Correction techniques for material classification

Abstract

When an x-ray fluorescence ("XRF") spectrum is used to classify material transported on a moving conveyor belt, there is the possibility that an x-ray beam only partially illuminates the piece of material, which may result in capturing an inaccurate XRF spectrum required to classify the piece of material. This may result in improper (erroneous) sorting and final sorting of material pieces, such as aluminum alloys. In a material processing system, an area of intersection between an x-ray beam spot from an x-ray fluorescence system and a piece of material is measured and used accordingly to correct the measured XRF spectrum associated with each piece of material. The material piece can then be sorted according to the corrected XRF spectrum.

Description

[0001] Cross - Reference to Related Applications

[0002] This application claims priority to U.S. Provisional Patent Application Serial No. 63 / 478,823 and U.S. Provisional Patent Application Serial No. 63 / 418,242, both of which are incorporated herein by reference in their entirety. Technical Field

[0003] The present disclosure generally relates to the processing of materials and, in particular, to the classification and / or sorting of materials. Background Art

[0004] This section is intended to introduce aspects of the art that may be related to exemplary embodiments of the present disclosure. This discussion is believed to be helpful in providing a framework for a better understanding of particular aspects of the present disclosure. Accordingly, it should be understood that this section should be viewed in this light and not necessarily as an admission of prior art.

[0005] Recycling is the process of collecting and processing materials that would otherwise be thrown away as trash and turning them into new products. Recycling benefits communities and the environment because it reduces the amount of trash sent to landfills and incinerators, conserves natural resources, improves economic security by using domestic sources of materials, prevents pollution by reducing the need to collect new raw materials, and saves energy. After collection, recyclables are generally sent to a materials recovery facility for sorting, cleaning, and processing into materials that can be used in manufacturing.

[0006] The recycling of aluminum (Al) scrap is a very attractive proposition because it can save up to 95% of the energy costs associated with manufacturing compared to the more expensive extraction of primary aluminum. Primary aluminum is defined as aluminum derived from aluminum - rich ores such as bauxite. At the same time, due to the lightweight nature of aluminum, the demand for aluminum in markets such as the automotive industry is steadily increasing. Therefore, by developing a well - thought - out and simple recycling program or system, certain economic benefits can be obtained for the aluminum industry. The use of recycled materials would be a cheaper source of metal than a primary source of aluminum. As the amount of aluminum sold to the automotive industry (and other industries) increases, it will become increasingly necessary to use recycled aluminum to supplement the availability of primary aluminum.

[0007] Therefore, it is particularly desirable to efficiently separate aluminum scrap metal into alloy families, as mixed aluminum scrap of the same alloy family is much more valuable than alloy mixed indiscriminately. For example, in a blending method for recycling aluminum, any amount of scrap consisting of similar or identical alloys of consistent quality is more valuable than scrap consisting of a mixed aluminum alloy. In such aluminum alloys, aluminum will always be the main body of the material. However, components such as copper, magnesium, silicon, iron, chromium, zinc, manganese, and other alloying elements provide a range of properties to alloyed aluminum and provide a means to distinguish one aluminum alloy from another. Each individual aluminum alloy is a mixture of alloys in which aluminum (Al) is the main metal. Various other alloys (including magnesium (Mg), copper (Cu), silicon (Si), zinc (Zn), and other metals) are used to create their respective different aluminum alloys. Therefore, each individual aluminum alloy has its own distinct chemical and mechanical properties (and ranges), such as tensile strength, yield strength, elongation, and other physical properties.

[0008] The Aluminum Association is the organization that defines the allowable limits of the chemical composition of aluminum alloys. Data on the chemical composition of aluminum wrought alloys are published by the Aluminum Association 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.

[0009] The International Alloy Designation System is the most widely accepted naming scheme for wrought alloys. Each alloy is given a four-digit number (xxxx), where the first digit (Xxxx) indicates the main alloying element, the second digit (xXxx) indicates a variant of the alloy if it is different from "0", and the third and fourth digits (xxXX) are arbitrary numbers used to identify a specific alloy in the series. For example, in aluminum alloy 3105, the first digit "3" indicates that the aluminum alloy is in the manganese series, the second digit "1" indicates the first variant of aluminum alloy 3005, and the third and fourth digits "05" identify a specific alloy in the 3000 series. Generally, wrought aluminum alloys in the 1xxx series consist essentially of pure aluminum with a minimum aluminum content of 99% by weight; the 2xxx series is wrought aluminum mainly alloyed with copper (Cu); the 3xxx series is wrought aluminum mainly alloyed with manganese (Mn); the 4xxx series is wrought aluminum alloyed with silicon (Si); the 5xxx series is wrought aluminum mainly alloyed with magnesium (Mg); the 6xxx series is wrought aluminum mainly alloyed with magnesium and silicon; the 7xxx series is wrought aluminum mainly alloyed with zinc (Zn); and the 8xxx series is a miscellaneous category. The Aluminum Association also has a similar document for cast aluminum alloys.

[0010] The presence of mixed debris of different alloys (i.e., heterogeneous mixtures) in a scrap body limits the ability of the scrap mixture to be effectively recycled unless the different alloys (or at least alloys belonging to different constitutive families (such as alloys designated by the Aluminum Association of America)) can be separated (e.g., sorted) prior to remelting. This is because when mixed scrap of multiple different alloy compositions or families of compositions is remelted, the resulting molten mixture contains proportions of primary alloys and elements (or different constituents) that are too high to meet the compositional limits required for any particular commercial alloy.

[0011] In addition, as demonstrated by the production and sale of Ford F-150 pickup trucks (which have a significantly increased body and frame parts made of aluminum rather than steel), additionally, it is desirable to recycle sheet metal scrap, which includes scrap generated in the manufacture of automotive components from aluminum sheets. Recycling of the scrap involves remelting the scrap to provide a molten metal body that can be cast and / or rolled into useful aluminum parts for further production of such transportation vehicles. However, automotive manufacturing scrap (and metal scrap from other sources such as airplanes, and commercial and household appliances) typically includes scrap pieces of forgings and castings and / or mixtures of two or more aluminum alloys that are substantially different from each other in composition. A specific example of mixed manufacturing scrap of aluminum sheets generated in certain current automotive manufacturing operations is a mixture of one or more alloy pieces of the Aluminum Association of America 5000 series and one or more alloy pieces of the Aluminum Association of America 6000 series. Thus, those skilled in the art of aluminum alloys will appreciate the difficulty of separating aluminum alloys (especially already processed alloys such as cast, forged, extruded, rolled, and generally wrought alloys) into reusable or recyclable processed products. In most cases, these alloys cannot be distinguished by visual inspection or by other conventional scrap sorting techniques such as density and / or eddy current techniques. Therefore, separating alloys of, for example, the 2000, 3000, 5000, 6000, and 7000 series is a difficult task; moreover, the ability to sort between aluminum alloys within the same Aluminum Association of America series has not been achieved in the prior art.

[0012] Accordingly, certain economic benefits can be obtained for the aluminum industry by developing a well-planned and simple recycling program or system. The use of recycled materials would be a cheaper metal resource than primary sources of aluminum. As the amount of aluminum sold to the automotive industry (and other industries) increases, it will become increasingly necessary to use recycled aluminum to supplement the availability of primary aluminum. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 FIG. shows a schematic diagram of a material handling system configured in accordance with an embodiment of the present disclosure.

[0014] Figure 2An exemplary representation of a control set of material pieces used during a training phase of an artificial intelligence ("AI") system is shown.

[0015] Figure 3 The figure shows a flow chart configured according to an embodiment of the present disclosure.

[0016] Figure 4 The figure shows a flow chart configured according to an embodiment of the present disclosure.

[0017] Figure 5 FIG. 1 is a block diagram of a data processing system configured according to an embodiment of the present disclosure.

[0018] Figure 6 An exemplary x-ray fluorescence ("XRF") system is illustrated.

[0019] Figure 7 The figure shows an example of misalignment of the x-ray beam spot and the piece of material.

[0020] Figure 8 The figure shows an example of a separator.

[0021] Figure 9 The figure shows an example of misalignment of an x-ray beam spot and a piece of thin ribbon material.

[0022] Figure 10 A depiction of an exemplary piece of thin ribbon material is shown.

[0023] Figure 11A , Figure 11B , Figure 11C , Figure 11D , Figure 11E and Figure 11F Illustrated are exemplary XRF spectra demonstrating how improper alignment or intersection of an x-ray beam spot and a piece of material may produce erroneous XRF readings or measurements.

[0024] Figure 12 The figure shows a flow chart configured according to an embodiment of the present disclosure.

[0025] Figure 13 The figure shows a non-limiting example of a measured XRF spectrum of a piece of material.

[0026] Figure 14 The figure shows an example of an x-ray beam spot partially irradiating a material piece.

[0027] Figure 15 An XRF spectrum of an exemplary piece of material that has been corrected / modified according to an embodiment of the present disclosure is shown.

[0028] Figure 16 An illustration of a flow chart of a process configured to correct / modify an XRF spectrum of a piece of material, according to certain embodiments of the present disclosure.

[0029] Figure 17 The figure shows a non - limiting example in which the position of a material piece (e.g., on a moving conveyor belt) is determined by a laser line from a profiler.

[0030] Figure 18 The figure shows a flowchart configured according to certain embodiments of the present disclosure.

[0031] Figure 19 The figure shows a flowchart of a process for recycling end - of - life (“EOL”) objects, including but not limited to vehicles, aircraft, or electrical appliances.

[0032] Figure 20 The figure shows a simplified schematic diagram of a laser - camera - based profiler configured according to an embodiment of the present disclosure.

[0033] Figure 21 The figure shows Figure 20 a demonstration of the use of a laser - camera - based profiler.

[0034] Figure 22A The figure shows an alternative embodiment in which multiple lasers are used in combination with a camera.

[0035] Figure 22B The figure shows an alternative embodiment in which multiple lasers of different colors are used in combination with a camera.

[0036] Figure 23 The figure shows an alternative embodiment in which lasers are used on each side of the camera.

[0037] Figure 24 The figure shows a flowchart configured according to certain embodiments of the present disclosure. Detailed Description

[0038] Various detailed embodiments of the present disclosure are disclosed herein. However, it should be understood that the disclosed embodiments are merely exemplary embodiments of the present disclosure, which may be embodied in various forms and alternative forms. The drawings are not necessarily to scale; some features may be enlarged or minimized to show details of particular components. Thus, the specific structural and functional details disclosed herein should not be construed as limiting, but merely as a representative basis for teaching one of ordinary skill in the art to employ the various embodiments of the present disclosure.

[0039] As used herein, "material" may include any article or object, including but not limited to: metals (black and / or colored), metal alloys (e.g., aluminum alloys), Heavies, Zorba, Twitch, metal pieces embedded in another different material, plastics / polymers (including but not limited to any of those disclosed herein, known in the industry, or newly created in the future), rubber, foam, glass (including but not limited to borosilicate or soda-lime glass, and various colored glasses), ceramics, paper, cardboard, polytetrafluoroethylene (Teflon), polyethylene, bundled wires, insulated wires, rare earth elements, leaves, wood, plants, plant parts, textiles, biological waste, packaging, electronic waste, batteries and accumulators, scrap from end-of-life vehicles, mining, construction and demolition waste, crop waste, forest residues, specifically grown grass, lignocellulosic energy crops, microalgae, food waste, hazardous chemicals and biomedical waste, construction waste, farm waste, biological articles, non-biological articles, objects having a specific carbon content, any other object that may be found within municipal solid waste, and any other object, article or material disclosed herein, including any additional types or categories within any of the foregoing that may be distinguishable from one another by one or more sensor systems (including but not limited to any of the sensor technologies disclosed herein).

[0040] In a more general sense, "material" may include any article or object composed of chemical elements, compounds or mixtures of chemical elements, or compounds or mixtures of compounds or mixtures of chemical elements, where the complexity of the compound or mixture can vary from simple to complex (all of which may also be referred to herein as materials having a specific composition "chemical composition" (also referred to herein as a specific "material composition")). "Chemical element" means a chemical element in the periodic table of chemical elements, including chemical elements that may be discovered after the filing date of this application. Within this disclosure, the terms "scrap", "scrap piece", "material", "material piece" and "material scrap piece" may be used interchangeably. As used herein, a material piece or scrap piece referred to as having a metal alloy composition is a metal alloy having a specific chemical composition that distinguishes the metal alloy from other metal alloys. As used herein, "contaminant" is any material or component of a material piece to be excluded from a sorted group of materials.

[0041] As used herein, the term "predetermined" refers to something such as that which has been pre-established or decided by a user of an embodiment of this disclosure.

[0042] As used herein, a thing referred to as "known" means a feature that has been previously determined and is thus already known. As used herein, "spectral imaging" is imaging using one or more bands across the electromagnetic spectrum. Although a typical camera captures an image composed of light across three bands in the visible spectrum (e.g., red, green, and blue (RGB)), spectral imaging can encompass a wide variety of techniques that include and go beyond the typical visible spectrum. For example, spectral imaging can use infrared, visible, ultraviolet, and / or x-ray spectra, or certain combinations of the above spectra. Spectral data or spectral image data is the digital data representation of a spectral image. Spectral imaging can include simultaneously acquiring spectral data in visible and non-visible light bands, illumination from outside the visible range, or using optical filters for capturing a specific spectral range. It is also possible to capture hundreds of bands for each pixel in a spectral image.

[0043] As used herein, the term "image data packet" refers to a grouping of digital data related to a captured spectral image of an individual piece of material.

[0044] As used herein, the term "sorting" and any of its derivatives refer to the physical separation of certain pieces of material (e.g., pieces of material of a specific sort) from other pieces of material.

[0045] As used herein, the terms "identifying" and "sorting", the terms "identification" and "sorting", and any of the foregoing derivatives may be used interchangeably. As used herein, "sorting a piece of material" is to assign or determine (i.e., identify) the type or category of material to which the piece of material belongs. For example, according to certain embodiments of the present invention, (as further described herein) a sensor system can be configured to capture (collect) and analyze any type of information for sorting materials and distinguishing such sorted materials from other materials, which sorting can be utilized within a sorting system to selectively sort pieces of material according to one or more sets of physical and / or chemical characteristics (e.g., which can be user-defined), the one or more sets of physical and / or chemical characteristics including but not limited to: color; texture; hue; shape; brightness; weight; density; chemical composition; size; uniformity; manufacturing type; chemical characteristics; a predetermined fraction; radioactive characteristics; transmissivity to light, sound, or other signals; and response to stimuli such as various fields, which fields include electromagnetic radiation ("EM") emitted and / or reflected by the piece of material.

[0046] The type or category (i.e., classification) of a material piece can be user-defined (e.g., pre-determined) and is not limited to any known material classification(s). The granularity of the type or category can vary from very coarse to very fine. For example, the type or category can include: plastics, ceramics, glass, metals, and other materials, where the granularity of such type or category is relatively coarse; different metals and metal alloys, such as, for example, zinc, copper, brass, chrome-plated, and aluminum, where the granularity of such type or category is finer; or between specific types of metal alloys, where the granularity of such type or category is relatively fine. Thus, the type or category can be configured to distinguish between materials of significantly different chemical compositions, such as, for example, plastics and metal alloys, or to distinguish between materials of nearly the same chemical composition, such as, for example, different types of metal alloys. It should be appreciated that the systems and methods discussed herein can be applied to accurately identify / classify the composition of a material piece before the material piece of completely unknown chemical composition is classified.

[0047] Figure 19 The figure shows a flowchart of a process or series of processes 1900 for recycling end-of-life (“EOL”) objects, including but not limited to vehicles, aircraft, or electrical appliances. The various steps and / or stages of process 1900 can be performed independently of each other by different entities. In process block 1901, the object is shredded, for example, by a commercial shredder, which produces EOL scrap. Typically, such objects are EOL vehicles, aircraft, and / or electrical appliances. A typical subsequent step 1902 is to remove any ferrous materials from the scrap, for example, by a magnet. For shredded objects containing one or more metals or metal alloys, such as vehicles, aircraft, and / or electrical appliances, the remaining non-ferrous scrap is typically referred to as Zorba 1903. Another commonly used process 1904 is to remove various specific materials, such as Heavies and fluff (e.g., foam, fabric, wood, etc.), from Zorba 1903 using separation / sorting techniques. The remaining scrap is then typically referred to as Twitch 1905, which can include various aluminum alloys. Then, it is generally desirable to sort Twitch 1905 according to one or more various processes 1906, which can produce sorted alloys 1907. Embodiments of the present disclosure can be implemented within one or more of process 1902, process 1904, process 1906.

[0048] According to certain embodiments of the present disclosure, the systems and methods described herein receive a heterogeneous mixture of multiple pieces of material (e.g., EOL scrap, Zorba, Heavies, or Twitch), where at least one piece of material within the heterogeneous mixture is composed of a chemical composition different from one or more other pieces of material, and / or at least one piece of material within the heterogeneous mixture is physically distinguishable from the other pieces of material, and / or at least one piece of material within the heterogeneous mixture has a category or type of material different from the category or type of material of the other pieces of material within the mixture, and the systems and methods are configured to identify / classify / distinguish / sort the one piece of material into a group separate from such other pieces of material. Embodiments of the present disclosure can be used to sort any type or category of material defined herein. In contrast, a homogeneous set or group of materials all fall within the same identifiable material category or type.

[0049] Although all embodiments of the present disclosure can be used to classify / sort any type of material as defined herein, the embodiments of the present disclosure described below are used to classify / sort metal alloy scrap (also referred to as "metal alloy scrap pieces") including aluminum alloy scrap pieces.

[0050] In x-ray fluorescence ("XRF") spectroscopy, the use of characteristic x-rays emitted (fluoresced) under x-ray beam excitation provides a method for identifying the elements present in different materials and their relative amounts, which can then be used to classify each material. The energy of the emitted x-rays depends on the atomic number of the fluorescent element. An energy-resolving detector is then used to detect the different energy levels at which the x-rays fluoresce and generate an x-ray fluorescence signal from the detected x-rays. The x-ray fluorescence signal can then be used to construct an energy spectrum of the detected x-rays (also referred to as an "XRF spectrum"), and the information can be used to identify one or more elements in the material that produce the fluorescing x-rays. Fluorescent x-rays are emitted isotopically from the irradiated element, and the detected radiation depends on the solid angle facing the detector and any absorption of the radiation before it reaches the detector. The lower the energy of the x-ray, the shorter the distance it will travel before being absorbed by air. Thus, when detecting x-rays, the amount of detected x-rays varies depending on the amount of emitted x-rays, the energy level of the emitted x-rays, the emitted x-rays absorbed in the transmission medium (e.g., air and / or non-vacuum environment or vacuum environment), the angle between the detected x-rays and the detector, and the distance between the detector and the irradiated material.

[0051] X-rays from the emitted x-ray beam cause each piece of material to emit x-ray fluorescence at various energy levels, depending on the elements contained in the piece of material. The fluorescent x-rays are detected and the pieces of material can then be classified based on the fluorescent x-rays. The pieces of material can then be sorted according to this classification (as a function of this classification).

[0052] In embodiments of the present disclosure, the x-ray fluorescence detected from a piece of material is used to identify some or all of the elements present in the piece of material, including the amount or relative amount of such elements. Embodiments of the present disclosure then utilize the identification of such elements to identify the type of material (e.g., a specific aluminum alloy) associated with the detected fluorescent x-rays. Additionally, embodiments of the present disclosure utilize the identification of the elements within a piece of material in order to classify the piece of material according to a predetermined criterion. For example, according to embodiments of the present disclosure, the x-ray fluorescence detected from an aluminum alloy material (e.g., an aluminum alloy scrap piece) can be used to assign an aluminum alloy classification to the piece of material (including according to the aluminum alloy classifications designated by the Aluminum Association of America).

[0053] Embodiments of the present disclosure will be described herein as sorting pieces of material into such separate groups by physically placing (e.g., discharging) the pieces of material into separate containers or bins according to user-defined groupings (e.g., piece of material classifications). As an example, within embodiments of the present disclosure, pieces of material are sorted into separate containers in order to separate pieces of material composed of one or more specific material compositions from other pieces of material composed of different material compositions. Additionally, embodiments of the present disclosure can be configured to sort aluminum alloy scrap pieces into separate containers such that substantially all aluminum alloy scrap pieces having a material composition that falls within one of the aluminum alloy series published by the Aluminum Association of America are sorted into a single container (e.g., the container can correspond to one or more specific aluminum alloy series (e.g., 1xxx, 2xxx, 3xxx, 4xxx, 5xxx, 6xxx, 7xxx, 8xxx)).

[0054] Furthermore, as will be described herein, embodiments of the present disclosure can be configured to sort aluminum alloy scrap pieces into separate containers according to the classification of the alloy composition of the aluminum alloy scrap pieces, even if such alloy compositions fall within the same Aluminum Association of America series. Thus, a sorting system according to embodiments of the present disclosure can classify and sort aluminum alloy scrap pieces having compositions that would all classify the aluminum alloy scrap pieces as a single aluminum alloy series (e.g., the 5xxx series or the 6xxx series) according to the aluminum alloy composition of the aluminum alloy scrap pieces into separate containers. For example, embodiments of the present disclosure can separately classify and sort aluminum alloy scrap pieces classified as aluminum alloy 5086 from aluminum alloy scrap pieces classified as aluminum alloy 5022 into separate containers, or separately classify and sort 6xx3 aluminum alloy from 6xx2 aluminum alloy into separate containers.

[0055] Figure 1 The figure shows an example of a material handling system 100 configured according to various embodiments of the present disclosure. The conveyor system 103 may be implemented to convey individual material pieces 101 through the material handling system 100 such that each of the individual material pieces 101 can be tracked, sorted, differentiated, and / or sorted into a predetermined desired group (e.g., classified). Such a conveyor system 103 may be implemented using one or more conveyor belts on which the material pieces 101 typically travel at a predetermined constant speed. However, certain embodiments of the present disclosure may be implemented using other types of conveyor systems, including those in which the material pieces freely fall past one or more of the various components of the material handling system 100 (or any other type of vertical sorter, or any other conveying system disclosed herein). Hereinafter, 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 actions or functions of conveying, capturing, stimulating, detecting, sorting, differentiating, and sorting may 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 stimulation sources, one or more emission detectors, one or more sorting modules, sorting devices, and / or other system components may be configured to perform these and other operations automatically.

[0056] In addition, although Figure 1 the simplified illustration in depicts a single stream of material pieces 101 on the conveyor belt 103, embodiments of the present disclosure in which multiple such streams of material pieces pass through the various components of the material handling system 100 in parallel may be implemented (e.g., see Figure 8 ). According to certain embodiments of the present disclosure, a suitable feeding mechanism (e.g., another conveyor system, a bowl feeder, or a hopper 102) may be utilized to feed the material pieces 101 onto the conveyor system 103, whereby the conveyor system 103 conveys the material pieces 101 through the various components within the material handling system 100. According to certain embodiments of the present disclosure, a tumbler and / or a vibrator may be used to separate individual material pieces from a collection of material pieces (e.g., a physical stack). According to certain embodiments of the present disclosure, the material pieces may be positioned into one or more separate (i.e., single-file) streams, which may be performed by an active or passive separator 106. Examples of passive separators are further described with respect to Figure 8 and in U.S. Patent No. 10,207,296.

[0057] Accordingly, certain embodiments of the present disclosure are capable of simultaneously tracking, sorting, differentiating, and / or separating a stream of such moving workpiece. Alternatively, a conveyor system (e.g., conveyor belt 103) may simply convey a collection of workpieces that have been placed on conveyor belt 103 in a random manner. Accordingly, in certain embodiments of the present disclosure, it is not required to separate the workpieces 101 to track, sort, differentiate, and / or separate the workpieces.

[0058] Within certain embodiments of the present disclosure, conveyor system 103 is operated by conveyor system motor 104 to travel at a predetermined speed. The predetermined speed may be programmable and / or adjustable by an operator in any known manner. Within certain embodiments of the present disclosure, the control of conveyor system motor 104 and / or position detector 105 may be performed by an automated control system 108. Such automated control system 108 may be operated under the control of computer system 107, and / or the functions for performing automated control may be implemented in software within computer system 107. If conveyor system 103 is a conveyor belt, it may be a conventional endless belt conveyor employing a conventional drive motor 104 adapted to move conveyor belt 103 at a predetermined speed.

[0059] Position detector 105 (e.g., a conventional encoder) may be operatively coupled to conveyor belt 103 and automated control system 108 to provide information corresponding to the movement (e.g., speed) of conveyor belt 103. Accordingly, as will be further described herein, by utilizing the control of conveyor belt drive motor 104 and / or automated control system 108 (and alternatively, including position detector 105), when each workpiece 101 among the workpieces 101 traveling on conveyor belt 103 is identified, they may be tracked by position and time (relative to the various components of material handling system 100) such that when each workpiece 101 passes through the vicinity of the various components of material handling system 100, the various components of material handling system 100 may be activated / deactivated. As a result, automated control system 108 is capable of tracking the position of each workpiece 101 among the workpieces 101 while each workpiece 101 travels along conveyor belt 103.

[0060] Referring again to Figure 1, certain embodiments of the present disclosure may utilize a vision or optical recognition system 110 as a way to track each of the material pieces 101 as the material pieces 101 travel on the conveyor system 103. The vision or optical recognition system 110 may utilize one or more stationary or live cameras 109 to record the position (i.e., location and timing) of each of the material pieces 101 on the moving conveyor system 103. The vision system 110 may further or alternatively be configured to perform certain types of identification (e.g., classification) on all or part of the material pieces 101, which will be further described herein. For example, such a vision system 110 may be used to capture or collect information about each of the material pieces 101. For example, the vision system 110 may be configured (e.g., utilizing an artificial intelligence (“AI”) system as further described herein) to capture or collect any type of information from the material pieces that can be utilized within the material handling system 100 to classify and / or selectively sort the material pieces 101 according to one or more sets of characteristics (e.g., physical and / or chemical and / or radioactive, etc.), as described herein. According to certain embodiments of the present disclosure, the vision system 110 may be configured to capture visual images (including one-dimensional, two-dimensional, three-dimensional, or holographic imaging) of each of the material pieces 101, for example, by using optical sensors utilized in typical digital cameras and video equipment. Then, such visual images captured by the optical sensors are stored in a memory device as image data (e.g., formatted as image data packets). According to certain embodiments of the present disclosure, such image data may represent images captured within the optical wavelengths of light (i.e., the wavelengths of light observable by a typical human eye). However, alternative embodiments of the present disclosure may utilize sensor systems configured to capture images of materials composed of wavelengths of light outside the visual wavelengths of the human eye.

[0061] According to certain embodiments of the present disclosure, the vision system 110 may implement a machine vision system for analyzing and / or determining the shape or relative shape of each of the material pieces 101, such as may be implemented within LabVIEW.

[0062] According to certain embodiments of the present disclosure, the material handling system 100 can be implemented using one or more sensor systems 120, which can be utilized individually or in combination with the vision system 110 to classify / identify / distinguish the material pieces 101. The sensor system 120 can be configured with any type of sensor technology, including sensors that utilize irradiated or reflected electromagnetic radiation (e.g., using infrared (“IR”), Fourier transform IR (“FTIR”), forward-looking infrared (“FLIR”), very near-infrared (“VNIR”), near-infrared (“NIR”), short-wave infrared (“SWIR”), long-wave infrared (“LWIR”), mid-wave infrared (“MWIR” or “MIR”), X-ray transmission (“XRT”), gamma rays, ultraviolet (“UV”), X-ray fluorescence (“XRF”), laser-induced breakdown spectroscopy (“LIBS”), Raman spectroscopy, anti-Stokes Raman spectroscopy, gamma spectroscopy, hyperspectral spectroscopy (e.g., any range beyond the visible wavelength), acoustic spectroscopy, NMR spectroscopy, microwave spectroscopy, terahertz spectroscopy, including one-dimensional, two-dimensional, or three-dimensional imaging with any of the foregoing), or by any other type of sensor technology including but not limited to chemical or radioactive sensors.

[0063] The (multiple) sensor system 120 can include an energy emission source 121, which can be powered by a power supply 122 to, for example, excite a response from each of the material pieces 101 in the material pieces 101. Within certain embodiments of the present disclosure, when each material piece 101 passes through the vicinity of the emission source 121, the sensor system 120 can emit an appropriate sensing signal towards the material piece 101. One or more detectors 124 can be positioned and configured to sense / detect one or more characteristics from the material piece 101 in a form suitable for the type of sensor technology utilized. The one or more detectors 124 and associated detector electronics 125 capture these received sensed characteristics to perform signal processing thereon and generate digitized information representative of the sensed characteristics (e.g., spectral data), which is then analyzed according to certain embodiments of the present disclosure and can be used to classify each of the material pieces 101. According to certain embodiments of the present disclosure, such a sensor system can be an XRF system as further described herein. The implementation of an XRF system (e.g., for use as the sensor system 120 herein) is further described in U.S. Patent No. 10,207,296.

[0064] It should be noted that although Figure 1The combination of the vision system 110 and one or more sensor systems 120 is illustrated, but embodiments of the present disclosure may be implemented using any combination of sensor systems that utilize any of the sensor technologies disclosed herein or any other sensor technology currently available or developed in the future. Within certain embodiments of the present disclosure, the combination of both the vision system 110 and one or more sensor systems 120 may be used to classify the material pieces 101. Additionally, embodiments of the present disclosure may include any combination of one or more sensor systems and / or vision systems, where the output of such sensor / vision systems is processed within an AI system (as further disclosed herein) to classify / identify / distinguish materials from a heterogeneous mixture of materials, which can then be sorted from each other.

[0065] According to certain embodiments of the present disclosure, the vision system 110 may be configured to capture additional information about each material piece, including information that a single sensor system alone cannot collect. For example, the vision system 110 may be configured to capture information about the color, size, shape, and / or uniformity of the material piece, which may assist in the identification / classification of the material piece. Additionally, the vision system 110 may be configured to identify material pieces that are not desired (e.g., contain contaminants), and may send a signal to reject the material piece before it reaches the (one or more) sensor systems.

[0066] According to certain embodiments of the present disclosure, the vision system 110 and / or the (one or more) sensor systems may be configured to identify which of the material pieces 101 in the material pieces 101 are not of the type to be sorted by the material handling system 100 (e.g., contain contaminants), and send a signal to reject such material pieces. In such a configuration, the identified material pieces 101 may be transferred / discharged using one of the mechanisms for physically transferring the sorted material pieces to individual containers as described below.

[0067] Within certain embodiments of the present disclosure, the material piece tracking device 111 (or as described herein with respect to Figures 16 to 18The further described profiler) and the accompanying control system 112 can be utilized and configured to determine the size and / or shape of each material piece 101 in the material piece 101 and the position (i.e., location and time) of each material piece 101 in the moving conveyor system 103 as the material piece 101 passes through the area near the material piece tracking device 111. Exemplary operations of such material piece tracking devices 111 and control systems 112 are further described in U.S. Patent No. 10,207,296. Alternatively, as previously disclosed, the vision system 110 can be used to track the position (i.e., location and time) of each material piece 101 in the material piece 101 as the material piece 101 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 piece.

[0068] According to certain embodiments of the present disclosure, the material tracking device 111 can be implemented upstream of the vision system 110 and / or the sensor system 120 (e.g., upstream of the conveyor system) such that when the material piece 101 is detected by the material tracking system 111, the material tracking device 111 triggers the material handling system 100 when the vision system 110 and / or the sensor system 120 are to capture the characteristics of the material piece. Additionally, the order in which the vision system 110 and the sensor system 120 are implemented within the material handling system 100 can be interchanged.

[0069] The classification of the material pieces that can be performed within the computer system 107 (e.g., using one or more various algorithms that combine information captured by the (multiple) sensor systems and / or the vision system) can be used by the automated control system 108 to activate one of the N (N>1) sorting devices 126…129 of the sorting device to sort (e.g., divert / discharge) the material piece 101 into one or more of the N (N>1) sorting containers 136…139 according to the determined classification (or sort onto another conveyor system that transports the material piece to the container). In Figure 1 only four sorting devices 126……129 and four sorting containers 136……139 associated with the sorting devices are illustrated as non-limiting examples.

[0070] The sorting device may include any known mechanism for redirecting the selected material pieces 101 toward the desired location, including but not limited to transferring the material pieces 101 from the conveyor system to a plurality of sorting containers (or to another conveyor system that transports the material pieces to the containers). For example, the sorting device may utilize air ejectors, wherein each of the air ejectors is assigned to one or more of the categories. When one or more of the air ejectors (e.g., 127) receive a signal from the automated control system 108, the air ejector (s) emit an air stream that causes the material pieces 101 to be transferred / ejected from the conveyor system 103 to the sorting container (e.g., 137) corresponding to the air ejector (or transferred / ejected to another conveyor system).

[0071] although Figure 1 The examples illustrated in use air ejectors to transfer / eject material pieces, but other mechanisms may be used to transfer / eject material pieces, such as robotically removing material pieces from a conveyor, pushing material pieces from a conveyor (e.g., with a paint brush type plunger), creating an opening (e.g., a trap door) in the conveyor system 103 through which material pieces can fall, or using air ejectors to separate material pieces into separate containers as they fall from the edge of a conveyor. As the term is used herein, a pusher device may refer to any form of device that can be activated to dynamically displace objects on or from a conveyor system / device, using pneumatic, mechanical, or other means to do so, such as any suitable type of mechanical push mechanism (e.g., an ACME screw drive), a pneumatic push mechanism, or an air ejector push mechanism.

[0072] In addition to the N sorting containers 136 ... 139 into which the material pieces 101 are transferred / discharged, the material handling system 100 may also include a container 140 for receiving material pieces 101 that are not transferred / discharged from the conveyor system 103 to any of the aforementioned sorting containers 136 ... 139. For example, when the classification of the material piece 101 is not determined (or simply because the sorting device fails to adequately transfer / discharge the piece), the material piece 101 may not be transferred / discharged from the conveyor system 103 to one of the N sorting containers 136 ... 139. Thus, the container 140 can be used as a default container into which unclassified or unsorted material pieces are placed. Alternatively, the container 140 can be used to receive one or more classified material pieces that are intentionally not assigned to any of the N sorting containers 136 ... 139. These such material pieces can then be further sorted according to other characteristics and / or by another sorting system.

[0073] Depending on the multiple classifications of the desired material pieces, multiple classifications can be mapped to a single sorting device and associated sorting containers. In other words, there need not be a one-to-one correlation between the classifications and the sorting containers. For example, a user may desire to sort certain classifications of materials into the same sorting container. To achieve such sorting, when the material pieces 101 are classified as falling into a predetermined classification group, the same sorting device can be activated to sort these material pieces 101 into the same sorting container. Such combined sorting can be applied to produce any desired combination of sorted material pieces. The mapping of the classifications can be programmed by the user (e.g., using any of the sorting algorithms described herein that are operated by the computer system 107) to produce such a desired combination. Accordingly, the classification of the material pieces can be user-defined and is not limited to any particular known classification of the material pieces.

[0074] By implementing an XRF system for the sensor system 120 in the material handling system 100, the signal representing the detected XRF spectrum can be converted into a discrete energy histogram on a per-channel (i.e., element) basis, as further described herein. Such a conversion process can be implemented within the control system 123 or the computer system 107. Within certain embodiments of the present disclosure, such a control system 123 or computer system 107 can include a commercially available spectral acquisition module, such as a commercially available Amptech MCA 5000 acquisition card and software programmed to operate the card. Such a spectral acquisition module, or other software implemented within the material handling system 100, can be configured to implement multiple channels for dispersing X-rays into a discrete energy (XRF) spectrum (i.e., histogram) having such multiple energy levels, whereby each energy level corresponds to an element for which the material handling system 100 has been configured to detect. The material handling system 100 can be configured such that there are sufficient channels corresponding to certain elements within the periodic table of the elements, which is important for differentiating between different materials. The energy counts for each energy level can be stored in separate collection storage registers. The computer system 107 then reads each collection register to determine the number of counts for each energy level during the collection interval and constructs an energy histogram. A sorting algorithm configured according to certain embodiments of the present disclosure can then utilize the histogram of the collected energy levels (also referred to herein as the XRF spectrum) to classify at least some of the material pieces 101 within the material pieces 101 and / or assist the vision system 110 in classifying the material pieces 101.

[0075] As disclosed previously, according to an alternative embodiment of the present disclosure, the vision system 110 may be configured with an AI system to capture or collect any type of information from the material piece, and the information may be utilized within the material handling system 100 to classify and / or selectively sort the material piece 101 according to one or more sets of characteristics. The AI system may implement any well-known AI system (e.g., artificial narrow intelligence (“ANI”), artificial general intelligence (“AGI”), and artificial super intelligence (“ASI”)); a machine learning system that includes a machine learning system implementing a neural network (e.g., artificial neural network, deep neural network, convolutional neural network, recurrent neural network, autoencoder, reinforcement learning, etc.); a machine learning system that implements supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, self-learning, feature learning, sparse dictionary learning, anomaly detection, robotic learning, association rule learning, fuzzy logic, deep learning algorithms, deep structured learning hierarchical learning algorithms, support vector machines (“SVM”) (e.g., linear SVM, non-linear SVM, SVM regression, etc.), decision tree learning (e.g., classification and regression tree (“CART”), ensemble methods (e.g., ensemble learning, random forest, bagging and pasting, patches and subspaces, boosting methods, stacking generalization, etc.), dimensionality reduction (e.g., projection, manifold learning, principal component analysis, etc.), and / or deep machine learning algorithms, such as those described and publicly available on the deeplearning.net website (including all software, publications, and hyperlinks to available software cited within the website), which website is hereby incorporated by reference herein.Non-limiting examples of publicly available machine learning software and libraries that can be utilized within the embodiments of the present disclosure include: Python, OpenCV, Inception, Theano, Torch, PyTorch, Pylearn2, Numpy, Blocks, TensorFlow, MXNet, Caffe, Lasagne, Keras, Chainer, Matlab Deep Learning, CNTK, MatConvNet (a MATLAB toolbox implementing convolutional neural networks for computer vision applications), DeepLearnToolbox (a MATLAB toolbox for deep learning (from Rasmus Berg Palm)), BigDL, Cuda-Convnet (a fast C++ / CUDA implementation of convolutional (or more generally, feedforward) neural networks), deep belief networks, RNNLM, RNNLIB - RNNLIB, matrbm, deeplearning4j, Eblearn.1sh, deepmat, MShadow, Matplotlib, SciPy, CXXNET, Nengo - Nengo, Eblearn, cudamat, Gnumpy, tri-factor RBM and mcRBM, mPoT (Python code for training natural image models using CUDAMat and Gnumpy), ConvNet, Elektronn, OpenNN, NeuralDesigner (Neural Designer), Theano generalized Hebbian learning, Apache Singa, Lightnet, and SimpleDNN.

[0076] According to certain embodiments of the present disclosure, certain types of machine learning can be performed in stages. For example, first, training occurs, which can be performed offline because the material handling system 100 is not used to perform the actual sorting / classification of the material pieces. The material handling system 100 can be used to train the machine learning system because a homogeneous set of material pieces (also referred to herein as control samples) (i.e., material pieces having the same type or class of material, or material pieces falling within the same predetermined fraction) (e.g., via the conveyor system 103) are passed through the material handling system 100; and all such material pieces may not be sorted but may be collected in a common container (e.g., container 140). Alternatively, the training can be performed at another location remote from the material handling system 100, including using some other mechanism for collecting sensed information (characteristics) of the control set of material pieces. During this training phase, algorithms within the machine learning system (e.g., using image processing techniques well known in the art) extract features from the captured information. Non-limiting 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. It is during this training phase that the algorithms within the machine learning system learn the relationships between the materials and their features / characteristics (e.g., captured by the vision system and / or the sensor system(s)), thus creating a knowledge base for the later classification of the heterogeneous mixture of material pieces received by the material handling system 100, which heterogeneous mixture of material pieces can then be sorted according to the desired classification. Such a knowledge base can include one or more libraries, where each library includes parameters (e.g., neural network parameters) for the machine learning system to utilize when classifying the material pieces. For example, a particular library can include parameters configured by the training phase for identifying and classifying a particular type or class of material, or one or more materials falling within a predetermined fraction. According to certain embodiments of the present disclosure, such libraries can be input into the machine learning system, and subsequently the user of the material handling system 100 can be able to adjust certain of the parameters in order to adjust the operation of the material handling system 100 (e.g., adjusting the threshold effectiveness of the degree to which the machine learning system identifies a particular material piece from the heterogeneous mixture of materials).

[0077] Additionally, the inclusion of certain materials in a material piece can result in the material having identifiable physical characteristics (e.g., visually distinguishable properties). Thus, when multiple material pieces containing such specific constituents are passed through the aforementioned training phase, the machine learning system can learn how to distinguish such material pieces from other material pieces. Accordingly, a machine learning system (or any AI system) configured in accordance with certain embodiments of the present disclosure can be configured to sort between material pieces based on their respective material / chemical compositions. It can be readily appreciated that embodiments of the present disclosure can be configured to use image data (e.g., visual images) of the material pieces as surrogates for representing one or more of the various physical and / or chemical properties of the material pieces (e.g., ductility, malleability, brittleness, hardness, luster, tensile strength, reactivity with various materials, etc.).

[0078] Reference Figure 2 , during the training phase, multiple material pieces 201 of one or more specific types, classifications, or fractions of (a) material as control samples can be delivered (e.g., by a conveyor system 203) past a vision system and / or one or more sensor systems such that algorithms within the machine learning system detect, extract, and learn what features characterize such types or classes of materials. For example, each of the material pieces 201 in the control samples of material pieces 201 can first be passed through such a training phase such that the algorithms within the machine learning system “learn” (are trained) how to detect, identify, and classify such material pieces 201. In the case of training a vision system (e.g., vision system 110), it is trained to visually discriminate (distinguish) between material pieces. This creates a library of parameters specific to such homogeneous classes of material pieces 201. The same process can be performed for images of any classified material pieces, thereby creating a library of parameters specific to such classified material pieces. For each type of material to be classified by the vision system, any number of exemplary material pieces of that classified material can be passed by the vision system. Given the captured sensed information as input data, the algorithms within the machine learning system can use N classifiers, each of the N classifiers being tested against one of N different material types. It should be noted that the machine learning system can be “taught” (trained) to detect any type, class, or fraction of material, including any of the types, classes, or fractions of materials disclosed herein.

[0079] After an algorithm has been established and a machine learning system has been sufficiently learned (trained) for differences in material classification (e.g., visually distinguishable differences) within, for example, a user-defined statistical confidence level, a library for different material classifications is then implemented into a material classification / sorting system (e.g., material handling system 100) for identifying, differentiating, and / or classifying material pieces from a heterogeneous mixture of material pieces and, subsequently, possibly sorting such classified material pieces in the event sorting is to be performed.

[0080] It should be understood that the present disclosure is not exclusively limited to AI technology. Other common techniques for material classification / identification can also be used. For example, a sensor system can utilize optical spectrometry techniques using multi-spectral or hyper-spectral cameras to provide signals that can indicate the presence or absence of a certain type, class, or fraction of material by examining the spectral emission of the material (i.e., spectral imaging). Spectral images of the material pieces can also be used in a template matching algorithm where a database of spectral images is compared with the acquired spectral image to find the presence or absence of certain types of materials from the database. The histogram of the captured spectral image can also be compared with a histogram database. Similarly, a bag-of-words model can be used in conjunction with feature extraction techniques such as scale-invariant feature transform (“SIFT”) to compare the extracted features between the captured spectral image and the spectral images in the database.

[0081] One point to mention here is that, according to certain embodiments of the present disclosure, the detected / captured features / characteristics (e.g., spectral images) of the material pieces are not necessarily simple, particularly identifiable or distinguishable physical properties; they can be abstract formulas that can only be expressed mathematically or not at all mathematically; however, an AI system can be configured to parse the spectral data to look for patterns that allow classification of control samples during the training phase. Additionally, the AI system can obtain sub-portions of the captured information (e.g., spectral images) of the material pieces and attempt to find correlations between predefined classifications.

[0082] According to certain embodiments of the present disclosure, instead of a training phase that utilizes control (homogeneous) samples of the material pieces conveyed by the vision system and / or the (one or more) sensor systems, the training of the AI system can be performed using tagging / annotation techniques (or any other supervised learning technique), whereby when data / information of the material pieces is captured by the vision / sensor system, the user inputs tags or annotations that identify each material piece, and such tags or annotations are subsequently used to create a library for use by the AI system when classifying the material pieces within a heterogeneous mixture of material pieces. In other words, a knowledge base of previously generated characteristics captured from one or more samples of a certain category of material can be completed by any of the techniques disclosed herein, whereby such a knowledge base is then used for automatically classifying the material.

[0083] Accordingly, as disclosed herein, certain embodiments of the present disclosure provide for the identification / classification of one or more different materials in order to determine which material pieces should be transferred from a conveyor system or device. According to certain embodiments, machine learning techniques can be utilized to train (i.e., configure) a neural network to identify various one or more different categories or types of materials. For example, an image of the material (e.g., traveling on a conveyor system) or other type of sensed information can be captured, and based on the identification / classification of such material, the systems described herein can decide which material pieces should be allowed to remain on the conveyor system and which material pieces should be transferred / removed from the conveyor system (e.g., transferred / removed to a collection container or transferred to another conveyor system).

[0084] According to certain embodiments of the present disclosure, any sensed characteristic output by any of the sensor systems 120 disclosed herein can be input into the AI system for classifying and / or sorting the material. For example, in an AI system implementing supervised learning, the output of the sensor system 120 that uniquely characterizes a particular type or composition of the material can be used to train the AI system.

[0085] Figure 3 The figure shows a flowchart of an exemplary embodiment depicting a process 3500 for classifying / sorting material pieces using a vision system and / or one or more sensor systems according to certain embodiments of the present disclosure. Process 3500 can be executed to classify a heterogeneous mixture of material pieces into any combination of predetermined types, categories, and / or fractions. Process 3500 can be configured to operate within any of the embodiments of the present disclosure described herein, which include Figure 1 the material handling system 100. Note that not all processing blocks must be implemented depending on the particular classification technique used. The operations of process 3500 can be performed by hardware and / or software, including within a system (e.g., Figure 1a computer system (e.g., a computer system 107, a vision system 110, and / or one or more sensor systems 120) that controls, for example, Figure 5 within a data processing system 3400). In process block 3501, a workpiece can be placed on a conveyor system. In process block 3502, the position of each workpiece on the conveyor system is detected for tracking each workpiece as it travels through the material handling system 100. This can be performed by the vision system 110 (e.g., by differentiating the workpiece from the underlying conveyor system material while communicating with a conveyor system position detector (e.g., position detector 105)). Alternatively, a workpiece tracking device 111 can be used to track the workpiece. Or, a light source (including but not limited to visible light, UV, and IR) can be created and any system having a detector can be used to locate the workpiece. In process block 3503, when the workpiece has traveled near one or more of the vision system and / or one or more sensor systems, sensed information / characteristics of the workpiece are captured / acquired. In process block 3504, a vision system (such as the previously disclosed vision system) implemented, for example, within the computer system 107 can perform preprocessing on the captured information, which can be used to detect (extract) information for each workpiece in the workpiece (e.g., from the background (e.g., the conveyor belt); in other words, the preprocessing can be used to identify the difference between the workpiece and the background). Well-known image processing techniques such as dilation, thresholding, and contouring can be used to identify the workpiece as being different from the background. In process block 3505, segmentation can be performed. For example, the captured information can include information related to one or more workpieces. Additionally, when an image of a particular workpiece is captured, the particular workpiece may be located on a seam of the conveyor belt. Thus, in such instances, it may be desirable to isolate the image of the individual workpiece from the background of the image. In an exemplary technique for process block 3505, the first step is to apply high contrast to the image; in this way, the background pixels are reduced to be mostly black pixels, and at least some of the pixels related to the workpiece are brightened to be mostly white pixels. Then, the white image pixels of the workpiece are dilated to cover the entire size of the workpiece. After this step, the position of the workpiece is a high-contrast image of all white pixels on a black background. Then, a contouring algorithm can be used to detect the boundaries of the workpiece. The boundary information is saved, and then the boundary positions are transferred to the original image. Then, segmentation is performed on the original image over an area larger than the previously defined boundaries. In this way, the workpiece is identified and separated from the background.

[0086] In optional process block 3506, the material pieces can be conveyed along the conveyor system within the vicinity of the material piece tracking device and / or sensor system to track each of the material pieces and / or determine the size and / or shape of the material pieces; this may be useful if an XRF system or some other spectral sensor is also implemented within the sorting system. In process block 3507, post-processing can be performed. Post-processing can involve resizing the captured information / data to prepare it for use in the neural network. This can also include modifying certain properties in some way (e.g., enhancing image contrast, changing the image background, or applying filters) in a manner that will result in an enhancement of the AI system's ability to classify the material pieces. In process block 3509, the data can be resized. In some cases, it may be desirable to resize the data to match the data input requirements of certain AI systems, such as neural networks. For example, a neural network may require an image size that is much smaller than the size of the images captured by a typical digital camera (e.g., 225×255 pixels or 299×299 pixels). Additionally, the smaller the input data size, the less processing time required to perform the classification. Thus, a smaller data size can ultimately increase the throughput of the material handling system 100 and increase its value.

[0087] In process blocks 3510 and 3511, each material piece is identified / classified based on the sensed / detected features. For example, process block 3510 can be configured with a neural network that employs one or more algorithms that compare the extracted features with the features stored in a previously generated (e.g., generated during the training phase) knowledge base and assigns the classification with the highest match to each of the material pieces based on such comparison. The algorithms can process the captured information / data in a hierarchical manner by using automatically trained filters. Then, the filter responses are successfully combined in the next algorithmic level until probabilities are obtained in the final step. In process block 3511, these probabilities can be used for each of the N classifications to decide into which of the N sorting containers the corresponding material piece should be sorted. For example, each of the N classifications can be assigned to a sorting container, and the material piece under consideration is sorted into the container corresponding to the classification that returns the highest probability greater than a predefined threshold. Within an embodiment of the present disclosure, such a predefined threshold can be preset by the user. If none of the probabilities is greater than the predetermined threshold, a particular material piece can be sorted into an exception container (e.g., sorting container 140).

[0088] Next, in process block 3512, the sorting device corresponding to one or more classifications of the material piece is activated (e.g., instructions are sent to the sorting device for sorting). Between the time when the image of the material piece is captured and the time when the sorting device is activated, the material piece has moved from near the vision system and / or the (multiple) sensor systems (e.g., at the conveyor system's conveyance rate) to a downstream position on the conveyor system. In an embodiment of the present disclosure, the activation of the sorting device is timed such that when the material piece passes by the sorting device mapped to the classification of the material piece, the sorting device is activated and the material piece is transferred / discharged from the conveyor system into its associated sorting container. Within an embodiment of the present disclosure, the activation of the sorting device can be timed by a corresponding position detector that detects when the material piece passes in front of the sorting device and sends a signal to enable the activation of the sorting device. In process block 3513, the sorting container corresponding to the activated sorting device receives the transferred / discharged material piece.

[0089] Figure 4 The figure shows a flowchart depicting an exemplary embodiment of process 400 configured according to certain embodiments of the present disclosure. Process 400 can be configured to operate within any of the embodiments of the present disclosure described herein, which include Figure 1 the material handling system 100.

[0090] The operations of process 400 can be performed by hardware and / or software, including within a computer system (e.g., Figure 1 the computer system 107) that controls the system (e.g., Figure 5 the data processing system 3400). In process block 401, a material piece can be placed on the conveyor system. Next, in optional process block 402, the material piece can be conveyed along the conveyor system within an area near the material piece tracking device and / or the optical imaging system (e.g., a profiler or a laser camera-based system as described herein) to track each material piece and / or determine the size and / or shape of the material piece. In process block 403, when the material piece travels near the sensor system, the material piece can be interrogated or excited using EM energy (waves) or some other type of stimulus suitable for a particular type of sensor technology utilized by the sensor system (e.g., an XRF system as described herein). In process block 404, the physical characteristics of the material piece are sensed / detected and captured by the sensor system. In process block 405, for at least some of the material pieces, the type of material is identified / classified (at least partially) based on the captured characteristics (e.g., XRF spectrum).

[0091] Next, if sorting of the material pieces is to be performed, in process block 406, the sorting device corresponding to one or more classifications of the material pieces is activated. Between the time the material piece is sensed and the time the sorting device is activated, the material piece has moved from near the sensor system to a downstream location on the conveyor system at the conveyor rate of the conveyor system. In certain embodiments of the present disclosure, the activation of the sorting device is timed such that when the material piece passes through the sorting device mapped to the classification of the material piece, the sorting device is activated and the material piece is transferred / discharged from the conveyor system into its associated sorting container (or onto another conveyor system). Within certain embodiments of the present disclosure, the activation of the sorting device can be timed by a corresponding position detector that detects when the material piece passes in front of the sorting device and sends a signal to enable activation of the sorting device. In process block 407, the sorting container (or other conveyor system) corresponding to the activated sorting device receives the transferred / discharged material piece.

[0092] According to an alternative embodiment of the present disclosure, process 400 can be configured to operate in conjunction with process 3500. For example, in certain embodiments of the present disclosure, process block 403 and process block 404 can be incorporated into process 3500 (e.g., operating serially or in parallel with process blocks 3503 to 3510) to combine the operation of the vision system 110 implemented with the AI system with a sensor system not implemented with the AI system (e.g., sensor system 120) for classifying and / or sorting the material pieces.

[0093] As described herein, an XRF system implementing XRF spectroscopy can be used as sensor system 120. When XRF spectroscopy is used to classify materials transported on a moving conveyor belt, there is a possibility that the x-ray beam only partially irradiates the material piece, which can result in inaccurate XRF spectra being captured for classifying the material piece. This can lead to inappropriate (incorrect) classification and ultimately sorting of the material piece (e.g., aluminum alloy).

[0094] Figure 6The figure shows a simplified diagram of an example of an XRF system 120 consisting of an x-ray tube 121 and a corresponding XRF detector 124. Such XRF systems can be any conventional XRF systems known in the art. When the material piece 101 is conveyed by the moving conveyor belt 103, the material piece 101 is irradiated by the x-ray beam 601. The irradiated x-ray beam 601 will typically have a conical form, resulting in the x-ray beam spot 602 contacting (intersecting) the upper surface of the material piece 101. Depending on the exact height of the upper surface of the material piece relative to the conveyor belt surface and the shape of the various profiles of such upper surfaces, the x-ray beam spot 602 will have a corresponding diameter. For the operation of the XRF system, it is desirable that the x-ray beam spot 602 irradiates only at least some parts of the material piece 101 and, when the resulting x-ray fluorescence is detected by the detector 124, does not irradiate any other material pieces or any part of the conveyor belt 103, which is necessary for generating an accurate XRF spectrum of the material piece 101 for accurate classification of the material piece 101. The problem is that it may occur relatively frequently within the material handling system 100 that when the material piece 101 is conveyed through the XRF system 120, the x-ray beam spot 602 does not fully fall on any part of the material piece 101 (i.e., does not fully intersect any part of the material piece 101).

[0095] Reference Figure 7 , the figure shows an example of an instance where the material piece 101 on the conveyor belt 103 is not correctly aligned or positioned relative to the XRF system 120 such that the x-ray beam spot 602 irradiates only a part of the material piece 101. In other words, the x-ray beam spot 602 does not fully or entirely intersect the conveyed material piece 101. For example, when the material piece 101 is conveyed through the XRF system, the placement of the material piece 101 onto the conveyor belt 103 may have resulted in the misalignment or only partial alignment of the material piece 101 with the x-ray beam spot 602.

[0096] Reference Figure 8 , the figure shows an exemplary separator 106 demonstrating how the material pieces 101 fed (placed) onto the conveyor system 103 should be aligned with the XRF system such that the x-ray beam 601 correctly irradiates each of the material pieces 101. Figure 8 The example of... schematically shows how one or more static alignment rods or bars (sometimes also referred to as "fingers") 810…817 can be configured to align individual material pieces 101 into one or more separate streams on a conveyor belt (or conveyor belts) such that they travel directly beneath the x-ray emitter 121 such that the x-ray beam spot 602 fully falls on each material piece 101 (intersects each material piece 101). However, as those skilled in the art will appreciate, these can be instances where the specific physical characteristics (e.g., size or shape) of the material pieces inhibit such correct alignment / positioning. Although Figure 8The example is not restrictive, but it shows how the material piece 101 can be separated into separate streams 802…805 (in this non - restrictive example, four separate streams) of the material piece 101 on the conveyor belt 103. In embodiments of the present disclosure, a single conveyor belt can convey such multiple separate streams, or multiple individually - driven conveyor belts can be utilized, whereby each of the conveyor belts conveys one or more separate streams (e.g., 802…805) of the material piece 101.

[0097] Referring again to Figure 7 , if such a material piece 101 is not positioned or fed (placed) onto the conveyor belt 103 in proper alignment with the downstream XRF system 120, the x - ray beam spot 602 may not irradiate the material piece 101 or may only irradiate a portion of the material piece 101, which may result in capturing an XRF spectrum that includes all or a portion of the underlying conveyor - belt material (or adjacent material pieces), thus potentially leading to misclassification (and sorting, if implemented) of the material piece 101.

[0098] Figure 9 The figure shows an example of another potential problem, whereby the size (e.g., cross - section) of a particular material piece 101 is narrower than the effective diameter of the x - ray beam spot 602, such as in the instance of a material piece 101 having an elongated shape (also referred to herein as a thin strip or a material piece having the form of a thin - strip shape). Again, in such instances, the captured XRF spectrum will include measurements of the x - ray fluorescence of the elements in the underlying conveyor belt 103 on which the material piece 101 travels.

[0099] As Figure 10 shown, when such thin strips are placed on the conveyor belt 103 for classification and sorting, they can ultimately be positioned on the conveyor belt 103 in different orientations, many of which can result in the problems previously described with respect to Figure 9 , whereby the x - ray beam spot 602 does not fully fall on the thin strip (i.e., does not fully intersect the thin strip), that is, the intersection between the x - ray beam spot 602 and the material piece 101 is less than 100% (and thus, a portion of the underlying conveyor belt is also irradiated, causing the XRF detector to make XRF measurements of the elements in the conveyor belt).

[0100] As used herein, a material piece having a thin strip shape or form is any material piece having a cross-sectional dimension smaller than the effective diameter of the XRF beam spot 602 used within a system for classifying material pieces using x-ray fluorescence (e.g., the material handling system 100). For example, if the effective XRF beam spot that contacts (intersects) the material piece within such a system has a diameter of two inches, then the thin strip material piece will be any material piece having a cross-sectional dimension less than two inches. Similarly, if the effective XRF beam spot within such a system has a diameter of two millimeters, then the thin strip material piece will be any material piece having a cross-sectional dimension less than two millimeters, and so on. As Figure 9 and Figure 10 shown, such thin strips typically have a length significantly greater than the width (e.g., the length is three times or more the width dimension).

[0101] The above problems and especially the non-limiting examples as previously described with respect to Figure 9 are the classification and sorting of aluminum alloys. When various forged aluminum alloys or sheet aluminum alloys are used in the manufacture of certain end-use devices (e.g., as body parts in a vehicle (e.g., a Ford F-150)), the unused aluminum alloy material within the stamping process composed of different forged aluminum alloys (commonly referred to in the industry as "clips") can be mixed and shredded, resulting in a heterogeneous mixture of shredded aluminum alloy pieces, including those aluminum alloy pieces having an elongated or thin strip shape or form. In addition, it is well known that in the automotive industry, the shredded pieces of clips having an elongated shape or form (i.e., thin strips) are typically composed of aluminum alloys having a relatively high copper content (e.g., 6xx3).

[0102] When it is known that such thin strips have a relatively high copper content (e.g., >0.2%) (and thus belong to the 6xx3 series aluminum alloy), and the x-ray beam spot 602 and the thin strip do not completely intersect (e.g., <100%), the XRF measurement of the copper content in the thin strip is inaccurate and can even be low enough such that a thin strip material piece having a high copper content is classified as a different aluminum alloy than the 6xx3 aluminum alloy (e.g., an aluminum alloy having a lower copper content associated with a different aluminum alloy such as 6xx2 or 5xx3 aluminum alloy).

[0103] Figures 11A - 11F The figure shows an exemplary XRF spectrum demonstrating how an incorrect alignment (i.e., intersection) of the XRF beam spot 602 and the material piece 101 (e.g., a thin strip such as shown in Figure 9 or Figure 10 ) can result in such incorrect XRF readings or measurements. Figure 11AThe figure shows an exemplary XRF spectrum captured when the x-ray beam spot 602 fully irradiates at least a portion of the material piece 101 (i.e., there is 100% intersection between the x-ray beam spot 602 and at least a portion of the material piece 101). Figure 11B The figure shows an exemplary XRF spectrum captured when there is 85% intersection between the x-ray beam spot 602 and the material piece 101. Figure 11C The figure shows an exemplary XRF spectrum captured when there is 72% intersection between the x-ray beam spot 602 and the material piece 101. Figure 11D The figure shows an exemplary XRF spectrum captured when there is 62% intersection between the x-ray beam spot 602 and the material piece 101. Figure 11E The figure shows an exemplary XRF spectrum captured when there is 40% intersection between the x-ray beam spot 602 and the material piece 101. Figure 11F The figure shows an exemplary XRF spectrum captured when there is 12% intersection between the x-ray beam spot 602 and the material piece 101. In each of these XRF spectra, the peaks of three elements are highlighted to show how this problem leads to incorrect XRF readings or measurements. The peak labeled 1100 represents the XRF measurement (i.e., energy level count) of an element (e.g., copper (Cu) in a specific aluminum alloy) that is known to be included in the material piece and is known not to be included in the material (or at least included in a known lower (e.g., significantly lower) amount) that makes up the conveyor belt 103. The peaks labeled 1101 and 1102 represent elements (e.g., titanium (Ti), zinc (Zn), or nickel (Ni)) that are known to be included in the conveyor belt material 103 and are also known not to be included in the classified material piece (or at least included in a known lower (e.g., significantly lower) amount). As can be readily determined from the relative comparison of the exemplary spectra shown Figures 11A - 11F in, the peak 1100 decreases, and the peaks 1101 and 1102 increase proportionally as the percentage of intersection between the x-ray beam spot 602 and the material piece 101 decreases.

[0104] Embodiments of the present disclosure solve the above problems by measuring the intersection area between the x-ray beam spot and the material piece and correspondingly correcting / modifying the measured XRF spectrum associated with each material piece.

[0105] According to certain embodiments of the present disclosure, when the conveyor belt is used with (a plurality of) known different elements that can be specifically identified and taken into account (e.g., including knowing the amounts and relative percentages of these elements included in the conveyor belt), an algorithm can be implemented to determine the intersection area between the x-ray beam spot and the material piece.

[0106] Referring again to Figures 11A to 11F, the conveyor belt 103 can be implemented within the material handling system 100, whereby the conveyor belt 103 is composed of one or more different elements that are known not to be included in the material pieces to be classified and / or sorted. For example, if the known material pieces contain one or more certain specific elements (e.g., copper (Cu), manganese (Mn), chromium (Cr), and / or iron (Fe)), then a conveyor belt can be implemented that does not contain these elements (or is included at least in known lower (e.g., significantly lower) amounts), but instead contains one or more other known different elements that are known not to be included in the material pieces (e.g., zinc (Zn), titanium (Ti), and / or nickel (Ni)). Accordingly, a classification system is implemented to correct / modify the measured XRF spectra associated with each material piece in the material pieces based on the measurements of one or more of these specific elements known to be included in the conveyor belt. As Figures 11A - 11F shown by the exemplary XRF spectra, with respect to using a conveyor belt specifically composed of elements including titanium and zinc, as the intersection of the x-ray beam spot 602 and the material piece 101 decreases, the peaks associated with titanium 1101 and zinc 1102 increase, while the peak 1100 associated with the measurement of copper in the material piece decreases proportionally.

[0107] Next, referring to Figure 12 , a system and process 1200 configured to correct / modify the measured XRF spectra of material pieces according to certain embodiments of the present disclosure are illustrated. As further described herein, the system and process 1200 can be implemented within the system and process 400. In this non-limiting example, the conveyor belt includes titanium and zinc, and the material piece (which can include a thin strip) has a relatively high (e.g., > 0.2%) copper content. In an optional process block 1201, at some time before the classification of the material piece begins, if the XRF spectrum of the conveyor belt is not known or predetermined, the XRF spectrum of the conveyor belt is measured (e.g., calibrated in the absence of the material piece; i.e., 0% intersection between the material piece and the conveyor belt) to determine the amount and / or relative amount of elements within the conveyor belt. After the operation of the material handling system 100 begins, in process block 1201, the XRF spectrum of the material piece is measured when the material piece travels past the XRF system (e.g., Figure 1 the XRF system 120). Figure 13 illustrates a non-limiting example of the measured XRF spectrum of a material piece, in which there are a measured peak 1300 of copper, a measured peak 1301 of titanium, and a measured peak 1302 of zinc in the measured XRF spectrum of the material piece. In process block 1203, based on the measured XRF spectrum of the material piece, subsequent measurements are made of specific conveyor belt elements unique to the conveyor belt composition (e.g., energy level counts) to determine the percentage of the conveyor belt measured by the x-ray beam of the XRF system.

[0108] As Figure 14As shown, in this particular example, the x-ray beam spot 602 partially irradiates the material piece 101. In process block 1204, the intersection of the x-ray beam spot 602 with the material piece 101 is inferred from the XRF measurements of one or more elements unique to the conveyor belt (in this example, titanium and zinc). In this particular example, the x-ray beam spot is determined (calculated) to have irradiated 72% of the material piece and 28% of the conveyor belt. For example, such an inference can be made because the energy level count of either or both of the titanium and zinc elements is 28% of a known amount within the conveyor belt (i.e., the ratio of the measured amount of either or both of these elements to their known amount within the conveyor belt). In process block 1205, the XRF spectrum associated with the material piece 101 as shown in Figure 13 is then corrected / modified by subtracting the measured values of the XRF spectrum of the belt elements (which are either previously known (predetermined) or which may have been obtained at some previous time period (e.g., see process block 1201)) and dividing by the intersection percentage (i.e., the measured amount (energy level count) associated with the various elements identified within the XRF spectrum divided by the intersection percentage, which in this example will be divided by 0.72), resulting in the corrected / modified XRF spectrum of the material piece 101 as shown in Figure 15 , which shows how the copper peak 1300 is elevated while the titanium peak 1301 and zinc peak 1302 are decreased. The material piece 101 can then be classified using this corrected / modified XRF spectrum according to process block 405 of the system and process 400 of Figure 4 . And if sorting of the material pieces is performed, the material piece 101 can then be sorted according to process block 406 of the system and process 400 of Figure 4 .

[0109] Thus, it can be readily appreciated that the system and process 1200 are configured to correct / modify the XRF measurements of a material piece when the irradiated x-ray beam spot 602 does not intersect the material piece 101 100%. In this particular example, the copper measured within the exemplary material piece has been correctly accounted for, which can result in such material pieces being classified / sorted as high copper aluminum alloy rather than low copper aluminum alloy.

[0110] Next, referring to Figure 16 , there is illustrated a system and process 1600 configured to correct / modify the measured XRF spectrum of a material piece according to an alternative embodiment of the present disclosure. As further described herein, the system and process 1600 can be implemented within the system and process 400. In this non-limiting example, the conveyor belt includes titanium and zinc, and the material piece (which may include a thin strip) has a relatively high (e.g., >0.2%) copper content. As previously disclosed, such high copper content aluminum alloys may be misclassified as low copper aluminum alloys.

[0111] In process block 1601, as the material piece 101 travels past the XRF system (e.g., Figure 1 XRF system 120), the position of the material piece 101 on the conveyor belt 103 is measured (determined) relative to the position of the irradiated XRF beam spot on the conveyor belt 103 (which is known / pre-determined). That is, the position of the material piece and the width of the conveyor belt are determined to determine whether the material piece will pass properly under the XRF system such that the x-ray beam spot fully intersects the material piece. The measurement (determination) of the position of the material piece on the conveyor belt can be performed by a commercially available laser profiler (which can be implemented as device 111 within the material handling system 100 (see Figure 1 )) under the principle of laser triangulation. This is illustrated by the non-limiting example shown in Figure 17 , where as the material piece 101 travels on the conveyor belt 103, the position of the material piece 101 on the conveyor belt 103 is determined by the laser line 1701 from the profiler. Process block 1602 determines the intersection of the material piece 101 with the XRF beam spot 602 to determine (calculate) the percentage of the conveyor belt that will be measured by the x-ray beam spot 602 of the XRF system.

[0112] In process block 1603, the measured value of the XRF spectrum associated with the material piece 101 is then corrected / modified (e.g., see Figure 13 ) by subtracting the conveyor belt measurement value of the belt element (which is previously known (pre-determined) or which may have been obtained during some previous time period (e.g., see process block 1201)) and dividing by the intersection percentage, thereby producing a corrected / modified XRF spectrum of the material piece 101 (e.g., see Figure 15 ). The material piece 101 can then be classified according to the process block 405 of the system and process 400 of Figure 4 . And if sorting of the material piece is performed, the material piece 101 can then be sorted according to the process block 406 of the system and process 400 of Figure 4 .

[0113] Thus, it can be readily appreciated that the system and process 1600 are configured to correct / modify the XRF measurement value of the material piece when the irradiated x-ray beam spot 602 does not intersect the material piece 101 100%.

[0114] Next, referring to Figure 18 , a system and process 1800 configured according to an embodiment of the present disclosure are illustrated. In process block 1801, the material piece 101 is measured while the material piece 101 is on the moving conveyor belt 103 as it passes by an optical profiler or other similar device. Such a profiler can be any commercially available optical profiler (which can be implemented as device 111 within the material handling system 100 (seeFigure 1 ). In process block 1802, the profiler performs a three-dimensional (“3-D”) reconstruction of the material piece 101. In process block 1803, based on the shape resulting from the 3D reconstruction, it is determined whether the material piece 101 is a thin strip (or any other predetermined shape) (i.e., process block 1803 performs the classification / identification of such certain material pieces). Then, the material piece 101 can be sorted in processing block 1804 based on the determination / identification of the material piece 101. For example, a thin strip of aluminum alloy can be classified / sorted as an aluminum alloy with a high copper content.

[0115] The system and process 1800 can be implemented independently within the material handling system 100 or within the system and process 400. For example, process block 1801 to process block 1803 can be implemented in parallel with Figure 4 process block 405 within the system and process 400. And if sorting of the material piece is performed, then the material piece 101 can be sorted according to processing block 406. Thus, then the material pieces not classified / identified by process block 1803 can be classified / identified according to process block 403 to process block 405.

[0116] Any of the above commercially available profilers can alternatively be replaced by a combination of a camera and a two-dimensional laser scanner. Figure 20 The figure shows a simplified schematic diagram of such a laser-based camera system operating under the principle of laser slicing or laser triangulation. When the material piece 101 travels under the camera 2001 on the conveyor belt 103, an image of the moving material piece 101 is taken while the material piece 101 is also irradiated by a laser line emitted from the laser 2002 located near the camera 2001 at an angle θ. From Figure 20 the top view in, it can be seen that when the material piece 101 moves past the camera 2001, the height x of each part of the material piece 101 can be determined by the positioning of the line drawn by the laser beam on the material piece 101. Naturally, basic geometry can be used to determine this height x. For example, if the laser beam is predetermined (positioned) to reach at a 45° angle relative to the plane of the conveyor belt 103, then the height x will be equal to the distance x from the center of the image taken by the camera 2001. An exemplary demonstration in this regard is shown in Figure 21 where it can be easily seen how the z dimension of the material piece is determined by measuring the displacement between the shifted laser line and the reference line.

[0117] Figure 22A An alternative embodiment of the embodiment shown in Figure 20 is shown in, whereby multiple lasers emitted from the laser 2202 are combined with the camera 2201 to provide higher resolution at a given frame rate and belt speed. Thus, multiple laser beams can be used to reduce the frame rate.

[0118] Figure 22B FIG. illustrates another alternative embodiment, where the camera 2203 is combined with a plurality of lasers 2204, the plurality of lasers 2204 having different color laser beams (e.g., two or more) emitted therefrom, which will further reduce the frame rate.

[0119] Note that for these embodiments, laser beams of different colors can be used in cases where the material piece is folded, such that different parts of the material piece can be correctly identified and measured.

[0120] Figure 23 FIG. illustrates another alternative embodiment, whereby two different lasers 2302, 2303 are used on each side of the camera 2301 to overcome the problem that no laser is reflected from a part of the material piece 101 due to the material piece 101 being possibly bent or folded, thereby obstructing the camera 2301 from imaging one of the laser beams, or due to the presence of vertical walls on the material piece 101.

[0121] Any structured light system (e.g., grid lasers, a single laser with a mirror array, etc.) can be used to replace the laser systems described herein.

[0122] Figure 24 FIG. illustrates a process 2400 configured in accordance with certain embodiments of the present disclosure. The process 2400 can be used in conjunction with any one of the above-described embodiments shown with respect to Figure 20 , Figure 21 , Figure 22A , Figure 22B and Figure 23 In processing block 2401, the camera will capture an original image of the material piece. In process block 2402, the laser is extracted using a machine vision algorithm. In process block 2403, the height of each part of the material piece is then calculated based on the geometry. In processing block 2404, then, as the conveyor belt moves, multiple parts of the material piece are combined to obtain a three-dimensional reconstruction of the material piece. Then, the material piece can be sorted in process block 2405 based on the determination / identification of the material piece.

[0123] Now refer to Figure 5, depicts a block diagram of a data processing (“computer”) system 3400 illustrating aspects in which embodiments of the present disclosure may be implemented. (The terms “computer,” “system,” “computer system,” and “data processing system” may be used interchangeably herein.) Aspects of computer system 107, automation control system 108, one or more sensor systems 120, and / or vision system 110 may be configured similarly to data processing system 3400. Data processing system 3400 may employ a local bus 3405 (e.g., Peripheral Component Interconnect (“PCT”) local bus architecture). Any suitable bus architecture may be utilized, such as Accelerated Graphics Port (“AGP”) and Industry Standard Architecture (“ISA”), etc. One or more processors 3415, volatile memory 3420, and non-volatile memory 3435 may be connected to local bus 3405 (e.g., via a PCI bridge (not shown)). An integrated memory controller and cache memory may be coupled to one or more processors 3415. One or more processors 3415 may include one or more central processing units and / or one or more graphics processing units and / or one or more tensor processing units. Additional connections to local bus 3405 may be made via direct component interconnection or via a plug-in board. In the depicted example, a communication (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) may be connected to local bus 3405 via direct component connection. An audio adapter (not shown), a graphics adapter (not shown), and a display adapter 3416 (coupled to display 3440) may be connected to local bus 3405 (e.g., via a plug-in board inserted into an expansion slot).

[0124] A user interface adapter 3412 may provide connections for a keyboard 3413 and a mouse 3414, a modem (not shown), and additional memory (not shown). An I / O adapter 3430 may provide connections for a hard disk drive 3431, a tape drive 3432, and a CD-ROM drive (not shown).

[0125] An operating system may run on one or more processors 3415 and be used to coordinate and provide control over the various components within data processing system 3400. In Figure 5Among them, the operating system can be a commercially available operating system. Object-oriented programming systems (e.g., Java, Python, etc.) can run in conjunction with the operating system and provide calls to the operating system from one or more programs (e.g., Java, Python, etc.) executed on the data processing system 3400. Instructions for the operating system, object-oriented operating system, and programs can be located on a non-volatile memory 3435 storage device (such as a hard disk drive 3431) and can be loaded into the volatile memory 3420 for execution by the processor 3415.

[0126] Those of ordinary skill in the art will appreciate that Figure 5 the hardware in may vary depending on the implementation. As Figure 5 an addition to or alternative to the hardware depicted in, other internal hardware or peripheral devices such as flash ROM (or equivalent non-volatile memory) or optical disk drives may also be used. Additionally, any of the processes in this disclosure can be applied to a multiprocessor computer system or be executed by multiple such data processing systems 3400. For example, the training of the vision system 110 can be executed by a first data processing system 3400, while the operation of the vision system 110 for sorting can be executed by a second data processing system 3400.

[0127] As another example, the data processing system 3400 can be a bootable stand-alone system configured without relying on a certain type of network communication interface, regardless of whether the data processing system 3400 includes a certain type of network communication interface. As a further example, the data processing system 3400 can be an embedded controller configured with ROM and / or flash ROM providing non-volatile memory for storing operating system files or user-generated data.

[0128] Figure 5 The examples depicted in and the above examples are not meant to imply architectural limitations. Further, the computer program form of aspects of this disclosure can reside on any computer-readable storage medium used by a computer system (i.e., floppy disk, compact disk, hard disk, magnetic tape, ROM, RAM, etc.).

[0129] As has been described herein, embodiments of this disclosure can be implemented to perform the various functions described for identifying, tracking, classifying, differentiating, and / or sorting material pieces. Such functions can be implemented in hardware and / or software, such as in one or more data processing systems (e.g., Figure 5implemented within a data processing system 3400), such as aspects of one or more data processing systems including the previously mentioned computer system 107, vision system 110, (multiple) sensor systems 120, and / or automation control system 108. However, the functionality described herein is not limited to implementation in any particular hardware / software platform.

[0130] As will be appreciated by those skilled in the art, aspects of the present disclosure may be embodied as a system, process, method, and / or program product. Accordingly, aspects of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, embodiments combining software and hardware aspects being commonly referred to herein as “circuitry,” “circuit system,” “module,” or “system.” Additionally, aspects of the present disclosure may take the form of a program product 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 may be utilized. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium.)

[0131] A computer-readable storage medium may be, for example but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, biological, atomic, or semiconductor system, apparatus, controller, or device, or any suitable combination of the foregoing, where the computer-readable storage medium itself is not a transitory signal. More specific examples (a non-exhaustive list) of the computer-readable storage medium may include the following: an electrical connection having one or more wires, a portable computer floppy disk, a hard disk, a random access memory (“RAM”) (e.g., Figure 5 RAM 3420), a read-only memory (“ROM”) (e.g., Figure 5 ROM 3435), an erasable programmable read-only memory (“EPROM”) or flash memory, an optical fiber, a portable compact disc read-only memory (“CD-ROM”), an optical storage device, a magnetic storage device (e.g., Figure 5 hard disk drive 3431), or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, controller, or device. Program code embodied on a computer-readable signal medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, fiber optic cable, radio frequency, etc., or any suitable combination of the foregoing.

[0132] A computer-readable signal medium may include a propagated data signal having computer-readable program code embodied therein (e.g., in baseband or as part of a carrier wave). Such a propagated signal can take any of a variety of forms including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium that is not a computer-readable storage medium and that can transfer, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, controller, or device.

[0133] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of 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 the specified logical function(s). It should also be noted that, in some implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.

[0134] Modules implemented in software for execution by various types of processors (e.g., CPU 3415) may include, for example, one or more physical or logical blocks of computer instructions, which may, for example, be organized as objects, procedures, or functions. However, the executable files of the identified modules need not be physically together, but may include different instructions stored in different locations, which, when logically combined, include the module and implement the stated purpose for that module. In fact, the executable code of a module may be a single instruction or many instructions, and may even be distributed over several different code segments, distributed among different programs, and across several memory devices. Similarly, operational data (e.g., the material classification library and neural network parameters described herein) may be identified and illustrated within a module herein and can be embodied in any suitable form and organized within any suitable type of data structure. The operational data may be collected as a single data set or may be distributed over different locations (including distributed over different storage devices). The data may be provided as electronic signals on a system or network.

[0135] These program instructions can be provided to one or more processors and / or (a) controller(s) of a general purpose computer, special purpose computer, or other programmable data processing apparatus (e.g., a controller) to produce a machine such that the instructions, executed via the (a) processor(s) (e.g., CPU 3415) of the computer or other programmable data processing apparatus, create circuitry configured to implement the functions / actions specified in the flowchart and / or one or more block diagram boxes or means for implementing the functions / actions specified in the flowchart and / or one or more block diagram boxes.

[0136] It will also be noted that each block in the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can be implemented by a variety of means, including by dedicated hardware systems that perform the specified functions or actions, e.g., which may include one or more graphics processing units, or by combinations of dedicated hardware and computer instructions. For example, a module can be implemented as a hardware circuit that includes custom VLSI circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, controllers, or other discrete components. A module can also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, and the like.

[0137] In the description herein, the techniques shown in the flowcharts may be described as a series of sequential acts. Without departing from the scope of this teaching, the order of the acts and the elements performing the acts can be freely changed. Acts can be added, deleted, or changed in several ways. Similarly, acts can be reordered or looped. Further, although processes, methods, algorithms, etc., may be described in sequential order, such processes, methods, algorithms, or any combination thereof can operate to execute in an alternative order. Further, some of the acts within a process, method, or algorithm can be performed simultaneously at least at one point in time (e.g., the acts are performed in parallel), and can also be performed in whole, in part, or in any combination thereof.

[0138] As used herein, a device is “configured” to perform a certain function or a device is “configured for” performing a certain function. It should be understood that this can include selecting pre-defined logic blocks and logically associating them such that they provide a particular logical function, which particular logical function includes monitoring or control functions. It can also include programming computer software-based logic for a control device, wiring discrete hardware components, or any combination of the foregoing. Such configured devices are physically designed to perform the specified one or more functions.

[0139] Within the scope not described herein, many details regarding specific materials, processing acts, and circuitry are conventional and can be found in textbooks and other sources in the fields of computing, electronics, and software.

[0140] Computer program code (i.e., instructions) for performing operations in aspects of the present disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, Python, C++, etc., conventional procedural programming languages such as the "C" programming language or similar programming languages, programming languages such as MATLAB or LabVIEW, or any AI software in the AI software disclosed herein. The program code can be executed entirely on a user's computer system as a stand-alone software package, partially on a user's computer system, partially on a user's computer system (e.g., a computer system for sorting) and partially on a remote computer system (e.g., a computer system for training an AI 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 via any type of network connection, which includes a local area network ("LAN") or a wide area network ("WAN"), or can be connected to an external computer system (e.g., via the Internet using an Internet service provider). As an example of the foregoing, aspects of the present disclosure can be configured to execute on one or more of the following: computer system 107, automation control system 108, vision system 110, and aspects of (a plurality of) sensor systems 120.

[0141] These program instructions can also be stored in a machine-readable storage medium, which can direct a computer system, other programmable data processing apparatus, controller, or other device to act in a particular manner, such that the instructions stored in the machine-readable medium produce an article of manufacture including instructions for implementing the functions / actions specified in the flowchart and / or one or more block diagrams.

[0142] The program instructions can also be loaded onto a computer, other programmable data processing apparatus, controller, or other device, such that a series of operational steps are executed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, such that the instructions executed on the computer or other programmable apparatus provide a process for implementing the functions / actions specified in the flowchart and / or one or more block diagrams.

[0143] The association of certain data can be achieved by any data association techniques known and practiced in the art (e.g., between classified material pieces and their known chemical compositions, such as within the collection storage register as described above). For example, the association can be implemented either manually or automatically. Automatic association techniques can include, for example, database searches, database merges, GREP, AGREP, SQL, etc. The association step can be achieved through a database merge function, for example, using key fields in each of the manufacturer and retailer data sheets. The key fields partition the database according to the high-level categories of the objects defined by the key fields. For example, a certain category can be designated as the key field in both the first data sheet and the second data sheet, and then the two data sheets can be merged based on the category data in the key fields. In these embodiments, preferably, the data corresponding to the key fields in each of the merged data sheets in the merged data sheet is the same. However, for example, data sheets with similar but not identical data in the key fields can also be merged by using AGREP.

[0144] In the description herein, numerous specific details (such as examples of programming, software modules, user selections, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, controllers, etc.) are provided to provide a thorough understanding of the embodiments of the present disclosure. However, those skilled in the relevant art will recognize that the present disclosure can be practiced without one or more of these specific details, or by using other methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of the present disclosure.

[0145] As used herein, "manufacturing type" refers to the type of manufacturing process by which a material piece is manufactured, such as a metal component that has been formed by a forging process, cast (including but not limited to expendable mold casting, permanent mold casting, and powder metallurgy), forged; a material removal process, etc.

[0146] As referred to herein, a "conveyor system" can be any known piece of mechanical handling equipment that moves materials from one location to another, including but not limited to: pneumatic mechanical conveyors, automatic conveyors, conveyor belts, belt-driven live roller conveyors, bucket conveyors, chain conveyors, chain-driven live roller conveyors, drag conveyors, dust-proof conveyors, electric rail vehicle systems, flexible conveyors, gravity conveyors, gravity skate conveyors, spool roller conveyors, electric roller conveyors, overhead I-beam conveyors, land conveyors, pharmaceutical conveyors, plastic belt conveyors, pneumatic conveyors, screw or auger conveyors, screw conveyors, pipe gallery conveyors, vertical conveyors, vibratory conveyors, wire mesh conveyors, and convey materials within a fluid past a vision and / or sensor system (including but not limited to very small particles suspended in the fluid).

[0147] Throughout this specification, references to "an embodiment", "one or more embodiments", or similar language mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of the phrases "in one embodiment", "in an embodiment", "an embodiment", "certain embodiments", "various embodiments", and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment. Additionally, the described features, structures, aspects, and / or characteristics of the present disclosure may be combined in any suitable manner in one or more embodiments. Accordingly, even if initially claimed features function in certain combinations, one or more features from the claimed combination may in some instances be deleted from the combination, and the claimed combination may be directed to a sub-combination or a variation of a sub-combination.

[0148] Benefits, advantages, and solutions to problems have been described above with respect to specific embodiments. However, benefits, advantages, solutions to problems, and any element(s) that may cause any benefit, advantage, or solution to occur or become more prominent should not be construed as critical, required, or essential features or elements of any or all claims. Further, unless explicitly described as necessary or critical, the components described herein are not necessary for the practice of the present disclosure.

[0149] Those skilled in the art who have read the present disclosure will recognize that changes and modifications can be made to the embodiments without departing from the scope of the present disclosure. It should be understood that the specific embodiments shown and described herein may illustrate the present disclosure and its best mode and are not intended to limit the scope of the present disclosure in any other way. Other variations may fall within the scope of the appended claims.

[0150] Herein, the term "or" may be intended to be inclusive, where "A or B" includes A or B and also includes both A and B. As used herein, the term "and / or" when used in the context of listing entities refers to the entities that exist individually or in combination. Thus, for example, the phrase "A, B, C, and / or D" includes A, B, C, and D individually, but also includes any and all combinations and sub-combinations of A, B, C, and D.

[0151] The terms used herein are for the purpose of describing particular embodiments only and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an", and "the" may also be intended to include the plural forms unless the context clearly dictates otherwise.

[0152] All corresponding structures, materials, acts, and equivalents of apparatus or step-plus-function elements in the appended claims can be intended to include any structure, material, or act for performing a function in combination with other claimed elements that are specifically claimed.

[0153] As used herein, "substantially" with respect to the property or circumstance being identified, refers to a degree of deviation that is small enough so as not to visually depart from the identified property or circumstance. In some instances, the exact allowable degree of deviation may depend on the specific context.

[0154] As used herein, for convenience, a plurality of items, structural elements, compositional elements, and / or materials may be presented in a common list. However, these lists should be understood to identify each member in the list as a separate and distinct member. Thus, no individual member of such a list should be construed as a de facto equivalent of any other member of the same list solely based on its presence in a common group and without contrary indication.

[0155] Unless otherwise defined, all technical and scientific terms used herein (such as abbreviations for chemical elements in the periodic table) have the same meaning as commonly understood by one of ordinary skill in the art to which the subject matter of this disclosure belongs.

[0156] Unless otherwise indicated, all numbers expressing quantities of ingredients, reaction conditions, etc. used in the specification and claims are to be understood as being modified in all instances by the term "about". Accordingly, unless indicated to the contrary, the numerical parameters set forth in this specification and the appended claims are approximations that may vary depending upon the desired properties sought to be obtained from the subject matter of this disclosure. As used herein, the term "about" when referring to a value or amount of mass, weight, time, volume, concentration, or percentage is intended to encompass variations of in some embodiments ±20%, in some embodiments ±10%, in some embodiments ±5%, in some embodiments ±1%, in some embodiments ±0.5%, and in some embodiments ±0.1% from the specified amount, as such variations are appropriate for performing the disclosed methods.

[0157] The term "coupled" as used herein is not intended to be limited to direct or mechanical coupling. Unless otherwise stated, terms such as "first" and "second" are used arbitrarily to distinguish between elements described by such terms. Thus, these terms are not necessarily intended to indicate a temporal or other prioritization of such elements.

Claims

1. A method, comprising: conveying a workpiece past an x-ray fluorescence ("XRF") system on a moving conveyor belt; irradiating the workpiece with an x-ray beam emitted by the XRF system; measuring an XRF spectrum of the workpiece resulting from the irradiation of the workpiece with the x-ray beam; determining an intersection area between an x-ray beam spot of the irradiated x-ray beam and the workpiece; modifying the measured XRF spectrum of the workpiece based on the determined intersection area; and classifying the workpiece based on the modified XRF spectrum.

2. The method according to claim 1, further comprising sorting the workpiece from a mixture of workpieces conveyed on the moving conveyor belt.

3. The method according to claim 1, wherein the determining the intersection area between the irradiated x-ray beam spot of the x-ray beam and the workpiece comprises: determining a first position of the workpiece on the moving conveyor belt relative to a second position where the x-ray beam spot of the x-ray beam contacts the conveyor belt; and calculating the intersection area based on the determined first and second positions.

4. The method according to claim 1, wherein the determining the intersection area between the irradiated x-ray beam spot of the x-ray beam and the workpiece further comprises: measuring an amount of a first specific element within the measured XRF spectrum and comparing the amount with a known amount of the first specific element contained within the conveyor belt; and determining the intersection area from a ratio of the measured amount to the known amount.

5. The method according to claim 4, wherein the known amount of the first specific element contained within the conveyor belt is determined from a measurement of the XRF spectrum of the conveyor belt.

6. The method according to claim 4, wherein it is known that the first specific element contained within the conveyor belt is not contained within the workpiece.

7. The method according to claim 6, wherein the modifying the measured XRF spectrum of the workpiece based on the determined intersection area further comprises dividing a measured amount of a second specific element within the measured XRF spectrum by a difference obtained by subtracting a ratio of the measured amount to the known amount from 1.

8. The method according to claim 6, wherein the modifying the measured XRF spectrum of the workpiece based on the determined intersection area further comprises subtracting the measured amount of the first specific element from the measured XRF spectrum.

9. The method according to claim 6, wherein the modifying the measured XRF spectrum of the workpiece based on the determined intersection area further comprises: subtracting the measured amount of the first specific element from the measured XRF spectrum; and dividing a measured amount of a second specific element within the measured XRF spectrum by a difference obtained by subtracting the ratio of the measured amount to the known amount from 1.

10. The method according to claim 9, wherein it is known that the second specific element is not contained within the conveyor belt.

11. The method according to claim 10, wherein, the material piece is composed of aluminum alloy, and wherein the second specific element is copper.

12. The method according to claim 11, wherein, the first specific element is tin or zinc.

13. The method according to claim 11, wherein, the material piece has the shape of a thin strip, the cross-sectional dimension of the thin strip is smaller than the diameter of the x-ray beam spot, and wherein the material piece is classified as 6xx3 aluminum alloy according to the modified XRF spectrum.

14. A material processing system, comprising: a conveyor system configured to convey a mixture of material pieces; an XRF system configured to (i) irradiate the material piece with an x-ray beam emitted by the XRF system, and (ii) measure the XRF spectrum of the material piece generated by the irradiation of the material piece with the x-ray beam; a circuit system configured to determine the intersection area between the x-ray beam spot of the irradiated x-ray beam and the material piece; a circuit system configured to modify the measured XRF spectrum of the material piece according to the determined intersection area; a circuit system configured to classify the material piece according to the modified XRF spectrum; and a circuit system configured to sort the material piece from the mixture of material pieces being conveyed on a moving conveyor belt.

15. The material processing system according to claim 14, wherein, the intersection area between the x-ray beam spot of the irradiated x-ray beam and the material piece is determined by the ratio of the measured amount of a first specific element in the measured XRF spectrum to the amount of the first specific element known to be contained in the conveyor belt, wherein the first specific element is not contained in the material piece.

16. The material processing system according to claim 15, wherein, the known amount of the first specific element contained in the conveyor belt is determined by a separate measurement value of the XRF spectrum of the conveyor belt.

17. The material processing system according to claim 15, wherein, the circuit system configured to modify the measured XRF spectrum of the material piece according to the determined intersection area further comprises: a circuit system configured to subtract the measured amount of the first specific element from the measured XRF spectrum; and a circuit system configured to divide the measured amount of a second specific element in the measured XRF spectrum by the difference obtained by subtracting the ratio of the measured amount to the known amount from 1.

18. The material processing system according to claim 17, wherein, the material piece is composed of aluminum alloy, and wherein the second specific element is copper.

19. The material processing system according to claim 18, wherein, the first specific element is tin or zinc.

20. The material processing system according to claim 18, wherein, The material piece has the shape of a thin strip, the cross-sectional dimensions of the thin strip being smaller than the diameter of the x-ray beam spot, and wherein the material piece is classified as a 6xx3 aluminum alloy according to the modified XRF spectrum.

Images