). Process block 1203 indicates that process blocks 1200-1202 can be performed for any other type of material piece (e.g., other “junk” or “fluff” material) that the user wishes to separate from a stream of material pieces, which can be classified by a vision system (e.g., a vision check using any of the vision-related techniques described herein, including but not limited to AI techniques). This can be achieved by a series of different vision systems, or a single vision system can be configured to perform classification in a substantially simultaneous or parallel manner with respect to any multiple predetermined types of material pieces (for example, image data captured by a vision system with respect to a single material piece is then analyzed (substantially simultaneously and / or in parallel with each other) by one or more AI algorithms to classify the material piece as belonging to one of multiple predetermined types of material pieces (e.g., a predetermined set of "junk" or "fluff" materials).

[0149] It should be noted that the implementation configuration of process blocks 1201-1203 may be optional. If process blocks 1201-1203 are implemented, it may be important to perform the sorting indicated by these process blocks before the sorting indicated by one or more of the other process blocks in process 1200 in order to improve the efficiency of the subsequent sorting of material pieces. For example, sorting various materials from the material stream (as sorted in process blocks 1201 and 1203) may be important before performing the sorting of other metals and / or metal alloys (as sorted in one or more subsequent process blocks in process 1200) (e.g., removing "junk" or "fluff" material before sorting the remaining solber). For example, removing "junk" or "fluff" material from the material stream before other materials can reduce the possibility of such "junk" or "fluff" material contaminating the material to be sorted later. In non-limiting examples, PCBs very often contain layers of copper, and XRF sensors may misclassify such PCBs as copper scrap pieces. However, vision systems can be configured to distinguish green PCBs from red copper metal with considerable accuracy. Consequently, since classification of such PCBs by XRF systems may result in them being sorted as copper scrap pieces, it may be advantageous to use vision checks to classify such PCBs so that they can be sorted out from the material stream.

[0150] Process blocks 1204–1225 describe the classification and sorting of materials that are typically found in Zorba (also referred to herein as "Zorba materials").

[0151] In process block 1204, the resulting data from the XRF system can be normalized with respect to the piece size. This step can be optional. This can be done by determining the XRF signal level according to the piece size, and then calibrating the classification to normalize with respect to the piece size.

[0152] According to embodiments as described with reference to Figures 12A and 12B, process 1200 can be configured to classify / sort wrought and / or extruded aluminum alloys before classifying / sorting specific cast aluminum alloys. According to embodiments of the present disclosure, process 1200 can be configured to classify / sort wrought aluminum alloys based on a combination of one or more vision checks and one or more sensor system classifications based on measured amounts of copper and zinc in the material pieces. According to embodiments of the present disclosure, process 1200 can be configured to classify / sort cast aluminum alloys based on a combination of one or more vision checks and one or more sensor system classifications based on measured amounts of copper and zinc in the material pieces.

[0153] In process block 1205, a vision check is performed to classify the wrought aluminum alloy pieces in the material stream. According to embodiments of the present disclosure, the material pieces classified as wrought aluminum alloy pieces by process block 1205 can be further classified and sorted according to one or more combinations of process blocks 1206-1210. Note that, according to certain embodiments of the present disclosure, any one or more of these classifications / sortings can be optional or omitted.

[0154] In process block 1206, the captured XRF spectrum of the material piece is used to determine whether the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a predetermined value (which has been empirically determined to be 10 according to certain non-limiting embodiments of this disclosure), and whether the measured amount of copper in the material piece is greater than a predetermined value "A". According to certain embodiments of this disclosure, a ratio of the value CU / ZN, as described with respect to process 700, may be used. Also, according to certain embodiments of this disclosure, a determination of CU>CUK, as described with respect to process block 725, may be used for the determination of CU>A.

[0155] If both decisions in process block 1206 are positive, the material piece is then classified as belonging to the 2xxx series of wrought aluminum alloys, and in process block 1207, the instruction is sent by process 1200 to the identified sorting device to sort the material piece accordingly. It should be noted that the 2xxx series of aluminum alloys is known to contain a certain amount more copper than other series of wrought aluminum alloys. Therefore, the value "A" can be set (predetermined) to effectively sort these 2xxx series aluminum alloys from other material pieces in the material stream (as predetermined by the user).

[0156] In process block 1208, the captured XRF spectrum of the material piece is used to determine whether the ratio of the measured amount of copper to the measured amount of zinc in the material piece is less than a predetermined value (which has been empirically determined to be 2 according to certain non-limiting embodiments of this disclosure), and whether the measured amount of zinc in the material piece is greater than a predetermined value "B". According to certain embodiments of this disclosure, a ratio of value CU / ZN, as described with respect to process 700, may be used. Also, according to certain embodiments of this disclosure, a determination of ZN>ZNK, as described with respect to process block 727, may be used for the determination of ZN>B.

[0157] If both decisions in process block 1208 are positive, the material piece is then classified as belonging to the 7xxx series of wrought aluminum alloys, and in process block 1209, the instruction is sent by process 1200 to the identified sorting device to sort the material piece accordingly. It should be noted that the 7xxx series aluminum alloys are known to contain a certain amount more zinc than other wrought aluminum alloy series. Therefore, the value "B" can be set (predetermined) to effectively sort these 7xxx series aluminum alloys from other material pieces in the material stream (as predetermined by the user).

[0158] According to embodiments of the present disclosure, process 1200 can send an instruction (process block 1210) to a designated sorting device to sort into a receiving section any remaining material pieces that have been classified as wrought aluminum but have not been sorted as either 2xxx or 7xxx series wrought aluminum pieces (and according to embodiments of the present disclosure, these material pieces can be designated as 3xxx, 5xxx, and / or 6xxx series aluminum pieces). Thus, process block 1210 can indicate that any material pieces that have not been classified / sorted as 2xxx or 7xxx series wrought aluminum alloys are to be classified as 3xxx / 5xxx / 6xxx series wrought aluminum alloys. According to alternative embodiments of the present disclosure, further classification / sorting can be performed among 3xxx, 5xxx, and / or 6xxx series aluminum alloys, such as those described with respect to process blocks 729-731.

[0159] According to certain embodiments of this disclosure, sorting by process block 1209 can be performed before sorting by process block 1207, however, the effectiveness of these sorts may be affected thereby. Furthermore, these classifications / sortings can be swapped / reordered to achieve a particular effectiveness / efficiency for one or more of these classifications / sortings.

[0160] In addition, according to alternative embodiments of this disclosure, any one or more of classifications 1207, 1209, or 1210 can be further modified by further classifications / sortings, and these can be further separated into finer alloy classifications (e.g., within that particular series of wrought aluminum) by utilizing classifications based on any suitable sensor technology (e.g., XRF, LIBS, etc.), such as those described in U.S. Patent No. 11,278,937, U.S. Patent Application Publication No. 2021 / 0346916, and U.S. Patent Application Publication No. 2021 / 0229133, the literature of which is incorporated herein by reference.

[0161] According to certain embodiments of the present disclosure, process 1200 can be configured such that material pieces classified as cast aluminum alloys are separated from a stream of material pieces, and any material pieces not classified as belonging to a wrought aluminum alloy as specified by either process block 1206 or 1208 are collected in a designated receiving section (see, for example, receiving section 140 in Figure 1).

[0162] (1) The combination of the vision check of process block 1205 and the XRF sensor system classification of process block 1206 can be used to sort 2xxx wrought aluminum alloy pieces from the material stream, (2) The combination of the vision check of process block 1205 and the XRF sensor system classification of process block 1206 can be used to sort 2xxx and / or 7xxx, 3xxx, 5xxx, and / or 6xxx series wrought aluminum alloy pieces from the material stream, (3) The combination of the vision check of process block 1205 and the XRF sensor system classification of process blocks 1206 and 1208 can be used to sort 7xxx and 3xxx, 5xxx, and / or It can be readily recognized that (4) the combination of the vision check of process block 1205 and the XRF sensor system classification of process blocks 1206 and 1208 can be used to sort 7xxx or 3xxx, 5xxx, and / or 6xxx series wrought aluminum alloy pieces from the material stream, and (5) the combination of the vision check of process block 1205 and the XRF sensor system classification of process blocks 1206 and 1208 can be used to sort 3xxx, 5xxx, and / or 6xxx series wrought aluminum alloy pieces from the material stream. In addition, all of the above combinations can also include the vision check of process blocks 1201 / 1203.

[0163] Furthermore, it can be recognized that it may be advantageous to configure process 1200 so that a vision check for wrought aluminum alloys by process block 1205 is performed in combination with a sensor system classification by process block 1206 in order to select 2xxx series aluminum alloys before selecting certain cast aluminum alloys known to contain relatively high amounts of copper. It can also be recognized that it may be advantageous to configure process 1200 so that a vision check for wrought aluminum alloys by process block 1205 is performed in combination with a sensor system classification by process block 1208 in order to select 7xxx series aluminum alloys before selecting certain cast aluminum alloys known to contain relatively high amounts of zinc.

[0164] In process block 1211, a vision check may be performed to classify extruded aluminum alloy pieces in a stream of material (see, for example, U.S. Patent No. 11,471,916, which is incorporated herein by reference). According to non-limiting embodiments of the present disclosure, such extruded aluminum alloy pieces may be classified as 6061, 6063, or other types of extruded material. Process 1200 may then send a command (process block 1212) to an identified sorting device to sort those material pieces accordingly. Additionally, according to alternative embodiments of the present disclosure, after sorting 1212, further classification / sorting may be performed to further separate these into finer alloy classifications (e.g., within those particular series of extruded aluminum) by utilizing any suitable sensor technology (e.g., XRF, LIBS, etc.).

[0165] In process block 1213, a vision check can be performed to classify cast aluminum alloy pieces in the material stream. Process block 1214 indicates that any material pieces remaining in the material stream that are not classified as cast aluminum can be sorted out of the stream as belonging to the "other" material classification (i.e., anything that is not wrought, extruded, or cast aluminum). Additionally, process block 1213 can be optionally implemented in which all remaining material pieces that were not sorted are then considered as cast aluminum alloy pieces. Process block 1213 can also be optionally implemented by the assumption in process 1200 that all material pieces that were not classified as wrought aluminum alloy by process block 1205 and / or not classified as extruded aluminum alloy by process block 1211 will subsequently be considered as cast aluminum alloy in process 1200.

[0166] It should be noted that, according to alternative embodiments of this disclosure, negative classification / sorting may be performed after any one or more of process blocks 1205, 1211, and 1213.

[0167] In process block 1215, a determination is made as to whether the measured total amount of copper and zinc in the material piece is greater than a predetermined value "C". According to certain embodiments of the present disclosure, such a determination can be made using the CU and ZN values ​​described in relation to process 700. Additionally, according to certain embodiments of the present disclosure, such a determination can be made using the total captured XRF spectral count (N-Total) (after being normalized by the length and height (or mass) of the piece) for the material piece with respect to the value AK, as disclosed in relation to process block 717. According to certain embodiments of the present disclosure, this AK value can be set as 0.4 × N-Total for 319 standard cast aluminum alloy (as determined, for example, by the Aluminum Association).

[0168] If the determination by process block 1215 is not positive, then process block 1216 determines whether the measured amount of iron in the material piece is greater than a predetermined value "D". According to certain embodiments of the present disclosure, the determination of FE for a value FEK, as similarly described with respect to process block 729, can be used to determine if FE > D. If FE > D, the material piece will be classified as a 360 cast aluminum piece, and in process block 1217, an instruction can be sent by process 1200 to a specified sorting device to sort the material piece accordingly. Otherwise, the material piece will be classified as a 356 cast aluminum piece, and in process block 1218, an instruction can be sent by process 1200 to a specified sorting device to sort the material piece accordingly.

[0169] Therefore, it can be readily recognized that process 1200 can be configured by a combination of process blocks 1215 and 1216 to sort material pieces so that they are classified as 356 / 360 cast aluminum material. In addition, the aforementioned combination can also include any one or more of the vision checks of process blocks 1201 / 1203, 1205, 1211, and / or 1213.

[0170] Since 319 and 38x cast aluminum alloys have a material composition represented by a relatively large copper peak compared to zinc, as captured in the XRF spectrum (copper concentration approximately 3-4%; zinc concentration <1%), process blocks 1219-1224 are implemented in process 1200 to separate these alloys from the die-cast zinc metal pieces (or all other cast aluminum alloys remaining in the stream of material pieces). Note that, according to alternative embodiments of the present disclosure, the material handling system can be configured so that all cast aluminum alloy pieces not classified as either 319 / 38x and / or die-cast zinc metal pieces are collected in a catch-all receiving section (see process block 1225).

[0171] In process block 1219, each such material piece is classified, thereby determining whether the captured XRF spectrum of the material piece indicates that the material piece has a relatively higher copper concentration than the zinc concentration, as previously described. For example, it is possible to determine whether the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a predetermined value "E". According to certain embodiments of the present disclosure, it is possible to determine whether the ratio of the value CU / ZN is greater than a predetermined value BK, as described with respect to process block 722.

[0172] If the ratio of the measured amount of copper to the measured amount of zinc in the material piece is not greater than a predetermined value "E", the material piece is classified as a die-cast zinc piece, and in process block 1220, process 1200 sends an instruction to the identified sorting device to sort the material piece accordingly.

[0173] In process block 1221, each such material piece is classified, thereby determining whether the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a predetermined value E and less than a predetermined value F. According to certain embodiments of the present disclosure, it is possible to utilize the determination of whether the ratio of value CU / ZN is greater than a predetermined value E and less than a predetermined value F.

[0174] If the answer is "yes", the material piece is classified as 38x cast aluminum piece, and in process block 1222, process 1200 sends an instruction to the identified sorting device to sort the material piece accordingly.

[0175] In process block 1223, each such material piece is classified, thereby determining whether the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a predetermined value F and less than a predetermined value G. According to certain embodiments of the present disclosure, it is possible to utilize the determination of whether the ratio of value CU / ZN is greater than a predetermined value F and less than a predetermined value G.

[0176] If the answer is "yes," the material piece is classified as a 319 cast aluminum piece, and in process block 1224, process 1200 sends an instruction to the identified sorting device to sort the material piece accordingly.

[0177] According to embodiments of the present disclosure, process 1200 can be configured such that any other material pieces that have not been sorted from the material stream are collected in a receiving section, as described in process block 1225.

[0178] (1) The XRF sensor system classification combination of process blocks 1215 and 1219 can be used to sort die-cast zinc pieces from the material stream, (2) The XRF sensor system classification combination of process blocks 1219 and 1221 can be used to sort 38x cast aluminum alloy pieces from the material stream, (3) The XRF sensor system classification combination of process blocks 1221 and 1223 can be used to sort 319 cast aluminum alloy pieces from the material stream, ( 4) The combination of XRF sensor system classifications of process blocks 1219, 1221, and 1223 can be used to separate die-cast zinc, 38x cast aluminum alloy, and 319 cast aluminum alloy pieces from the material stream, and (5) the combination of XRF sensor system classifications of process blocks 1215, 1219, 1221, and 1223 can be used to separate 356, 360, 38x, and 319 cast aluminum alloy and die-cast zinc pieces from the material stream. In addition, the aforementioned combinations can also include any one or more of the vision checks of process blocks 1201 / 1203, 1205, 1211, and / or 1213.

[0179] Figure 8 illustrates a simplified schematic diagram of a non-limiting example of a material handling system 800 configured according to embodiments of the present disclosure. Label 808 represents a conveyor system, which can consist of any combination of conveyor devices as described herein, and which includes, but is not limited to, one or more conveyor belts for transporting multiple material pieces (not shown) through a vision system and an XRF system 801 (or any other appropriately configured sensor technology disclosed herein) and N (N≧1) sorting devices 802…804. The N sorting devices 802…804 can be configured to sort the specifically classified material pieces into N corresponding receiving sections or onto N other conveyor systems 805…807, respectively. According to certain embodiments of the present disclosure, one or more of the N conveyor systems 805…807 can be configured to transport their respective sorted material pieces to another sorting device (not shown) for further sorting based on one or more classifications derived from information captured from a vision system and / or an XRF system 801 (see, for example, the discussion relating to Figure 10).

[0180] Therefore, the material handling system 800 can be configured to implement one or more embodiments of the process 700 described with respect to Figures 7A to 7C, thereby, each sorting being based on one or more classifications derived from information captured from the vision system and / or XRF system 801. For example, various configurations of the system and process 800 can be configured to implement one or more combinations of process blocks 704 to 708, 790, one or more combinations of process blocks 709 to 714, one or more combinations of process blocks 704, 709, 715, 717, and / or 721, or one or more combinations of process blocks 725 to 731.

[0181] Similarly, the material handling system 800 can be configured to implement one or more embodiments of process 1200 as described with respect to Figures 12A to 12B, thereby each sorting being based on one or more classifications derived from information captured from the vision system and / or XRF system 801. For example, various configurations of the system and process 800 can be configured to implement one or more combinations of process blocks 1205 to 1210, one or more combinations of process blocks 1215 to 1218, one or more combinations of process blocks 1205, 1211, 1213, 1215, 1219, 1221, and / or 1223, or one or more combinations of process blocks 1219 to 1225.

[0182] According to non-limiting exemplary embodiments of the present disclosure, at least a portion of the components of the material handling system 100 can be linked together (e.g., sequentially or in parallel) to perform multiple iterations or layers of classification / sorting. Such linkages can be physical / mechanical links between systems, or links between classification / sorting processes in any desired manner by separate material handling systems (or the same material handling system performing different classification / sorting processes separately). For example, when two or more systems 100 are linked together in such a manner, the conveyor system can be implemented by a single conveyor belt (or multiple conveyor belts), which transports the material pieces through a first vision system (and, according to a particular embodiment, a sensor system) configured to sort / separate material pieces of a first set of materials into one or more receiving sections (e.g., sorting receiving sections 136…139) of the first set by sorting devices (e.g., a first automated control system 108 and one or more associated sorting devices 126…129), and then transports the material pieces through a second vision system (and, according to a particular embodiment, another sensor system) configured to sort / separate material pieces of a second set of materials into one or more sorting receiving sections of the second set by a second sorting device. A further discussion of such multi-stage sorting is found in U.S. Patent Application Publication No. 2022 / 0016675, which is incorporated herein by reference.

[0183] As further described herein, such a series of material handling systems 100 can include any number of such systems linked together in such a manner. According to certain embodiments of the present disclosure, each successive material handling system can be configured to classify / sort materials of a different classification or type than the previous system (for example, as described with respect to Figures 7A-7C and Figures 12A-12B).

[0184] Figures 9A and 9B illustrate simplified schematic diagrams of systems and processes 1600 configured according to certain non-limiting exemplary embodiments of the present disclosure for sorting / classifying multiple material pieces (for example, as described with respect to various aspects of process 700 in Figures 7A and 7C and process 1200 in Figures 12A and 12B). Figure 9A illustrates an exemplary non-limiting schematic diagram of a side view of such a system and process 1600, while Figure 9B illustrates a top view.

[0185] Multiple material pieces 1601 can be transported (for example, by a conveyor belt 1602) or piled up in a hopper and picked up by an inclined conveyor system 1603. Note that the material pieces 1601 are not shown in Figure 9B for simplification. The conveyor system 1603 transports the material pieces 1601 through an AI and / or XRF system to sort the material pieces for sorting. Alternatively, any other of the disclosed sensor systems 120 (e.g., LIBS, XRT, etc.) can be used instead of the XRF system.

[0186] For example, various configurations of the system and process 1600 can be configured to implement one or more combinations of process blocks 705-708 and 790, one or more combinations of process blocks 709-714, one or more combinations of process blocks 704, 709, 715, 717, and / or 721, or one or more combinations of process blocks 725-731.

[0187] For example, consider the combination of process blocks 725-731. As a non-limiting example, an XRF or vision system implementing the AI ​​system 1610 can be configured to classify which of the material pieces 1601 are composed of 2xxx series wrought aluminum alloy. The conveyor system 1603 can be configured to operate at a speed sufficient to "throw" material pieces that have not been classified as 2xxx series wrought aluminum alloy onto the subsequent inclined conveyor system 1604. Material pieces classified as being composed of 2xxx series wrought aluminum alloy are discharged by a sorting device 1620 onto a lower-positioned conveyor system 1606. For example, such a sorting device 1620 could be an air jet nozzle, such as one described herein, which is operated to discharge material pieces classified as 2xxx series wrought aluminum alloy from the normal trajectory of material pieces being "thrown" from the end of conveyor system 1603 onto conveyor system 1604. Material pieces classified as 2xxx series wrought aluminum alloys can be transported into the receiving section 1630.

[0188] Material pieces not classified as 2xxx series wrought aluminum alloy can be transported through the XRF or AI system 1611, which can be configured to identify and sort those material pieces that consist of 7xxx series wrought aluminum alloy. Conveyor system 1604 can be configured to operate at a speed sufficient to "throw" the material pieces not classified as 7xxx series wrought aluminum alloy onto the subsequent inclined conveyor system 1605. Material pieces classified as consisting of 7xxx series wrought aluminum alloy can be discharged by a sorting device 1621 onto a lower-positioned conveyor system 1607. For example, such a sorting device 1621 can be an air jet nozzle, such as one described herein, which is operated to discharge material pieces classified as 7xxx series wrought aluminum alloy from the normal trajectory of material pieces "thrown" from the end of conveyor system 1604 onto conveyor system 1605. The classified material pieces can be transported into the receiving section 1631.

[0189] Material pieces not classified as 7xxx series wrought aluminum alloys can be transported through the XRF or AI system 1612, which can be configured to identify and classify those material pieces as 3xxx series wrought aluminum alloys.

[0190] The conveyor system 1605 can be configured to operate at a speed sufficient to "throw" material pieces that have not been classified as 3xxx series wrought aluminum alloy onto another conveyor system (not shown) or into the receiving section 1633. Material pieces classified as 3xxx series wrought aluminum alloy can be discharged by a sorting device 1622 onto a lower-positioned conveyor system 1608. For example, such a sorting device 1622 could be an air jet nozzle, such as one described herein, which is operated to discharge material pieces classified as 3xxx series wrought aluminum alloy from the normal trajectory of material pieces "thrown" from the end of the conveyor system 1605. These classified material pieces can be transported into the receiving section 1632. The remaining material pieces thrown from the end of the conveyor belt 1605 can be considered as being classified as either or both of the 5xxx and 6xxx series wrought aluminum alloys.

[0191] It should be noted that the system and process 1600 is not limited to a single line of the conveyor system, but can be extended to multiple lines, each discharging the classified material pieces onto multiple conveyor systems (e.g., conveyor systems 1606…1608). Similarly, one or more of the conveyor systems 1606…1608 can be equipped with additional XRF or AI systems for further classifying those material pieces. For example, material pieces classified as consisting of 5xxx and 6xxx series wrought aluminum alloys (and collected into the receiving section 1633) could instead be transported (by an unshown conveyor system) through another XRF and / or AI system (or other sensor system 120) to classify and / or sort them among their wrought aluminum alloys.

[0192] Accordingly, according to certain embodiments of the present disclosure, a sorting / sorting system, such as those described with respect to one or more of the process blocks 717-721, is capable of first sorting the cast aluminum material pieces, and then sorting / sorting the remaining material pieces among the various remaining wrought aluminum alloys.

[0193] Similarly, the material handling system 1600 can be configured to implement one or more embodiments of the process 1200 described with respect to Figures 12A to 12B, thereby each sorting being based on one or more classifications derived from information captured from the vision system and / or XRF system 801. For example, various configurations of the system and process 800 can be configured to implement one or more combinations of process blocks 1205 to 1210, one or more combinations of process blocks 1215 to 1218, one or more combinations of process blocks 1205, 1211, 1213, 1215, 1219, 1221, and / or 1223, or one or more combinations of process blocks 1219 to 1225.

[0194] Referring to Figure 10, a schematic diagram is shown of a non-limiting example of a linked connection of successive material handling systems (either physically linked or implemented successively by a plurality of appropriately configured material handling systems 100 (or the same material handling system appropriately configured for each successive classification / sorting)) according to a particular embodiment of the present disclosure, which can be implemented by any material handling system that utilizes one or more vision systems and / or one or more sensor systems 120 (for example, utilizing artificial intelligence ("AI")) to implement one or more different embodiments as described with respect to Figures 7A-7C or Figures 12A-12B. For simplification, with respect to the following discussion of Figure 10, such combination of one or more vision systems and / or one or more sensor systems may simply be referred to as a material classification system. In Figure 10, arrows schematically illustrate how different material pieces are transported along such exemplary material handling systems. While four separate material handling systems are illustrated in this non-limiting example, any number of such material handling systems can be combined in any way to separate and sort various different classes of materials. Although the example in Figure 10 illustrates various classes of materials to be sorted (e.g., those typically contained by Zorba, Zebra, and Twitch), embodiments of the present disclosure are applicable to the classification / sorting of any combination of heterogeneous mixtures of material pieces.

[0195] In this particular example, a group of materials, including heterogeneous mixtures of material 3801a (e.g., Zorba and "junk" or "fluff" materials (e.g., aluminum, stainless steel, plastic, wood, rubber, brass, copper, PCB, e-scrap, copper wire, etc.)), is fed onto a first conveyor system 3803a (identified as conveyor belt #1 in Figure 10) from, for example, a ramp or chute 3802a (e.g., from a ramp or chute 102, e.g., a hopper). The conveyor system 3803a transports material pieces 3801a through the material sorting system 3810a, which can be configured to use a sorter 3826a to sort / separate material pieces (e.g., "junk" or "fluff" material) from the rest of the material pieces (identified as sort #1), and the sorter 3826a can utilize any of the sorting devices described herein to deposit into one or more receiving sections 3836a (see, for example, process blocks 701-703 in Figure 7A or process blocks 1201-1203 in Figure 12A).

[0196] The remaining heterogeneous mixture of material piece 3801b (e.g., Zorba material) can then be transported along the same conveyor system or piled up on conveyor system 3803b (identified as conveyor belt #2 in Figure 10) 3802b. Conveyor system 3803b passes these material pieces 3801b through material sorting system 3810b, which can be configured to use sorter 3826b to identify and separate zebra pieces from twitch pieces (identified as sorting #2), and sorter 3826b can include one or more combinations of sorting / sorting (see process blocks 704, 709, and 715 in Figures 7A–7B, for example).

[0197] In this particular non-limiting example, copper and brass material pieces 3801c can then be stacked on a conveyor system 3803c (identified as conveyor belt #3 in Figure 10) for identification by a material classification system 3810c, and sorted by a sorter 3826c (identified as sorter #3). This section of the material handling system can be configured to separate and sort material pieces made from copper and copper wire from brass (see, for example, process blocks 705-706), which can then be stacked in one or more receiving sections or on the conveyor system for further classification / sorting. According to a particular embodiment of the present disclosure, each of the material pieces classified as copper, copper wire, yellow brass, and red brass material pieces can be individually sorted and stacked in separate receiving sections for copper 3836c and copper wire 3837c. The remaining material pieces (yellow brass and red brass) are then a mixture of different materials that can be deposited into the receiving section 3840, or further processed by a sorting / sorting system (not shown) as previously described (see, for example, process blocks 707, 708, and 790).

[0198] Embodiments of the present disclosure are not limited to a linear sequence of such material handling systems, but may include a combination of branching such material handling systems for further classification and sorting of one or more specific classes of materials. For example, Figure 10 illustrates how a material piece classified as an aluminum alloy (twitch) material piece 3836b, sorted in sorting #2, is then deposited onto a conveyor system 3803d (identified as conveyor belt #4 in Figure 10) 3802d. For example, a sorter 3826b may physically sort such twitch material pieces onto a conveyor system (e.g., conveyor system 3803d), or the receiving section 3836b in which the twitch material pieces are deposited may be a ramp or chute for depositing the twitch material pieces onto the conveyor system 3803d, or the receiving section containing the twitch material pieces may simply be operated to deposit the twitch material pieces onto the conveyor system 3803d. The material classification system 3810d can then be configured to classify these twitch material pieces into cast aluminum alloys and wrought aluminum alloys (for example, as described herein with respect to process block 721 in Figure 7B), or into wrought aluminum alloys, extruded aluminum alloys, and cast aluminum alloys (for example, as described herein with respect to process blocks 1205, 1211, and 1213 in Figure 12A). In this sorting #4, the sorter 3826d can then be configured to separate the cast aluminum alloys from the wrought aluminum alloys based on the classification by the material classification system 3810d, thereby allowing the cast aluminum alloys to be deposited into the receiving section 3837d, and the wrought aluminum alloys to be deposited into the receiving section 3836d or onto a conveyor system (not shown) for further classification / sorting.

[0199] A variation of the system in Figure 10 may include further classifying / sorting cast aluminum alloys into different predefined cast aluminum alloys using one or more sensor systems 120 (including, but not limited to, XRF systems (such as those described with respect to process blocks 722-724 in Figure 7B and also with respect to process blocks 1215-1225 in Figure 12B)). Another variation of the system in Figure 10 may include further classifying / sorting wrought aluminum alloys into different predefined wrought aluminum alloys using one or more sensor systems 120 (including, but not limited to, XRF systems (such as those described with respect to process blocks 725-731 in Figure 7C and also with respect to process blocks 1206-1210 in Figure 12A)).

[0200] As can be easily seen, the material handling system illustrated in Figure 10 can be modified to any combination of classification / sorting systems for sorting materials as desired.

[0201] According to various embodiments of this disclosure, different types or classes of materials can be classified by different types of sensors for use with an AI system, and can be combined to classify material pieces in a stream of scrap or waste.

[0202] According to various embodiments of this disclosure, data from two or more sensors can be combined using one or more AI systems to perform material piece classification.

[0203] According to various embodiments of this disclosure, multiple sensor systems can be mounted on a single conveyor system, and each sensor system utilizes a different AI system. According to various embodiments of this disclosure, multiple sensor systems can be mounted on different conveyor systems, and each sensor system utilizes a different AI system.

[0204] According to various embodiments of this disclosure, different types or classes of materials can be classified by different types of sensors for use with an AI system, and can be combined to classify material pieces in a stream of scrap or waste.

[0205] According to various embodiments of this disclosure, data from two or more sensors (e.g., spectral data or XRF spectral data) can be combined using one or more AI systems to perform material piece classification.

[0206] Referring here to Figure 11, a block diagram illustrating the data processing ("computer") system 3400 is shown, in which embodiments of the embodiments of the present disclosure can be implemented. (The terms "computer," "system," "computer system," and "data processing system" may be used interchangeably herein.) Embodiments of computer system 107, automation control system 108, sensor system 120, and / or vision system 110 can be similarly configured as computer system 3400. Computer system 3400 may use a local bus 3405 (for example, a Peripheral Component Interconnection ("PCI") local bus architecture). In particular, any suitable bus architecture may be used, such as Accelerated Graphics Port ("AGP") and Industry Standard Architecture ("ISA"). One or more processors 3415, volatile memory 3420, and non-volatile memory 3435 may be connected to the local bus 3405 (for example, through a PCI bridge (not shown)). The integrated memory controller and cache memory can be coupled to one or more processors 3415. The one or more processors 3415 may include one or more central processor units and / or one or more graphics processor units and / or one or more tensor processing units. Additional connections to the local bus 3405 can be made through direct component interconnects or through add-in boards. In the illustrated example, a communications (e.g., network (LAN)) adapter 3425, an I / O (e.g., Small Computer System Interface ("SCSI") host bus) adapter 3430, and an expansion bus interface (not shown) can be connected to the local bus 3405 by direct component interconnects.An audio adapter (not shown), a graphics adapter (not shown), and a display adapter 3416 (connected to display 3440) can be connected to local bus 3405 (for example, by an add-in board inserted into an expansion slot).

[0207] The user interface adapter 3412 can provide connections for a keyboard 3413 and mouse 3414, a modem (not shown), and additional memory (not shown). The I / O adapter 3430 can provide connections for a hard disk drive 3431, a tape drive 3432, and a CD-ROM drive (not shown).

[0208] The operating system can run on one or more processors 3415 and be used to coordinate and provide control over various components within the computer system 3400. The operating system can be a commercially available operating system. An object-oriented programming system can run in conjunction with the operating system and provide calls to the operating system from programs or programs running on the system 3400 (e.g., Java, Python, etc.). The operating system, the object-oriented operating system, and instructions for the programs can be located on non-volatile memory 3435 storage devices (e.g., hard disk drive 3431, etc.) and can be loaded into volatile memory 3420 for execution by processors 3415.

[0209] Those skilled in the art will recognize that the hardware in Figure 11 can be modified depending on the implementation. Other internal hardware or peripheral devices (e.g., flash ROM (or equivalent non-volatile memory) or optical disc drives) can be used in addition to or instead of the hardware depicted in Figure 11. Furthermore, any of the processes of this disclosure can be applied to a multiprocessor computer system or can be carried out by multiple such systems 3400. For example, training of the vision system 110 can be carried out by a first computer system 3400, while the operation of the vision system 110 for sorting can be carried out by a second computer system 3400.

[0210] As another example, the computer system 3400 may be a standalone system configured to be bootable independently of any type of network communication interface, regardless of whether the computer system 3400 includes any type of network communication interface. As yet another example, the computer system 3400 may be an embedded controller, which is configured to include ROM and / or flash ROM providing non-volatile memory for storing operating system files or user-created data.

[0211] The examples depicted in Figure 11 and described above are not intended to imply any architectural limitations. Furthermore, computer program forms of the embodiments of this disclosure can reside on any computer-readable storage medium used by a computer system (i.e., floppy disks, compact disks, hard disks, tapes, ROMs, RAMs, etc.).

[0212] As described herein, embodiments of the present disclosure can be implemented to perform the various functions described for identifying, tracking, classifying, and / or sorting material pieces. Such functionality can be implemented in hardware and / or software, such as the previously described computer system 107, vision system 110, sensor system 120, and / or automated control system 108, for example, in one or more data processing systems (for example, data processing system 3400 in Figure 11). Nevertheless, the functionality described herein is not limited to implementation in any particular hardware / software platform.

[0213] As will be recognized by those skilled in the art, aspects of this disclosure can be embodied as systems, processes, methods, and / or program products. Accordingly, various aspects of this disclosure can take the form of entirely hardware embodiments, entirely software embodiments (including firmware, resident software, microcode, etc.), or embodiments combining software and hardware embodiments, which can generally be referred to herein as “circuits,” “circuit configurations,” “modules,” or “systems.” Furthermore, aspects of this disclosure can take the form of program products embodied in one or more computer-readable storage media having computer-readable program code embodied thereon. (However, any combination of one or more computer-readable media can be used. Computer-readable media can be computer-readable signaling media or computer-readable storage media.)

[0214] Computer-readable storage media can be, for example, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, biological, atomic, or semiconductor systems, apparatus, controllers, or devices, or any suitable combination of the foregoing, and computer-readable storage media are not transient signals in themselves. More specific examples (a non-exclusive list) of computer-readable storage media can include electrical connectors having one or more wires, portable computer diskettes, hard disks, random access memory ("RAM") (e.g., RAM 3420 in Figure 11), read-only memory ("ROM") (e.g., ROM 3435 in Figure 11), erasable programmable read-only memory ("EPROM" or flash memory), optical fibers, portable compact disk read-only memory ("CD-ROM"), optical storage devices, magnetic storage devices (e.g., hard drive 3431 in Figure 11), or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium can be any tangible medium capable of containing or storing a program for use by or in connection with an instruction execution system, apparatus, controller, or device. Program code embodied on a computer-readable signaling medium can be transmitted using any suitable medium (including, but not limited to, wireless, wireline, fiber optic cable, RF, or any suitable combination thereof).

[0215] A computer-readable signaling medium can contain propagated data signals in which computer-readable program code is embodied (for example, in the baseband or as part of a carrier wave). Such propagated signals can take any of a variety of forms (including, but not limited to, electromagnetic, optical, or any suitable combination thereof). A computer-readable signaling medium can be any computer-readable medium that is not a computer-readable storage medium and that can communicate, propagate, or transport programs for use by or in connection with an instruction execution system, apparatus, controller, or device.

[0216] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of the systems, methods, processes, and program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, segment, or portion of code, which includes one or more executable program instructions for implementing a specified logical function. It should also be noted that in some implementations, the functions described in a block may occur in a different order than that shown in the figure. For example, two blocks shown consecutively may actually be executed substantially simultaneously, or blocks may be executed in reverse order depending on the functionality involved.

[0217] Modules implemented in software for execution by various types of processors (e.g., GPU3401, CPU3415) can, for example, contain one or more physical or logical blocks of computer instructions, which can be organized as, for example, objects, procedures, or functions. Nevertheless, the executable files of identified modules do not need to be physically located together and can contain entirely different instructions stored in different locations, which, when logically joined together, contain the module and fulfill the stated purpose for the module. In fact, a module of executable code can be a single instruction or many instructions and can be distributed across several different code segments, between different programs, and even across several memory devices. Similarly, behavioral data (e.g., a materials classification library as described herein) can be identified and illustrated within modules herein, can be embodied in any suitable form, and can be organized within any suitable type of data structure. Behavioral data can be collected as a single dataset or distributed across different locations (including "across different storage devices"). The data can provide electronic signals over a system or network.

[0218] These program instructions are provided to one or more processors and / or controllers of a general-purpose computer, a dedicated computer, or other programmable data processing device (e.g., a controller) and are capable of creating a machine in which the instructions (which are executed via the processors of the computer or other programmable data processing device (e.g., GPU3401, CPU3415)) cause the generation of circuit configurations or means for implementing functions / actions specified in one or more blocks of a flowchart and / or block diagram.

[0219] Furthermore, it should be noted that each block in the block diagram and / or flowchart diagram, as well as any combination of blocks within the block diagram and / or flowchart diagram, can be implemented by a dedicated hardware-based system (for example, it may include one or more graphics processing units (e.g., a GPU3401)) that performs a specified function or action, or a combination of dedicated hardware and computer instructions. For example, a module can be implemented as a hardware circuit, including a custom VLSI circuit or gate array, off-the-shelf semiconductors (e.g., logic chips, transistors, controllers, etc.), or other discrete components. Alternatively, a module can be implemented in a programmable hardware device (e.g., a field-programmable gate array, programmable array logic, or programmable logic device, etc.).

[0220] Computer program code (i.e., instructions) for performing the actions for the aspects of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​(e.g., Java, Smalltalk, Python, or C++), conventional procedural programming languages ​​(e.g., the "C" programming language or similar programming languages), programming languages ​​such as MATLAB® or LabVIEW, or any of the machine learning software disclosed herein. The program code can run entirely on the user's computer system, partially on the user's computer system, as a standalone software package, partially on the user's computer system (e.g., a computer system used for sorting) and partially on a remote computer system (e.g., a computer system used to train a machine learning system), or entirely on a remote computer system or server. In the latter scenario, the remote computer system can be connected to the user's computer system through any type of network (including a local area network ("LAN") or a wide area network ("WAN")), or the connection can be made to an external computer system (e.g., via the Internet using an Internet service provider). As an example of those described above, various aspects of the present disclosure can be configured to run on one or more of the following: a computer system 107, an automated control system 108, a vision system 110, and a sensor system 120.

[0221] Furthermore, these program instructions can be stored in a computer-readable storage medium that can instruct a computer system, other programmable data processing device, controller, or other device to function in a specific manner, and the instructions stored in the computer-readable medium are used to produce articles of manufacture that include instructions for implementing functions / actions identified in one or more blocks of a flowchart and / or block diagram.

[0222] Furthermore, program instructions are loaded onto a computer, other programmable data processing device, controller, or other device, causing a series of operational steps to be performed on the computer, other programmable device, or other device, creating a computer implementation process, and the instructions executed on the computer or other programmable device provide a process for implementing functions / actions identified in one or more blocks of a flowchart and / or block diagram.

[0223] One or more databases may be contained within a host for storing and providing access to data for various implementation forms. Furthermore, for security reasons, a person skilled in the art will recognize that any database, system, or component in this disclosure may contain any combination of databases or components in one or more locations, and each database or system may include any of various appropriate security features (e.g., firewalls, access codes, encryption, and decryption). A database can be any type of database (e.g., relational, hierarchical, and / or object-oriented). Common database products that may be used to implement a database include IBM's DB2, any database product available from Oracle Corporation, Microsoft Access from Microsoft Corporation, or any other database product. A database can be organized in any appropriate form, including data tables or lookup tables.

[0224] Embodiments of this disclosure offer a paradigm shift from "binary" sorting, thereby reducing costs. While this innovation may not be immediately eye-catching, it significantly reduces the overall cost of sorting. Existing sorters are designed to sort materials in a binary manner, where an air nozzle at the end of the conveyor discharges one class into one of two bins. If eight classes need to be separated, as in Zorba's case, the entire stream must be run across the binary sorter in eight different passes, which takes eight times longer than trying to remove a single object in the stream. Embodiments of this disclosure allow multiple classes to be sorted in a single pass, which in this case reduces the overall sorting time to one-eighth.

[0225] Aspects of the present disclosure provide a method for sorting material pieces from a stream of material being transported, the method comprising: performing one or more vision checks on each material piece in the stream of material being transported, each of which includes classifying the material piece in response to processing a visual image captured from the material piece through an AI system; performing one or more sensor system classifications on each material piece in the stream of material being transported; and sorting the material pieces from the stream of material into one or more classification groups in response to a combination of the one or more vision checks and the one or more sensor system classifications. The stream of material being transported may include one or more wrought aluminum alloys and one or more cast aluminum alloys, and the sorting step includes sorting one or more of the wrought aluminum alloys from the stream of material to one or more first classification groups based on a first combination of one or more vision checks and one or more sensor system classifications, and sorting one or more of the cast aluminum alloys from the stream of material to one or more second classification groups based on a second combination of one or more vision checks and one or more sensor system classifications, wherein the step of sorting one or more wrought aluminum alloys from the stream of material is performed before the step of sorting one or more cast aluminum alloys from the stream of material, and optionally the first combination includes a vision check to determine whether the material piece is composed of a wrought aluminum alloy and one or more sensor system classifications based on the measured amounts of copper and zinc in the material piece, optionally the second combination includes a vision check to determine whether the material piece is composed of a cast aluminum alloy,The process includes one or more sensor system classifications based on measured amounts of copper and zinc in a material piece, and optionally, a second combination also includes a vision check to determine whether the material piece is composed of a wrought aluminum alloy, the vision check being performed before a vision check to determine whether the material piece is composed of a cast aluminum alloy. The step of sorting one or more wrought aluminum alloys from a stream of material being transported into one or more first classification groups is to sort the material piece from the stream of material pieces to be classified as a 2xxx series wrought aluminum alloy when a) the vision check determines that the material piece is composed of a wrought aluminum alloy, and (1) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a first pre-determined value, and (2) the measured amount of copper in the material piece is greater than a second pre-determined value, or b) the vision check determines that the material piece is composed of a wrought aluminum alloy, and (1) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a first pre-determined value Steps to sort the material piece from the material piece stream to be classified as a 7xxx series wrought aluminum alloy when the sensor system classification determines that (1) the measured amount of zinc in the material piece is less than the determined value, and (2) the measured amount of zinc in the material piece is greater than a second predetermined value, or c) Steps to sort the material piece from the material piece stream to be classified as a 3xxx and / or 5xxx and / or 6xxx series wrought aluminum alloy when: (1) the vision check determines that the material piece is made of a wrought aluminum alloy, and (2) the first of one or more sensor system classifications determines that (i) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is not greater than a first predetermined value, and(ii) The measured amount of copper in the material piece is not greater than a second predetermined value, and (3) The second of one or more sensor system classifications determines that (i) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is not less than a third predetermined value, and (ii) the measured amount of zinc in the material piece is not greater than a fourth predetermined value. The step of sorting one or more cast aluminum alloys from a stream of material being transported into one or more second classification groups is to sort the material piece from the stream of material pieces so that it is classified as 360 cast aluminum alloy when a vision check determines that the material piece is not composed of wrought aluminum alloy, a first of one or more sensor system classifications determines that the total measured amount of copper and zinc in the material piece is not greater than a first predetermined value, and a second of one or more sensor system classifications determines that the measured amount of iron in the material piece is greater than a second predetermined value, or b) the material piece is composed of wrought aluminum alloy When the vision check determines that there is no copper and zinc in the material piece, and the first of one or more sensor system classifications determines that the total measured amount of copper and zinc in the material piece is not greater than the first predetermined value, and the second of one or more sensor system classifications determines that the measured amount of iron in the material piece is not greater than the second predetermined value, the step of sorting the material piece from the material piece stream to be classified as 356 cast aluminum alloy, or c) When the following applies, the step of sorting the material piece from the material piece stream to be classified as 38x cast aluminum alloy: (1) The vision check determines that the material piece is made of cast aluminum alloy,(2) A first of one or more sensor system classifications determines that the total measured amount of copper and zinc in the material piece is greater than a first predetermined value, and (3) A second of one or more sensor system classifications determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a second predetermined value and less than a third predetermined value, or d) A step of sorting the material piece from the stream of material pieces to be classified as 319 cast aluminum alloy when: (1) VisionCheck determines that the material piece is made of cast aluminum alloy, and (2) A first of one or more sensor system classifications determines that the total measured amount of copper and zinc in the material piece is greater than a first predetermined value, and (3) A second of one or more sensor system classifications determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a second predetermined value and less than a third predetermined value. The method may further include the step of sorting a material piece from a stream of material pieces so that it is classified as a die-cast zinc piece when: (1) a vision check determines that the material piece is not composed of a wrought aluminum alloy, (2) a first of one or more sensor system classifications determines that the total measured amount of copper and zinc in the material piece is greater than a first predetermined value, and (3) a second of one or more sensor system classifications determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is less than a second predetermined value. The stream of material being transported may include Zorba material. The method may further include the step of sorting one or more junk materials from the stream of material being transported based on one or more vision checks, the step of sorting junk materials isThis step is performed before the steps of sorting one or more wrought aluminum alloys and one or more cast aluminum alloys. The method may further include the step of sorting extruded aluminum alloys from a stream of material into one or more third classification groups based on a third combination of one or more vision checks, the step of sorting one or more extruded aluminum alloys from a stream of material being performed after the step of sorting one or more wrought aluminum alloys from a stream of material, and before the step of sorting one or more cast aluminum alloys from a stream of material. Each of the one or more sensor system classifications can be performed by a spectroscopic system. The spectroscopic system can be an X-ray fluorescence system. Each of the one or more vision checks can be performed by a single vision system implementing one or more AI models in an AI system, and each of the one or more sensor system classifications can be performed by a single spectroscopic system implementing one or more algorithms for analyzing spectral data collected from material pieces.

[0226] Aspects of the present disclosure are methods for sorting material pieces from a stream of conveyed Zorba material, the method comprising the steps of: performing a vision check on each material piece in the stream of conveyed Zorba material, each vision check comprising classifying each material piece in accordance with processing a visual image captured from each material piece through an AI system, the vision checks being performed by a single vision system implementing a different AI model in the AI ​​system for each vision check; performing a sensor system classification on each material piece in the stream of conveyed Zorba material, each sensor system classification being performed by a different algorithm analyzing spectral data collected from each material piece by a single spectroscopic system; and one or more of the vision checks. The method provides a method comprising the steps of: sorting multiple different wrought aluminum alloy material pieces from a stream of conveyed Zorba material into separately sorted classification groups based on one or more first combinations of sensor system classifications and; sorting multiple different cast aluminum alloy material pieces from a stream of conveyed Zorba material into separately sorted classification groups based on one or more vision checks and one or more second combinations of sensor system classifications, wherein optionally, the step of sorting multiple different wrought aluminum alloy material pieces from a stream of conveyed Zorba material is performed before the step of sorting multiple different cast aluminum alloy material pieces from a stream of conveyed Zorba material, optionally, the sensor system classification is based on measured amounts of copper and zinc in the material piece, and optionally, the single spectroscopic system is an X-ray fluorescence system. The step of sorting multiple different wrought aluminum alloy material pieces from a stream of conveyed Zorba material into separately sorted classification groups is performed if a) a vision check determines that the material piece is composed of a wrought aluminum alloy, and(1) When the first sensor system classification determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a first predetermined value, and (2) the measured amount of copper in the material piece is greater than a second predetermined value, the step is to sort the material piece from the Zorba material stream being transported so that it is classified as a 2xxx series wrought aluminum alloy, or b) when the vision check determines that the material piece is made of a wrought aluminum alloy, and (1) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is less than a third predetermined value, and (2) the measured amount of zinc in the material piece is less than a fourth predetermined value The procedure may include either of the following steps: when the second sensor system classification determines that the material is greater than a certain value, sort the material piece from the stream of transported Zorba material to be classified as a 7xxx series wrought aluminum alloy; or c) when the second sensor system classification determines that (1) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is not less than a third predetermined value, and (2) the measured amount of zinc in the material piece is not greater than a fourth predetermined value, sort the material piece from the stream of transported Zorba material to be classified as a 3xxx and / or 5xxx and / or 6xxx series wrought aluminum alloy. The step of sorting multiple different cast aluminum alloy material pieces from a stream of conveyed Zorba material into separately sorted classification groups is a) the step of sorting the material piece from the stream of conveyed Zorba material to be classified as 360 cast aluminum alloy when a vision check determines that the material piece is composed of cast aluminum alloy, a first sensor system classification determines that the total measured amount of copper and zinc in the material piece is less than a first predetermined value, and a second system classification determines that the measured amount of iron in the material piece is greater than a second predetermined value, orb) When the vision check determines that the material piece is made of cast aluminum alloy, the first sensor system classification determines that the total measured amount of copper and zinc in the material piece is less than the first predetermined value, and the second system classification determines that the measured amount of iron in the material piece is less than the second predetermined value, the step of sorting the material piece from the Zorba material stream to be classified as 356 cast aluminum alloy, or c) When the vision check determines that the material piece is made of cast aluminum alloy, the first sensor system classification determines that the total measured amount of copper and zinc in the material piece is greater than the first predetermined value, and the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than the third predetermined value The system may include either of the following steps: d) when the third sensor system classification determines that the material piece is smaller than a fourth predetermined value, the material piece is sorted from the Zorba material stream being transported to be classified as 38x cast aluminum alloy; or d) when the vision check determines that the material piece is made of cast aluminum alloy, the first sensor system classification determines that the total measured amount of copper and zinc in the material piece is greater than a first predetermined value, and the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a fourth predetermined value and smaller than a fifth predetermined value, the material piece is sorted from the Zorba material stream being transported to be classified as 319 cast aluminum alloy. This method involves a vision check determining that the material piece is composed of a cast aluminum alloy, a first sensor system classification determining that the total measured amount of copper and zinc in the material piece is greater than a first predetermined value, and a third predetermined value determining that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is less than a third predetermined value.When the fifth sensor system classification is determined, it may further include the step of sorting the material piece from the stream of conveyed Zorba material so that it is classified as a die-cast zinc piece.

[0227] Aspects of the present disclosure provide a system for sorting material pieces, the system comprising: a conveyor system configured to transport a stream of material; a vision system configured to perform one or more vision checks on each material piece in the transported stream of material, each of which includes classifying each material piece in response to processing a visual image captured from each material piece through an AI system; a sensor system configured to perform one or more sensor system classifications on each material piece in the transported stream of material; and a sorting device configured to sort material pieces from the transported stream into one or more classification groups in response to commands received from a combination of one or more vision checks and one or more sensor system classifications. The stream of material being transported may include one or more wrought aluminum alloys and one or more cast aluminum alloys, and the sorting device is configured to sort one or more of the wrought aluminum alloys from the stream of material being transported into one or more first classification groups in response to commands received from a first combination of one or more vision checks and one or more sensor system classifications, and is configured to sort one or more of the cast aluminum alloys from the stream of material being transported into one or more second classification groups in response to commands received from a second combination of one or more vision checks and one or more sensor system classifications, the step of sorting one or more wrought aluminum alloys from the stream of material being transported is performed before the step of sorting one or more cast aluminum alloys from the stream of material being transported, and optionally, the first combination includes a vision check for determining whether a material piece is composed of a wrought aluminum alloy and one or more sensor system classifications based on measured amounts of copper and zinc in the material piece, optionally,A second combination includes a vision check to determine whether a material piece is made of cast aluminum alloy and one or more sensor system classifications based on measured amounts of copper and zinc in the material piece, optionally, the second combination also includes a vision check to determine whether a material piece is made of wrought aluminum alloy, the vision check being performed before the vision check to determine whether the material piece is made of cast aluminum alloy. A sorting device configured to sort one or more wrought aluminum alloys from a stream of conveyed material into one or more first classification groups is configured to sort a material piece from a stream of material pieces as a 2xxx series wrought aluminum alloy in response to a command received from a combination of a vision check determining that a material piece is made of wrought aluminum alloy and sensor system classification determining that (1) the ratio of measured amount of copper to measured amount of zinc in the material piece is greater than a first predetermined value and (2) the measured amount of copper in the material piece is greater than a second predetermined value. A sorting device configured to sort material pieces into 7xxx series wrought aluminum alloys in response to commands received from a combination of a vision check that determines that a material piece is made of wrought aluminum alloy and a sensor system classification that determines that (1) the ratio of measured amount of copper to measured amount of zinc in the material piece is less than a first predetermined value and (2) the measured amount of zinc in the material piece is greater than a second predetermined value, or a sorting device configured to sort material pieces into 7xxx series wrought aluminum alloys in response to commands received from a combination of the following:A sorting device configured to sort material pieces from a stream of material pieces into 3xxx and / or 5xxx and / or 6xxx series wrought aluminum alloys, which may include: (1) a vision check determining that a material piece is composed of a wrought aluminum alloy; and (2) a first of one or more sensor system classifications determining that: (i) the ratio of measured amount of copper to measured amount of zinc in the material piece is not greater than a first predetermined value; and (ii) the measured amount of copper in the material piece is not greater than a second predetermined value; and (3) a second of one or more sensor system classifications determining that: (i) the ratio of measured amount of copper to measured amount of zinc in the material piece is not less than a third predetermined value; and (ii) the measured amount of zinc in the material piece is not greater than a fourth predetermined value. A sorting device configured to sort one or more cast aluminum alloys from a stream of material being transported into one or more second classification groups is configured to sort a material piece from a stream of material pieces to be classified as 360 cast aluminum alloy in response to a command received from a combination of a first vision check determining that a material piece is not composed of wrought aluminum alloy, a first of one or more sensor system classifications determining that the total measured amount of copper and zinc in the material piece is not greater than a first predetermined value, and a second of one or more sensor system classifications determining that the measured amount of iron in the material piece is greater than a second predetermined value, or b) a first vision check determining that a material piece is not composed of wrought aluminum alloy, a first of one or more sensor system classifications determining that the total measured amount of copper and zinc in the material piece is not greater than a first predetermined value,A sorting device configured to sort a material piece from a stream of material pieces into 356 cast aluminum alloy in response to a command received from a combination of the following: (1) a vision check determining that the material piece is made of cast aluminum alloy; and (2) a first of the following sensor system classifications determining that the total measured amount of copper and zinc in the material piece is greater than a first predetermined value; and (3) a second of the following sensor system classifications determining that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a second predetermined value. A sorting device configured to sort a material piece from a stream of material pieces to be classified as 319 cast aluminum alloy in response to a command received from a second of one or more sensor system classifications that determines that the material piece is greater than a predetermined value and less than a third predetermined value, or from a combination of the following: (1) a vision check that determines that the material piece is composed of cast aluminum alloy; (2) a first of one or more sensor system classifications that determines that the total measured amount of copper and zinc in the material piece is greater than a first predetermined value; and (3) a third of one or more sensor system classifications that determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a third predetermined value and less than a fourth predetermined value.

[0228] The system may further include a sorting device configured to sort material pieces from a stream of material pieces into die-cast zinc pieces in response to commands received from a combination of the following: (1) a first vision check determining that the material piece is not composed of a wrought aluminum alloy; (2) a first of one or more sensor system classifications determining that the total measured amount of copper and zinc in the material piece is greater than a first predetermined value; and (3) a third of one or more sensor system classifications determining that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is less than a third predetermined value. The stream of material being transported may include Zorba material. The system may further include a sorting device configured to sort one or more junk materials from the stream of material being transported in response to commands received from a combination of one or more vision checks, wherein the step of sorting junk materials is performed before the steps of sorting one or more wrought aluminum alloys and one or more cast aluminum alloys. The system may further include a sorting device configured to sort extruded aluminum alloys from a stream of material into one or more third classification groups in response to commands received from one or more third combinations of vision checks, wherein the step of sorting one or more extruded aluminum alloys from a stream of material is performed after the step of sorting one or more wrought aluminum alloys from a stream of material, and before the step of sorting one or more cast aluminum alloys from a stream of material. Each of the one or more sensor system classifications may be performed by a spectroscopic system, and optionally, the sensor system is an X-ray fluorescence system.Each of the one or more vision checks can be performed by a single vision system implementing one or more AI models within an AI system, and each of the one or more sensor system classifications can be performed by a single spectroscopic system implementing one or more algorithms for analyzing spectral data collected from material pieces, optionally the spectroscopic system being an X-ray fluorescence system.

[0229] In this specification, "configuring" a device, or a device "configured" to perform some function, can include selecting predefined logical blocks and logically associating them so that they provide a specific logical function, which should be understood to include monitoring or control functions. It can also include programming computer software-based logic for a modified control device, wiring discrete hardware components, or any or all of the above. Such a configured device is physically designed to perform one or more specified functions.

[0230] In this description, numerous specific details are provided, such as examples of programming, software modules, user selection, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, and controllers, in order to provide a thorough understanding of embodiments of the disclosure. However, those skilled in the art will recognize that the disclosure can be practiced without one or more of these specific details, or using other methods, components, materials, etc. In other cases, well-known structures, materials, or operations may not be shown or described in detail to avoid obscuring aspects of the disclosure.

[0231] Throughout this specification, any reference to “one embodiment,” “multiple embodiments,” or similar language means that a particular feature, structure, or characteristic described in relation to an embodiment is included in at least one embodiment of this disclosure. Therefore, throughout this specification, the occurrences of the words “in one embodiment,” “in a particular embodiment,” “a variety of embodiments,” and similar language may, but not necessarily, refer to the same embodiment. Furthermore, the features, structures, aspects, and / or characteristics described in this disclosure can be combined in any suitable manner in one or more embodiments. Accordingly, even if features may be initially claimed to act in a particular combination, one or more features from a claimed combination can, in some cases, be removed from that combination, and the claimed combination can be directed towards subcombinations or variations of subcombinations.

[0232] Benefits, advantages, and solutions to problems have been described above with respect to specific embodiments. However, benefits, advantages, solutions to problems, and any elements that may cause any benefit, advantage, or solution to arise or become more prominent should not be construed as important, necessary, or essential features or elements of any or all claims. Furthermore, components described herein are not required for the practice of this disclosure unless expressly described as essential or important.

[0233] A person skilled in the art who has read this disclosure will recognize that modifications and alterations can be made to the embodiments without departing from the scope of this disclosure. It should be recognized that specific implementations shown and described herein may be for illustrative purposes of the disclosure and its best mode, and may not be intended in any way to limit the scope of this disclosure. Other modifications may be found within the appended claims.

[0234] This specification contains many specific examples, which should not be construed as limitations on the scope of this disclosure or the scope of the claims, but rather as descriptions of features specific to particular implementations of this disclosure. Headings in this specification may not be intended to limit this disclosure, the embodiments of this disclosure, or other matters disclosed under those headings.

[0235] In this specification, the term “or” may be intended to be inclusive; “A or B” includes A or B, and also includes both A and B. When used in the context of a list of entities, as used herein, the term “and / or” refers to the entities existing individually or in combination. Thus, for example, the phrase “A, B, C, and / or D” includes A, B, C, and D individually, but also any and all combinations and subcombinations of A, B, C, and D.

[0236] The technical terms used herein are for the sole purpose of describing specific embodiments and are not intended to limit the disclosure. As used herein, the singular forms "a," "an," and "the" may also be intended to include the plural forms unless the context explicitly indicates otherwise.

[0237] All means or step-plus-function elements in the following claims may include any structures, materials, or actions for performing a function in combination with other claimed elements, such as those specifically claimed.

[0238] As used herein with respect to identified characteristics or circumstances, “substantially” refers to a degree of deviation that is small enough not to impair the identified characteristics or circumstances to a measurable degree. The exact degree of acceptable deviation may, in some cases, depend on the specific context.

[0239] As used herein, multiple items, structural elements, compositional elements, and / or materials may be presented in common lists for convenience. However, these lists should be interpreted as if each member of the list were individually identified as a distinct and unique member. Therefore, individual members of such lists should not be interpreted as de facto equivalents of any other members of the same list, solely on the basis that they are presented in a common group, unless otherwise indicated.

[0240] Unless otherwise defined, all technical and scientific terms used herein (such as acronyms used in reference to chemical elements in the periodic table) have the same meaning as those generally understood by those skilled in the art in the field to which the disclosed subject matter belongs. Any methods, devices, and materials similar to or equivalent to those described herein may be used in the practice or testing of the disclosed subject matter, but representative methods, devices, and materials are described herein. [Explanation of Symbols]

[0241] 100 Material Handling Systems 101 Material Pieces 102 Hopper 103 Conveyor System 104 Conveyor System Motor 105 Position detector 106 Singulator 107 Computer Systems 108 Automation Control System 109 Still cameras, live action cameras 110 Vision System 111 Material Piece Tracking Device 112 Control Systems 120 Sensor System 121 Energy Release Sources 122 Power supply 123 Control System 124 detectors 125 Detector Electronic Equipment 126 sorting devices 127 Sorting devices 128 sorting devices 129 Sorting devices 136 Sorting and receiving section 137 Sorting and receiving section 138 Sorting and receiving section 139 Sorting and receiving section 140 Receptor part 800 Material Handling System 801 Vision System, XRF System 802 Sorting device 803 Sorting device 804 Sorting device 805 Conveyor System 806 Conveyor System 807 Conveyor System 808 Conveyor System 1600 Material Handling System 1601 Material Pieces 1602 Conveyor Belt 1603 Conveyor System 1604 Conveyor System 1605 Conveyor System 1606 Conveyor System 1607 Conveyor System 1608 Conveyor System 1610 XRF or AI system 1611 XRF or AI system 1612 XRF or AI system 1620 sorting device 1621 Sorting device 1622 Sorting device 1630 Receptor part 1631 Receptor part 1632 Receptor part 1633 Receptor part 3400 Computer Systems 3401 GPU 3405 Local Bus 3412 User Interface Adapter 3413 Keyboard 3414 Mouse 3415 Processor, CPU 3416 Display Adapter 3420 volatile memory 3425 Communication Adapter 3430 I / O Adapter 3431 Hard Disk Drive 3432 Tape Drive 3435 Non-volatile memory 3440 displays 3801a Materials, material pieces 3801b Material piece 3801c Material Piece 3802a Ramp, chute 3802b is deposited 3802c Deposited 3802d is deposited 3803a Conveyor System 3803b Conveyor System 3803c Conveyor System 3803d Conveyor System 3810a Material Classification System 3810b Material Classification System 3810c Material Classification System 3810d Material Classification System 3826a Sorter 3826b Sorter 3826c Sorter 3826d Sorter 3836a Receiver 3836b Aluminum Alloy (Twitch) Material Piece, Receiver 3836c Copper 3836d Receiver 3837c Copper Wire 3837d Receiver 3840 Receiver

Claims

1. A method for sorting material pieces from a stream of material being transported, A step of performing one or more vision checks on each material piece in the stream of material being transported, wherein each of the one or more vision checks includes classifying each material piece in response to processing a visual image captured from each material piece through an artificial intelligence ("AI") system, The steps include performing one or more sensor system classifications on each material piece in the stream of material being transported, The steps include sorting material pieces from the stream of material being transported into one or more classification groups, depending on the combination of the one or more vision checks and the one or more sensor system classifications, and Methods that include...

2. The stream of material being transported includes one or more wrought aluminum alloys and one or more cast aluminum alloys, and the sorting step is: A step of sorting one or more of the wrought aluminum alloys from the stream of material being transported into one or more first classification groups based on a first combination of one or more vision checks and one or more sensor system classifications, A step of sorting one or more of the cast aluminum alloys from the stream of material being transported into one or more second classification groups based on a second combination of the one or more vision checks and the one or more sensor system classifications. Includes, The step of separating one or more wrought aluminum alloys from the stream of material being transported is performed before the step of separating one or more cast aluminum alloys from the stream of material being transported. Optionally, the first combination includes a vision check to determine whether a material piece is composed of a wrought aluminum alloy, and one or more sensor system classifications based on measured amounts of copper and zinc in the material piece. Optionally, the second combination includes a vision check to determine whether the material piece is composed of a cast aluminum alloy, and one or more sensor system classifications based on the measured amounts of copper and zinc in the material piece. The method according to claim 1, wherein optionally the second combination also includes a vision check to determine whether the material piece is composed of a wrought aluminum alloy, the vision check being performed prior to the vision check to determine whether the material piece is composed of a cast aluminum alloy.

3. The step of sorting one or more of the wrought aluminum alloys from the stream of material being transported into one or more first classification groups is: a) When the vision check determines that the material piece is made of a wrought aluminum alloy, and the sensor system classification determines that (1) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a first predetermined value, and (2) the measured amount of copper in the material piece is greater than a second predetermined value, the step is to sort the material piece from the stream of material pieces so that it is classified as a 2xxx series wrought aluminum alloy, or b) When the vision check determines that the material piece is made of a wrought aluminum alloy, and the sensor system classification determines that (1) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is less than a first predetermined value, and (2) the measured amount of zinc in the material piece is greater than a second predetermined value, the step is to sort the material piece from the stream of material pieces so that it is classified as a 7xxx series wrought aluminum alloy, or c) The step of sorting the material piece from the stream of material pieces so that it is classified as a 3xxx and / or 5xxx and / or 6xxx series wrought aluminum alloy when the following conditions apply: (1) Vision check determines that the material piece is composed of a wrought aluminum alloy, and (2) The first of the one or more sensor system classifications determines the following: (i) The ratio of the measured amount of copper to the measured amount of zinc in the material piece is not greater than a first predetermined value, and (ii) The measured amount of copper in the material piece is not greater than a second predetermined value, (3) When the second of the one or more sensor system classifications determines the following: (i) The ratio of the measured amount of copper to the measured amount of zinc in the material piece is not less than a third predetermined value, and (ii) The measured amount of zinc in the material piece is not greater than a fourth predetermined value. The method according to claim 2, comprising any of the following:

4. The step of sorting one or more of the cast aluminum alloys from the stream of material being transported into one or more second classification groups is: a) When VisionCheck determines that the material piece is not composed of a wrought aluminum alloy, and a first of the one or more sensor system classifications determines that the total measured amount of copper and zinc in the material piece is not greater than a first predetermined value, and a second of the one or more sensor system classifications determines that the measured amount of iron in the material piece is greater than a second predetermined value, the step of sorting the material piece from the stream of material pieces to be classified as a 360 cast aluminum alloy, or b) When the vision check determines that the material piece is not composed of a wrought aluminum alloy, and the first of the one or more sensor system classifications determines that the measured total amount of copper and zinc in the material piece is not greater than a first predetermined value, and the second of the one or more sensor system classifications determines that the measured amount of iron in the material piece is not greater than a second predetermined value, the step of sorting the material piece from the stream of material pieces to be classified as 356 cast aluminum alloy, or c) The step of sorting the material piece from the stream of material pieces so that it is classified as 38x cast aluminum alloy when the following conditions are met: (1) Vision check determines that the material piece is made of cast aluminum alloy, and (2) The first of the one or more sensor system classifications determines that the measured total amount of copper and zinc in the material piece is greater than the first predetermined value, (3) When the second of the one or more sensor system classifications determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a second predetermined value and less than a third predetermined value, d) Steps to sort the material piece from the stream of material pieces so that it is classified as 319 cast aluminum alloy: (1) Vision check determines that the material piece is made of cast aluminum alloy, and (2) The first of the one or more sensor system classifications determines that the measured total amount of copper and zinc in the material piece is greater than the first predetermined value, (3) When the second of the one or more sensor system classifications determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a second predetermined value and less than a third predetermined value, The method according to claim 2, comprising any of the following:

5. The following steps involve sorting a material piece from the stream of material pieces so that it is classified as a die-cast zinc piece: (1) The vision check determined that the material piece is not made of wrought aluminum alloy, and (2) The first of the one or more sensor system classifications determines that the measured total amount of copper and zinc in the material piece is greater than the first predetermined value, (3) When the second of the one or more sensor system classifications determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is less than the second predetermined value, The method according to claim 4, further comprising:

6. The method according to any one of claims 2 to 5, wherein the stream of material being transported includes Zorba material, and the method further includes the step of sorting one or more junk materials from the stream of material being transported based on one or more vision checks, wherein the step of sorting the junk materials is performed before the step of sorting the one or more wrought aluminum alloys and the step of sorting the one or more cast aluminum alloys.

7. The method according to any one of claims 2 to 5, further comprising the step of sorting extruded aluminum alloys from a stream of material being transported into one or more third classification groups based on a third combination of the one or more vision checks, wherein the step of sorting the one or more extruded aluminum alloys from a stream of material being transported is performed after the step of sorting the one or more wrought aluminum alloys from a stream of material being transported, and before the step of sorting the one or more cast aluminum alloys from a stream of material being transported.

8. Each of the above classifications of one or more sensor systems is performed by a spectroscopic system. The method according to any one of claims 2 to 5, wherein optionally the spectroscopic system is an X-ray fluorescence system.

9. Each of the one or more vision checks is performed by a single vision system implementing one or more AI models in the AI ​​system, and each of the one or more sensor system classifications is performed by a single spectroscopic system implementing one or more algorithms for analyzing spectral data collected from the material piece. The method according to any one of claims 2 to 5, wherein optionally the spectroscopic system is an X-ray fluorescence system.

10. A method for sorting material pieces from a stream of conveyed Zorba material, A step of performing a vision check on each material piece in the stream of conveyed Zorba material, wherein each of the vision checks includes classifying each material piece in accordance with processing a visual image captured from each material piece through an artificial intelligence ("AI") system, and the vision checks are performed by a single vision system that implements a different AI model within the AI ​​system for each of the vision checks, A step of performing sensor system classification on each material piece in the stream of conveyed Zorba material, wherein each of the sensor system classifications is performed by a different algorithm that analyzes spectral data collected from each material piece by a single spectroscopic system, A step of sorting a plurality of different wrought aluminum alloy material pieces from the stream of conveyed Zorba material into separately sorted classification groups based on one or more of the vision checks and one or more first combinations of the sensor system classifications, A step of sorting multiple different cast aluminum alloy material pieces from the stream of conveyed Zorba material into separately sorted classification groups based on one or more of the aforementioned vision checks and one or more second combinations of the aforementioned sensor system classifications, Includes, The step of optionally sorting the plurality of different wrought aluminum alloy material pieces from the stream of conveyed Zorba material is performed prior to the step of sorting the plurality of different cast aluminum alloy material pieces from the stream of conveyed Zorba material. The classification of the sensor system is based on the measured amounts of copper and zinc in the material piece. The method wherein the single spectroscopic system is optionally an X-ray fluorescence system.

11. The step of sorting a plurality of different wrought aluminum alloy material pieces from the stream of conveyed Zorba material into separately sorted classification groups is: a) When a vision check determines that a material piece is made of a wrought aluminum alloy, and the first sensor system classification determines that (1) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a first predetermined value, and (2) the measured amount of copper in the material piece is greater than a second predetermined value, the step is to sort the material piece from the stream of conveyed Zorba material so that it is classified as a 2xxx series wrought aluminum alloy, or b) When the vision check determines that the material piece is made of a wrought aluminum alloy, and the second sensor system classification determines that (1) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is less than a third predetermined value, and (2) the measured amount of zinc in the material piece is greater than a fourth predetermined value, the step is to sort the material piece from the stream of conveyed Zorba material so that it is classified as a 7xxx series wrought aluminum alloy, or c) When the second sensor system classification determines that (1) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is not less than the third predetermined value, and (2) the measured amount of zinc in the material piece is not greater than the fourth predetermined value, the step of sorting the material piece from the stream of conveyed Zorba material to be classified as 3xxx and / or 5xxx and / or 6xxx series wrought aluminum alloy, The method according to claim 10, comprising any of the following:

12. The step of sorting multiple different cast aluminum alloy material pieces from the stream of conveyed Zorba material into separately sorted classification groups is: a) When a vision check determines that a material piece is made of cast aluminum alloy, a first sensor system classification determines that the total measured amount of copper and zinc in the material piece is less than a first predetermined value, and a second system classification determines that the measured amount of iron in the material piece is greater than a second predetermined value, the step of sorting the material piece from the transported Zorba material stream to be classified as 360 cast aluminum alloy, or b) When the vision check determines that the material piece is made of cast aluminum alloy, the first sensor system classification determines that the measured total amount of copper and zinc in the material piece is less than the first predetermined value, and the second system classification determines that the measured amount of iron in the material piece is less than the second predetermined value, the step of sorting the material piece from the stream of conveyed Zorba material to be classified as 356 cast aluminum alloy, or c) When the vision check determines that the material piece is made of cast aluminum alloy, the first sensor system classification determines that the total measured amount of copper and zinc in the material piece is greater than a first predetermined value, and the third sensor system classification determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a third predetermined value and less than a fourth predetermined value, the step of sorting the material piece from the stream of conveyed Zorba material to be classified as 38x cast aluminum alloy, or d) When the vision check determines that the material piece is made of a cast aluminum alloy, the first sensor system classification determines that the measured total amount of copper and zinc in the material piece is greater than the first predetermined value, and the fourth sensor system classification determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than the fourth predetermined value and less than the fifth predetermined value, the step of sorting the material piece from the stream of conveyed Zorba material to be classified as 319 cast aluminum alloy. The method according to claim 10, comprising any of the following:

13. The method according to claim 12, further comprising the step of sorting the material piece from the stream of conveyed Zorba material to be classified as a die-cast zinc piece when the vision check determines that the material piece is composed of a cast aluminum alloy, the first sensor system classification determines that the measured total amount of copper and zinc in the material piece is greater than the first predetermined value, and the fifth sensor system classification determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is less than the third predetermined value.

14. It is a system for sorting material pieces. A conveyor system configured to transport a stream of materials, A vision system configured to perform one or more vision checks on each material piece in the stream of material being transported, wherein each of the one or more vision checks includes classifying each material piece in response to processing a visual image captured from each material piece through an artificial intelligence ("AI") system, A sensor system configured to perform one or more sensor system classifications on each material piece in the stream of material being transported, A sorting device configured to sort material pieces from a stream of material into one or more classification groups in response to commands received from one or more combinations of vision checks and one or more sensor system classifications, A system that includes this.

15. The stream of material being transported includes one or more wrought aluminum alloys and one or more cast aluminum alloys, and the sorting device is It is configured to sort one or more of the wrought aluminum alloys from the stream of material being transported into one or more first classification groups in response to a command received from the first combination of the one or more vision checks and the one or more sensor system classifications, and The system is configured to sort one or more of the cast aluminum alloys from the stream of material being transported into one or more second classification groups in response to a command received from a second combination of one or more vision checks and one or more sensor system classifications. The step of optionally separating one or more wrought aluminum alloys from the stream of material being transported is performed before the step of separating one or more cast aluminum alloys from the stream of material being transported. Optionally, the first combination includes a vision check to determine whether a material piece is composed of a wrought aluminum alloy, and one or more sensor system classifications based on measured amounts of copper and zinc in the material piece. Optionally, the second combination includes a vision check to determine whether the material piece is composed of a cast aluminum alloy, and one or more sensor system classifications based on the measured amounts of copper and zinc in the material piece. The system according to claim 14, wherein the second combination optionally includes a vision check to determine whether the material piece is composed of a wrought aluminum alloy.

16. The sorting device, configured to sort one or more of the wrought aluminum alloys from the stream of material being transported into one or more first classification groups, a) A sorting device configured to sort a material piece from a stream of material pieces to be classified as a 2xxx series wrought aluminum alloy in response to a command received from a combination of a vision check that determines that a material piece is composed of a wrought aluminum alloy and a sensor system classification that determines that (1) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a first predetermined value and (2) the measured amount of copper in the material piece is greater than a second predetermined value, or b) The sorting device is configured to sort the material piece from a stream of material pieces to be classified as a 7xxx series wrought aluminum alloy in response to a command received from a combination of a vision check that determines that the material piece is composed of a wrought aluminum alloy and a sensor system classification that determines that (1) the ratio of the measured amount of copper to the measured amount of zinc in the material piece is less than a first predetermined value and (2) the measured amount of zinc in the material piece is greater than a second predetermined value, or c) The sorting device, configured to sort material pieces from a stream of material pieces into 3xxx and / or 5xxx and / or 6xxx series wrought aluminum alloys in response to commands received from a combination of the following: (1) A vision check to determine that the material piece is made of wrought aluminum alloy. (2) The first of the one or more sensor system classifications that determines the following: (i) The ratio of the measured amount of copper to the measured amount of zinc in the material piece is not greater than a first predetermined value, and (ii) The measured amount of copper in the material piece is not greater than a second predetermined value, and (3) The second of the one or more sensor system classifications that determines the following: (i) The ratio of the measured amount of copper to the measured amount of zinc in the material piece is not less than a third predetermined value, and (ii) The measured amount of zinc in the material piece is not greater than a fourth predetermined value. The system according to claim 15, comprising any of the following:

17. The sorting device, configured to sort one or more of the cast aluminum alloys from the stream of material being transported into one or more second classification groups, a) The sorting device is configured to sort the material piece from a stream of material pieces to be classified as 360 cast aluminum alloy in response to a command received from a combination of the first vision check which determines that the material piece is not composed of a wrought aluminum alloy, the first of the one or more sensor system classifications which determines that the total measured amount of copper and zinc in the material piece is not greater than a first predetermined value, and the second of the one or more sensor system classifications which determines that the measured amount of iron in the material piece is greater than a second predetermined value, or b) The sorting device is configured to sort the material piece from a stream of material pieces to be classified as 356 cast aluminum alloy in response to a command received from a combination of the first vision check which determines that the material piece is not composed of a wrought aluminum alloy, the first of the one or more sensor system classifications which determines that the measured total amount of copper and zinc in the material piece is not greater than the first predetermined value, and the second of the one or more sensor system classifications which determines that the measured amount of iron in the material piece is not greater than the second predetermined value, or c) The sorting device, configured to sort material pieces from a stream of material pieces to be classified as 38x cast aluminum alloy in response to commands received from a combination of the following: (1) The vision check that determines that the material piece is made of a cast aluminum alloy, and (2) A first of the one or more sensor system classifications that determines that the total measured amount of copper and zinc in the material piece is greater than a first predetermined value, (3) The second of the one or more sensor system classifications that determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than a second predetermined value and less than a third predetermined value, d) The sorting device, configured to sort material pieces from a stream of material pieces to be classified as 319 cast aluminum alloy in response to commands received from a combination of the following: (1) The vision check that determines that the material piece is made of a cast aluminum alloy, and (2) The first of the one or more sensor system classifications that determines that the measured total amount of copper and zinc in the material piece is greater than the first predetermined value, (3) The third of the one or more sensor system classifications that determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is greater than the third predetermined value and less than the fourth predetermined value, The system according to claim 15, comprising any of the following:

18. The sorting device is configured to sort material pieces from a stream of material pieces into die-cast zinc pieces in response to commands received from a combination of the following: (1) The first vision check that determines that the material piece is not composed of a wrought aluminum alloy, and (2) The first of the one or more sensor system classifications that determines that the total measured amount of copper and zinc in the material piece is greater than the first predetermined value, (3) The third of the one or more sensor system classifications that determines that the ratio of the measured amount of copper to the measured amount of zinc in the material piece is less than a third predetermined value, The system according to claim 17, further comprising:

19. The system according to any one of claims 15 to 18, wherein the stream of material being transported includes Zorba material, and the system further includes the sorting device configured to sort one or more junk materials from the stream of material being transported in response to a command received from a combination of one or more vision checks, the step of sorting the junk materials being performed before the step of sorting the one or more wrought aluminum alloys and the step of sorting the one or more cast aluminum alloys.

20. The system according to any one of claims 15 to 18, further comprising the sorting device configured to sort extruded aluminum alloys from a stream of material being transported into one or more third classification groups in response to a command received from a third combination of one or more vision checks, wherein the step of sorting the one or more extruded aluminum alloys from a stream of material being transported is performed after the step of sorting the one or more wrought aluminum alloys from a stream of material being transported and before the step of sorting the one or more cast aluminum alloys from a stream of material being transported.

21. Each of the above classifications of one or more sensor systems is performed by a spectroscopic system. The system according to any one of claims 15 to 18, wherein the sensor system is optionally an X-ray fluorescence system.

22. Each of the one or more vision checks is performed by a single vision system implementing one or more AI models in the AI ​​system, and each of the one or more sensor system classifications is performed by a single spectroscopic system implementing one or more algorithms for analyzing spectral data collected from the material piece. The system according to any one of claims 15 to 18, wherein the spectroscopic system is optionally an X-ray fluorescence system.

23. A computer program product comprising instructions for causing the system according to any one of claims 14 to 18 to perform the method described in any one of claims 1 to 5.

24. A computer-readable storage medium having the computer program product described in claim 23 stored thereon.

Images