Automated battery sorting system

Abstract

The present invention provides a system, apparatus, non-temporary computer-readable medium, and method for automatically classifying and sorting batteries of various classifications. [Solution] The battery classification system scans the target battery using multiple sensors, analyzes the signals from the multiple sensors using a classifier machine learning model to determine the battery classification of the target battery, and provides the predicted battery classification to the battery sorting mechanism 720 for sorting the target battery.

Description

Technical Field

[0001] Cross - Reference to Related Applications This application claims the benefits and priority of U.S. Provisional Patent Application No. 63 / 373,380, filed on August 24, 2022, U.S. Patent Application No. 18 / 452,961, filed on August 21, 2023, and U.S. Patent Application No. 18 / 452,974, filed on August 21, 2023. Each of the foregoing applications is hereby incorporated by reference in its entirety.

Background Art

[0002] In recent years, as an alternative to fossil fuels and other energy types, the introduction of various batteries has increased significantly. Further, the recent popularity of electric vehicles and other electronic devices has led to a significant increase in demand for battery production, as well as an increase in demand for the safe and efficient recycling or disposal of batteries and battery materials.

[0003] Despite the progress in battery production and implementation in various fields of use, existing methods for the bulk recycling and / or disposal of batteries and battery materials face several drawbacks. For example, conventional systems can safely recycle or dispose of batteries with a specific chemical composition, such as lithium - ion batteries. However, certain compositions of batteries are difficult or impossible to recycle in a safe and efficient manner. Therefore, various classifications of batteries must be sorted with a high level of certainty before recycling or disposal. Unfortunately, conventional methods of sorting and separating batteries generally require human attention and scrutiny for each battery, resulting in inefficiency and often inaccurate procedures when processing a large number of batteries for recycling and / or disposal.

[0004] These pose additional challenges and problems with respect to conventional battery recycling systems.

Summary of the Invention

[0005] Embodiments of the present disclosure provide benefits and / or solve one or more of the aforementioned or other problems in the art for automatically classifying and sorting batteries of various classifications using systems, apparatus, non-temporary computer-readable media, and methods. For example, the disclosed system intelligently classifies and sorts batteries according to chemical composition, shape factors, and / or other classifications utilizing various sensors and sorting mechanisms.

[0006] In some embodiments, for example, a device for sorting batteries of various configurations includes a hopper mechanism configured to discharge batteries individually onto a conveyor, and a scanner mechanism equipped with multiple sensors configured to determine the predicted battery configuration for each battery. The device also includes an array of sorting mechanisms configured to transfer batteries into multiple bins according to the predicted battery configuration. In one or more embodiments, additional sensors, such as infrared (IR) cameras, are implemented to detect abnormalities in discharged batteries, such as high temperatures.

[0007] Furthermore, in one or more embodiments, the battery classification system receives multiple signals corresponding to the target battery from multiple sensors. For example, the multiple sensors include two or more of the following: an X-ray scanning array, a three-dimensional (3D) scanner, and an RGB camera or an infrared camera. Accordingly, using a classifier model, the system determines the predicted battery classification of the target battery from multiple battery classifications based on the multiple signals. In one or more embodiments, the system indicates the predicted battery classification to the battery sorting mechanism.

[0008] Accordingly, the disclosed embodiments offer significant advantages over existing solutions, including improved efficiency enabled by automated battery classification and sorting. Furthermore, the disclosed embodiments exhibit increased safety by eliminating the need for human interaction with potentially volatile or unstable batteries, by accurately predicting battery classification to avoid failures in subsequent processes, and by providing enhanced measures for detecting battery anomalies throughout the classification and sorting process.

[0009] Additional features and benefits of one or more embodiments of the present disclosure are outlined in the following description, some of which may become apparent from that description or may be grasped by the implementation of such exemplary embodiments. [Brief explanation of the drawing]

[0010] A more detailed description, using the attached drawings, provides one or more embodiments with additional specificities and details, as briefly described below. [Figure 1] Figure 1 illustrates a perspective view of an automated battery sorting system according to one or more embodiments. [Figure 2] Figure 2 illustrates additional perspective views of an automated battery sorting system according to one or more embodiments. [Figure 3] Figure 3 illustrates a top view of an automated battery sorting system according to one or more embodiments. [Figure 4] Figure 4 illustrates a perspective view of a scanning bay of an automated battery sorting system according to one or more embodiments. [Figure 5A] Figure 5A illustrates additional perspective views of the scanning bay of an automated battery sorting system according to one or more embodiments. [Figure 5B] Figure 5B illustrates additional perspective views of the scanning bay of an automated battery sorting system according to one or more embodiments. [Figure 6]Figure 6 illustrates a perspective view of a battery tipper and hopper assembly of an automated battery sorting system according to one or more embodiments. [Figure 7] Figure 7 illustrates an environment in which a battery classification system can operate according to one or more embodiments. [Figure 8] Figure 8 illustrates a schematic diagram of a battery classification system according to one or more embodiments. [Figure 9] Figure 9 illustrates a battery classification system using an RGB camera according to one or more embodiments. [Figure 10] Figure 10 illustrates a battery classification system utilizing a three-dimensional (3D) scanner and an X-ray scanning array according to one or more embodiments. [Figure 11] Figure 11 illustrates a flowchart of a series of operations for classifying and sorting batteries according to one or more embodiments. [Figure 12] Figure 12 illustrates a block diagram of an exemplary computer device for implementing one or more embodiments of the present disclosure. [Modes for carrying out the invention]

[0011] This disclosure describes one or more embodiments of a battery classification system that intelligently classifies batteries of various configurations based on inputs from various sensors. For example, in some implementations, the battery classification system uses a battery classifier machine learning model based on various sensor signals to predict the battery classification for a target battery. Furthermore, some embodiments include a battery sorting mechanism configured to sort batteries according to the battery classification predicted by the embodiment of the battery classification system.

[0012] In some embodiments, for example, the battery classification system receives multiple signals corresponding to the target battery from multiple sensors. In response, the battery classification system uses a classifier machine learning model to determine the predicted battery classification of the battery from multiple battery classifications based on the multiple signals. In some embodiments, the battery classification system also indicates the predicted battery classification to the battery sorting mechanism. Furthermore, in some embodiments, the multiple sensors include two or more of the following: X-ray scanning arrays, three-dimensional (3D) scanners, RGB cameras, or infrared cameras.

[0013] In addition, one or more embodiments of a device for sorting batteries of various configurations include a hopper mechanism, a scanner mechanism, and an array of sorting mechanisms. In some embodiments, the hopper mechanism is configured to discharge multiple batteries individually onto a conveyor. Furthermore, the scanner mechanism, in some embodiments, comprises multiple types of sensors positioned around the conveyor and configured to determine the predicted battery configuration for each battery from multiple battery configurations. Also, in some embodiments, the array of sorting mechanisms is positioned around the conveyor and configured to transfer multiple batteries from the conveyor to multiple bins based on the predicted battery configuration for each of the multiple batteries.

[0014] Accordingly, the disclosed embodiments provide automated classification and sorting of batteries, including various classifications such as, but not limited to, chemical composition, shape factors, and other configurations. Furthermore, by utilizing various sensors for scanning and analyzing individual batteries, such as three-dimensional (3D) scanners, X-ray scanning arrays, RGB cameras, and infrared (IR) cameras, the disclosed systems accurately and efficiently classify and sort batteries for further processing. In fact, the disclosed systems can identify / classify batteries of various classifications and sort large quantities of batteries accordingly, while improving safety and efficiency. In addition, one or more disclosed embodiments utilize a classifier machine learning model to intelligently and efficiently predict battery classifications according to data provided by a battery classification database.

[0015] Therefore, the disclosed battery classification and sorting system offers many advantages and benefits over conventional systems and methods. For example, by utilizing multiple sensor types and a trained classifier model, the battery classification system improves accuracy compared to conventional systems. Specifically, the disclosed embodiment utilizes a classifier machine learning model to intelligently identify battery classifications in an automated process by comparing and analyzing various attributes provided by sensors with a data library of battery classifications.

[0016] Furthermore, by utilizing an automated process for determining battery classification using a trained classifier model, the disclosed system improves efficiency compared to conventional systems. Specifically, the disclosed embodiment intelligently analyzes and determines the classification of a large number of batteries, automatically and without requiring human consideration for each battery in most implementations. Thus, the disclosed system can efficiently sort batteries into item groups according to their predicted classifications.

[0017] In addition, the disclosed system improves the safety of the process for identifying and sorting batteries for recycling and / or disposal. Specifically, the disclosed system reliably predicts the classification of batteries and avoids inadvertent handling of batteries by incorrect procedures. For example, a battery with a certain chemical composition may be impossible or uneconomical to process by typical processes, while other types of batteries can be easily recycled by known procedures. Further, by utilizing sensors such as infrared (IR) cameras to scan for battery abnormalities (e.g., high temperature), the disclosed system can prevent accidents involving volatile materials typical of many batteries.

[0018] As explained by the foregoing discussion, the present disclosure utilizes various terms to describe the features and advantages of the disclosed system. Here, additional details regarding the meaning of such terms are provided. For example, as used herein, the term "machine learning model" refers to a model that can be trained and / or adjusted based on inputs to approximate an unknown function. For example, the term "machine learning model" can include, but is not limited to, a random forest model, a decision tree (e.g., a series of gradient-boosted decision trees (e.g., XGBoost algorithm)), a multilayer perceptron, linear regression, a support vector machine, a deep learning architecture, a deep learning transformer (e.g., a self-attention transformer), or logistic regression. In other embodiments, the machine learning model can include neural networks such as convolutional neural networks, recurrent neural networks (e.g., LSTM), graph neural networks, self-attention transformer neural networks, diffusion neural networks, or adversarial generative neural networks.

[0019] As used herein, the term "X-ray attenuation" refers to the decrease in the intensity of X-rays as they cross through a material, which can be caused by the absorption or deflection of photons from the X-ray beam. X-ray attenuation can be affected by different factors such as the beam energy and the atomic energy of the data that absorbs the X-rays. In particular, the disclosed system takes into account the X-ray attenuation detected when determining the chemical and / or material composition of the target battery, as will be considered in more detail below.

[0020] As used herein, the term "object recognition" refers to computer techniques for finding and identifying objects within an image. For example, the term "object recognition" can include, but is not limited to, appearance-based methods, edge matching, segmentation methods, grayscale matching, gradient matching, object detection neural networks, decision trees, or any of various models trained to recognize objects within an image.

[0021] Additional details are provided herein in connection with exemplary diagrams depicting exemplary embodiments and implementations of the disclosed methods, apparatuses, and systems. For example, FIGS. 1-6 illustrate various diagrams of an automated battery sorting system 100 according to one or more embodiments. Specifically, FIG. 1 illustrates a perspective view of the automated battery sorting system 100, FIG. 2 shows an additional perspective view of the automated battery sorting system 100, and FIG. 3 illustrates a top view of the automated battery sorting system 100. Further, FIG. 4 illustrates a perspective view of the scanning bays 102 and 104 of the automated battery sorting system 100, and FIGS. 5A-5B illustrate additional perspective views of the scanning bays 102 and 104. Further, FIG. 6 illustrates a perspective view of the tipper mechanism 110 and hopper 112 of the automated battery sorting system 100.

[0022] As illustrated in Figures 1-3, the automated battery sorting system 100 includes a tipper mechanism 110 configured to receive a large number of batteries for sorting. In some embodiments, the tipper mechanism 110 includes a large chamber or bin 126 into which unsorted batteries can be placed to initiate the sorting process. In some embodiments, for example, a load of batteries can be directly transferred into the bin 126 from a battery collection container, barrel, truck bed, pallet, etc. Furthermore, the tipper mechanism 110 may include, but is not limited to, devices for moving batteries from the bin 126 into a hopper 112, such as a movable platform, slide, pneumatic lifter and / or tipper, or conveyor belt. Thus, batteries placed in the bin 126 pass from the bin 126 through the tipper mechanism 110 into the hopper 112, which forces them to pass through individually for subsequent scanning. In some embodiments, for example, the hopper includes a vibrating table configured to separate batteries in a group of items by shape factor and / or weight. For example, in some implementations, the hopper 112 removes smaller batteries from the group of items so that smaller batteries are separated from relatively larger batteries. Additional details and examples of the tipper mechanism 110 and the hopper 112 are described below in relation to Figure 6.

[0023] As further illustrated in Figures 1-3, in some embodiments, individual batteries pass from hopper 112 along inclined conveyor 114 and fall into feeder 116 for individual scanning, classification, and sorting. Alternatively, in one or more embodiments, batteries are directed directly from hopper 112 to the scanning area of ​​automated battery sorting system 100. For example, the outlet of hopper 112 may be positioned directly above or otherwise close to the scanning area or horizontal conveyor of automated battery sorting system 100. Furthermore, in some embodiments, automated battery sorting system 100 includes one or more actuators and / or structures configured to arrange batteries arriving before entering subsequent scanning areas. For example, automated battery sorting system 100 may arrange individual batteries for single measurement and single discharge / diversion into associated storage bins. Also, in some embodiments, one or more arrangement mechanisms (e.g., actuators, structures, etc.) can position batteries arriving at specific angles related to X-ray and other scanning power sources to improve measurement accuracy. The array mechanism may include, but is not limited to, guide rails, pneumatic arms, vibration tables, expansion / contraction brackets, gates, etc.

[0024] In the exemplary embodiment, each battery slides individually through the feeder 116 toward the first scanning bay 102 and the second scanning bay 104, or passes through in another manner. In particular, the first scanning bay 102 comprises one or more sensors, including, but not limited to, one or more RGB cameras, infrared (IR) cameras, or 3D scanners. Furthermore, the 3D scanner may include, but is not limited to, one or more optical cameras, 3D laser scanners, computed tomography scanners, structured optical 3D scanners, LiDAR, or time-of-flight laser scanners. Thus, in one or more embodiments, the automated battery sorting system 100 utilizes various visual sensors to scan each battery within the first scanning bay 102. As will be further described below (for example, in relation to Figures 7-10), the automated battery sorting system 100 utilizes various sensors to determine the attributes of each battery based on the sensor signals and to predict the battery classification or category of each battery based on the determined attributes.

[0025] Furthermore, the sensors(s) in the first scanning bay 102, and optionally the second scanning bay 104 of the automated battery sorting system 100, include an X-ray scanning array configured to emit and detect an X-ray beam as it passes through each battery for further analysis (i.e., to provide additional input to the battery classifier model). In some embodiments, either or both of the first scanning bay 102 and the second scanning bay 104 further include an array mechanism configured to position each battery in an ideal position and / or orientation for the scanning procedure. Such an array mechanism may include, for example, a series of bumpers / rails, movable actuators, tumblers, or other devices capable of rearranging smaller batteries into larger batteries. As also mentioned, in response to scanning each battery in the first and second scanning bays 102 and 104 to determine various attributes of each battery, the automated battery sorting system 100 utilizes a classifier model to determine the predicted battery classification for each battery.

[0026] In any case, the automated battery sorting system 100 includes at least one scanning bay and multiple sensors. As shown in Figures 1-3, in at least one specific example, the automated battery sorting system 100 includes two scanning bays 102 and 104, each housing a different type of scanner. In one or more implementations, the first scanning bay 102 includes one or more sensors for detecting / measuring / acquiring attributes of a first type of battery. Similarly, the second scanning bay 104 includes one or more additional sensors for detecting / measuring / acquiring attributes of a second type of battery, which are different from the attributes of the first type.

[0027] For example, in one or more implementations, the first scanning bay 102 includes one or more sensors that detect / measure / acquire one or more visible attributes of the battery (e.g., attributes of a first type). In particular, one or more sensors in the first scanning bay 102 detect / measure / acquire one or more of the following: battery size (e.g., volume, height, width), battery color, battery shape, text on the battery, etc. Similarly, in one or more implementations, the second scanning bay 104 includes one or more sensors that detect / measure / acquire one or more invisible attributes of the battery (e.g., attributes of a second type). In particular, one or more sensors in the second scanning bay 104 detect / measure / acquire one or more of the following: battery temperature, battery X-ray decay, atomic number of one or more data of the battery, battery data composition, battery weight, etc.

[0028] Furthermore, as shown in Figures 1-3, the automated battery sorting system 100 comprises one or more stands 124, providing screener or operator access to scanning bays 102 and 104 and other areas of the system. In addition, the shown screener stands 124 provide access to support cabinets 122 that house various components of the scanning system in bays 102 and 104, such as generators, IO feeds, analog controls, and / or digital operator consoles.

[0029] Furthermore, some embodiments of the automated battery sorting system 100 include one or more infrared cameras positioned at one or more locations within the system to monitor high-temperature batteries, and optionally include a safety mechanism. For example, the safety mechanism may include one or more of an alarm, a fire extinguisher, a battery dunk tank, or an emergency power off (EPO) configured to be activated in response to a signal from at least one of multiple types of sensors. For example, the automated battery sorting system 100 includes a safety receptacle (e.g., a dunk tank) for discarding batteries whose temperature has risen as detected by one or more infrared cameras. The safety receptacle includes a flame-retardant material. Alternatively, the automated battery sorting system 100 is configured to add fire-resistant material to the safety receptacle once a battery has been added to it. As used herein, the term “safety receptacle” refers to a receptacle for storing batteries and other potentially hazardous materials. In one or more embodiments, the safety receptacle may be made from a durable fire-resistant material such as metal. Furthermore, the terms “flame retardant material” or “fire retardant” refer to materials used to prevent fires related to metals, flammable liquids, or volatile materials such as lithium-ion batteries. For example, in some implementations, fire retardants may include mineral-based fire extinguishing agents such as vermiculite, perlite, expanded clay, expanded polystyrene (EPS), CellBlockEX, and other fire, heat, and / or smoke suppressing compounds.

[0030] In addition, in one or more embodiments, various components of the automated battery sorting system 100 are covered with shock-absorbing material (e.g., rubber) to mitigate the impact on batteries as they pass through the system. Furthermore, in some embodiments, the automated battery sorting system 100 includes an antistatic coating on its metal surfaces to reduce the risk of electrical short circuits in batteries.

[0031] As illustrated, after passing through scanning bays 102 and 104, each battery continues along the conveyor 106 toward a plurality of sorting bins 108. The automated battery sorting system 100 transfers each target battery to one of the sorting bins 108 according to the predicted classification for each battery. In particular, the sorting bins 108 contain bins for each battery configuration of a plurality of battery configurations. Furthermore, in one or more implementations, one or more of the sorting bins 108 are equipped with safety bins (e.g.,

[0044] ). In some embodiments, for example, the automated battery sorting system 100 utilizes multiple actuators or gates (i.e., diverters) to move the target batteries into the corresponding bins of the sorting bins 108. For example, as shown in Figure 2, some embodiments include a movable actuator 202 selectively positioned to push, pull, or guide the arriving batteries into the sorting bins 108 according to the expected classification. Alternatively, or in addition to, embodiments of the automated battery sorting system 100 may include a sorting mechanism that includes pneumatic actuators, guides, hoists, cranes, platforms, or alternative means for diverting batteries to their respective bins in the sorting bins 108. Furthermore, in some embodiments, the automated battery sorting system 100 includes one or more sensors configured to verify that the batteries have been received by the correct sorting bins 108. For example, the verification sensors may include, but are not limited to, a camera or pressure sensor integrated with the sorting bins 108.

[0032] Figures 1-3 illustrate an automated battery sorting system 100 having two rows of sorting bins 108. Specifically, Figures 1-3 illustrate rows of sorting bins on each side of a conveyor 106. In alternative implementations, the automated battery sorting system 100 may include more or fewer rows of sorting bins than two. For example, in one or more implementations, the automated battery sorting system 100 may include one row of sorting bins 108 on one side of the conveyor 106. Alternatively, the automated battery sorting system 100 may include three or four rows of sorting bins 108. For example, the automated battery sorting system 100 may include multiple rows of sorting bins 108 at different vertical heights on both sides of the conveyor 106.

[0033] As also shown, the automated battery sorting system 100 includes return conveyors 118, 120, and 128 for returning batteries to the hopper 112 (or, alternatively, the receiving bin 126 of the tipper mechanism 110) if additional scanning and / or analysis is required. For example, in some cases, battery classification may be insufficient if, for some reason, a battery was not properly scanned or if a battery configuration that was not previously seen is encountered. At least in such cases, the battery is returned to the front of the automated battery sorting system 100 and the scanning and classification process is repeated. In some embodiments, batteries whose classification is uncertain or otherwise insufficient are sorted into bins of sorting bins 108 designated for alternative handling. In some implementations, unidentified batteries are allowed to pass through the end of the conveyor 106 so that they fall into one or more bins 130 located at the end of the conveyor 106.

[0034] Furthermore, in some embodiments, instead of (or in addition to) the sorting bins 108 positioned adjacent to the conveyor 106, the automated battery sorting system 100 may include additional conveyors adjacent to the main conveyor 106, which can be configured to deliver batteries to individual bins or to other areas for sorting and / or further processing. Thus, in some embodiments, the aforementioned actuators can cause batteries to be diverted onto additional conveyors according to the expected classification for each battery.

[0035] As shown in Figures 4 and 5A-5B, scanning bays 102 and 104 include one or more sensors for scanning the battery as it passes from the feeder 116 and across the conveyor 106. For example, scanning bay 102 includes a scanning bar 402 equipped with one or more of a three-dimensional (3D) scanner, an RGB camera, or an infrared (IR) camera. In additional embodiments, the scanning bay 102 includes additional sensors in additional locations to provide scanning of each battery at various angles and / or distances as it passes through the scanning bay 102. For example, in some embodiments, multiple cameras are provided in various locations to acquire images of each side of each battery. For example, in addition to or instead of being located within the scanning bar 402, RGB cameras are positioned on the side of the conveyor so that they can acquire views of the sides of the batteries as they pass through the scanning bay 102. Furthermore, in some embodiments, additional sensors are provided to measure the weight of each battery for additional input to predict the corresponding battery configuration.

[0036] Furthermore, as shown in Figure 4, the scanning bay 104 includes an X-ray scanning array comprising an X-ray emitter 404 and an X-ray detector 406. In one or more embodiments, for example, the X-ray emitter is mounted in the housing of the scanning bay 104 and oriented to emit an X-ray beam toward the conveyor 106. Correspondingly, in one or more embodiments, the X-ray detector 406 is mounted beneath the conveyor 106 and detects and measures the X-ray beam emitted from the X-ray emitter 404 through each battery as it passes through the scanning bay 104. Furthermore, in one or more embodiments, the X-ray detector 406 is housed in a retractable drawer 412, thus facilitating adjustment and maintenance of the X-ray detector 406. In additional implementations, the scanning bay 104 includes multiple X-ray scanning arrays. For example, the scanning bay 104 includes two, three, or more photodetector arrays, each arranged at different angles to the batteries placed on the conveyor 106. In particular, in addition to measuring the X-ray attenuation passing vertically through the batteries as shown in Figure 4, the scanning bay 104 includes an X-ray scanning array that measures the X-ray attenuation passing horizontally through the batteries. In such an implementation, the automated battery sorting system 100 includes an X-ray emitter on one side of the conveyor 106 and an X-ray detector on the opposite side of the conveyor 106. In any case, in light of the disclosure herein, it will be understood that the scanning bays 102, 104 may include sensors located on one or more sides of the conveyor 106, vertically above and / or below the conveyor 106, and at one or more acute angles (e.g., 30 degrees, 45 degrees, 60 degrees, 120 degrees, 135 degrees, 150 degrees) relative to the conveyor 106.

[0037] Furthermore, as also shown in Figures 4 and 5A-5B, the support cabinet 122 includes a generator 408 for supplying power to the X-ray scanning array and / or other components of the automated battery sorting system 100. Additionally, the exemplary support cabinet includes 10 boxes 410 (i.e., input / output modules) and a control assembly 502 (see Figure 5A). While the shown control assembly 502 is an analog control device related to the X-ray scanning array, embodiments of the automated battery sorting system 100 may also include an operating console capable of controlling sensors in both scanning bays 102 and 104, as well as other aspects of the battery classification and sorting system of the automated battery sorting system 100.

[0038] As further shown in Figure 6, the automated battery sorting system 100 also includes a tipper mechanism 110 with a receiving bin 126 for receiving a group of batteries for classification and sorting. With the group of batteries loaded into the receiving bin 126 of the tipper mechanism 110, an actuator 606 of the tipper mechanism 110 raises the group of batteries into a hopper 112 and distributes them toward the subsequent sections of the automated battery sorting system 100. In some embodiments, for example, the actuator 606 rotates the chamber (i.e., tip) of the tipper mechanism 110 upward until the batteries are distributed from an opening 608 adjacent to the hopper 112. Additional examples of actuators for moving the group of batteries from the receiving bin 126 to the hopper 112 may include, for example, a conveyor belt, a movable platform, or a drop chute (e.g., having a receiving bin 126 positioned above the hopper 112). Alternatively, the battery can be loaded directly into the hopper 112 by hand, a conveyor, a forklift, or another loading mechanism.

[0039] As described above, the hopper 112 vibrates and separates the batteries, distributing them onto an inclined conveyor 114, either directly to the feed chute 116 or in another way toward the scanning area of ​​an automated battery sorting system 100. For example, in some embodiments, the hopper 112 is configured to individually distribute the batteries therefrom to the inclined conveyor 114 (see Figures 1-3) via a tapered outlet 604. As illustrated, the hopper 112 includes an excitation table 602 configured to separate the batteries and guide them toward the tapered outlet 604. In some embodiments, the hopper 112 also includes gradually narrowing rails or side walls that further guide the batteries toward the tapered outlet 604 as they are excited away from each other by the excitation table 602. In some embodiments, the batteries are guided through a tapered chamber with or without the use of an excitation table.

[0040] As also shown in Figure 6, the hopper 112 may further include a weighing gate 610. In one or more embodiments, for example, the weighing gate 610 may be equipped with one or more sensors that detect individual batteries as they pass through the weighing gate 610 toward the tapered outlet 604. In some embodiments, weighing gates such as the weighing gate 610 are located at one or more selected locations in the automated battery sorting system 100 to keep track of the amount of batteries passing through various sections of the automated battery sorting system 100.

[0041] As described above, the disclosed embodiments include a battery classification system configured to intelligently classify batteries of various types or configurations (i.e., various classifications) based on multiple sensor signals, such as those described above in relation to the automated battery sorting system 100 in Figures 1-6. For example, Figure 7 illustrates a schematic diagram of a battery classification system 704 operating according to one or more embodiments.

[0042] As shown in Figure 7, in some embodiments, the computer device 702 includes a battery classification system 704 that communicates with a plurality of sensors 710 and a battery sorting mechanism 720. In alternative embodiments, the battery classification system 704 is located on one or more server devices that communicate with the computer device 702, the plurality of sensors 710, and / or the battery sorting mechanism 720 over a network. In fact, various configurations of the computer device, server device, storage device, sensors, and other components are anticipated by this disclosure.

[0043] As shown in Figure 7, the battery classification system 704 includes a classifier model 706 and a database 708 containing multiple battery classifications and their associated attributes (i.e., the chemical composition, shape factors, and other attributes of the battery within each of the multiple battery classifications). Thus, the battery classification system 704 is trained to compare and / or use the battery classification data contained in the database 708 to make battery classification predictions based on signals from multiple sensors 710. As previously stated, in one or more embodiments, the classifier model 706 includes a machine learning model trained to classify batteries based on multiple signals from multiple sensors 710.

[0044] As shown in Figure 7, in some embodiments, the plurality of sensors 710 include an X-ray scanning array 712 (e.g., as described above in relation to the second scanning bay 104, X-ray emitter 404 and X-ray detector 406), a three-dimensional (3D) scanner 714 (e.g., as described above in relation to the first scanning bay 102 and scanning bar 402), one or more RGB cameras 716 (e.g., as described above in relation to the first scanning bay 102 and scanning bar 402), and / or an infrared camera 718 (e.g., as described above in relation to the first scanning bay 102 and scanning bar 402). In fact, embodiments of the battery classification system 704 may include any or all of the sensors among the plurality of sensors 710 shown, as well as additional sensors for the batteries to be scanned / imaged. Furthermore, Figures 1-6 illustrate exemplary types, configurations, and arrangements of sensors for scanning batteries, but alternative embodiments include different types, configurations, and arrangements of the plurality of sensors 710. Furthermore, in some embodiments, sensor data is received indirectly from multiple sensors 710, such as from an alternative source or within a data package received with each target battery.

[0045] Furthermore, as shown in Figure 7, in one or more embodiments, the battery classification system 704 communicates with a battery sorting mechanism 720 which includes multiple actuators 722 for sorting batteries into multiple sorting bins 724 (for example, as described above in relation to Figures 1-6). For example, in response to a prediction of the battery classification for a target battery, the battery classification system 704 indicates the predicted classification to the battery sorting mechanism 720, and in some implementations, indicates the location of the target battery on the conveyor 106. In response, the battery sorting mechanism 720 uses one or more actuators from the multiple actuators 722 (e.g., actuator 202) to move the target battery into a bin of the sorting bin 724 corresponding to the predicted battery classification.

[0046] In addition, in some embodiments, the battery classification system 704 is configured to detect and respond to abnormalities within the batteries. For example, as shown in Figure 7, a plurality of sensors 710 include an infrared camera 718, which is configured to monitor batteries experiencing high temperatures or other thermal anomalies. When a high temperature (or other undesirable thermal condition) exceeding a certain threshold is detected, the battery classification system 704 indicates the anomaly to the battery sorting mechanism 720, which then activates one or more alarms 726 to stop the classification process and / or eject the battery in question (e.g., move the battery in question into a safety receptacle (e.g., a dunk tank or other enclosure)).

[0047] As described above, the battery classification system 704 can predict battery classification based on signals from multiple sensors utilizing a classifier model. For example, Figure 8 illustrates a battery classification system 704 in one or more embodiments that determines battery classification 826 using a classifier machine learning model 802. Specifically, Figure 8 shows a battery classification system 704 that receives multiple signals from sensor 816 and uses the classifier machine learning model 802 to determine battery classification 826 from multiple battery classifications stored in database 814. Battery classification can include various categories of batteries, such as, but not limited to, chemical composition, size, intended use, commercial brand, model type / number, etc. The chemical composition of a battery can include, for example, lithium, lithium ions, aluminum ions, magnesium ions, sodium ions, potassium ions, alkaline, nickel, carbon-zinc, silver oxide, aluminum-air, zinc-air, zinc-carbon, zinc chloride, zinc ions, lead-acid, or any other battery composition received for classification by the battery classification system 704.

[0048] As shown in Figure 8, the multiple sensors 816 include a three-dimensional (3D) scanner, an X-ray scanning array 820, one or more RGB cameras 822, and an infrared (IR) camera 824. The sensors 816 acquire / measure signals that are passed to the battery classification system 704. The battery classification system 704 determines one or more attributes of the battery from the signals. The classifier machine learning model 802 determines the battery classification from one or more attributes.

[0049] In the exemplary embodiment, for example, the battery classification system 704 receives an image from the 3D scanner 818. From the image, the battery classification system 704 determines one or more physical attributes of the batteries in the image. For example, the battery classification system 704 determines one or more dimensions 804 of the target battery from the signal (e.g., data) received from the 3D scanner 818. Specifically, the battery classification system 704 determines one or more of the height, width, length, or volume of the target battery. The classifier machine learning model 802 generates a battery classification 826 based on at least a portion of the dimensions 804.

[0050] Alternatively, in one or more implementations, for example, the battery classification system 704 manipulates signals received from the 3D scanner 818 to determine or generate attributes of the target battery. For example, the battery classification system 704 generates a three-dimensional profile of the target battery. Specifically, the battery classification system 704 reconstructs the three-dimensional shape or profile of the target battery using one or more images or 3D scans. In other words, the battery classification system 704 determines the shape of the target battery from signals from the sensor 816. The classifier machine learning model 802 generates a battery classification 826 based on at least a portion of the shape or profile of the target battery.

[0051] Furthermore, the battery classification system 704 determines one or more indicators of X-ray attenuation 806 from the signal received from the X-ray scanning array 820 of the target battery. In one or more embodiments, for example, the X-ray scanning array 820 writes the X-ray data associated with the target battery to a cache memory in one or more data subsets (i.e., chunks). Thus, the battery classification system 704 can access one or more data subsets for the target battery, and if multiple subsets correspond to a single battery, the multiple subsets can be concatenated for subsequent processes. In some embodiments, the battery classification system 704 receives a signal from the X-ray scanning array 820, monitors the temperature of one or more scintillators of the X-ray scanning array 820, and, if necessary, recalibrates the X-ray gain lookup table in accordance with the static offset and gain rate per pixel as each changes in real time (e.g., depending on temperature). In one or more embodiments, the battery classification system 704 uses an X-ray gain lookup table to determine the X-ray attenuation 806 and normalizes the signal from the detector of the X-ray scanning array 820 to obtain an attenuation measurement result adjusted according to the aforementioned real-time update. Furthermore, in embodiments, the battery classification system 704 uses a time-attenuation model to reduce the effect of afterglow from the scintillator shown in any given signal from the X-ray scanning array 820.

[0052] In addition, in some embodiments, the battery classification system 704 arranges high and low energy pixels from the X-ray scanning array 820 signal to generate high / low energy pairs (e.g., as shown in database 814) to determine which portion of the received pixels falls into a defined region related to a given chemical composition of the battery. Also, in one or more embodiments, the battery classification system 704 aligns a segmented 3D scan for the target battery (e.g., received from a 3D scanner 818) with the corresponding low and high energy scans received from the X-ray scanning array 820 to utilize the distribution and ratio of battery height to magnitude of X-ray attenuation when determining the chemical composition or category of the target battery. Thus, the battery classification system 704 described herein can store the inferred predictions and / or confidence levels in memory, or transmit such results directly to the classifier machine learning model 802 for further analysis, or to the battery sorting mechanism 828 to sort the target batteries according to the inferred predictions and / or confidence levels.

[0053] In one or more implementations, the battery classification system 704 receives X-ray attenuation values ​​806 from the X-ray scanning array 820, and uses these signals to determine the attributes of the target battery. For example, the battery classification system 704 determines the battery's chemical composition or material composition from the attenuation values ​​806. The classifier machine learning model 802 generates a battery classification 826 based at least part on the battery's chemical composition or material composition of the target battery.

[0054] More specifically, the battery classification system 704 receives X-ray attenuation values ​​806 in the form of high-energy attenuation values ​​and low-energy attenuation values ​​for the target battery. In one or more implementations, the battery classification system 704 generates an attenuation energy curve by plotting the high-energy attenuation value versus the low-energy attenuation value. The battery classification system 704 determines the battery chemical composition from the attenuation energy curve. For example, the battery classification system 704 stores known attenuation energy curves for different battery chemical compositions in a database 814. The battery classification system 704 maps the generated attenuation energy curve to the known attenuation energy curve to determine the battery chemical composition of the target battery.

[0055] In addition, the battery classification system 704 receives one or more images (e.g., signals) of the target batteries from the RGB camera 822. The battery classification system 704 generates one or more attributes from the one or more images. For example, the battery classification system 704 utilizes character recognition 808 and object recognition 810 to determine additional attributes of the target batteries. In one or more embodiments, for example, the RGB camera 822 includes one or more overhead cameras mounted / positioned to view each target battery from each of its sides (e.g., top, front, rear, side). The battery classification system 704 segments the batteries from the RGB images using a background subtraction technique, stores the segmented images in cache memory (e.g., a Redis cache with an in-memory key-value store for storing and retrieving images and data), and can utilize a camera driver to associate the placement and / or location of each battery with the stored image. Thus, the battery classification system 704 can access the segmented images from memory and perform object and / or character recognition on the associated batteries. For example, the battery classification system 704 determines the printed characters or codes on the label of the target battery. The classifier machine learning model 802 generates a battery classification 826 based on at least some of the printed characters or codes of the target battery.

[0056] In one or more implementations, the battery classification system 704 utilizes a classifier machine learning model 802 to compare words, letters, and other recognized data with different battery types in a database 814. In some embodiments, the classifier machine learning model 802 includes one or more deep learning models configured to perform object recognition to identify a specific manufacturer and / or model of each target battery.

[0057] Furthermore, in some embodiments, the battery classification system 704 receives one or more image frames from the RGB camera 822, segments each image frame to find one or more individual batteries within the frame, links image frames containing the same battery (e.g., using the shape or contour of the battery), performs character recognition 808 and / or object recognition 810, and associates the resulting object / character output with the battery ID and / or physical location of the battery (e.g., the xy position on the conveyor belt of the battery sorting device).

[0058] Furthermore, the classifier machine learning model 802 receives signals from the infrared camera 824 corresponding to the temperature 812 and / or thermal profile of the target battery. As described above, in some embodiments, the battery classification system 704 can activate one or more safety measures in response to detection via signals from the infrared camera 824, in response to the battery showing a high temperature (e.g., when it is determined that the temperature of the target battery has reached a threshold temperature) or other thermal anomaly. For example, in response to the detection of a thermal anomaly in the target battery, the battery classification system 704 can activate an alarm and / or fire extinguisher (or flame retardant), move the target battery to a dunk tank or other disposal location, shut down the battery sorting device, and / or notify / warn the user of the anomaly.

[0059] Therefore, as shown in Figure 8, the classifier machine learning model 802 determines the battery classification 826 of the target battery based on one or more of the dimensions 804, X-ray attenuation 806, character recognition 808, object recognition 810, or temperature 812 indicated by the signals received from the sensor 816. In some embodiments, for example, the classifier machine learning model 802 aggregates inferences generated from the signals of various sensors 816 (as described above) to produce the final battery classification. For example, in one or more implementations, the classifier machine learning model 802 utilizes a decision tree to generate the battery classification 826 based on the attributes of the target battery determined from the signals from the sensor 816. Alternatively, the classifier machine learning model 802 includes a classification neural network. In such an implementation, the classification neural network concatenates the values ​​of the attributes of the target battery. The classification neural network utilizes a first set of neural network layers (e.g., encoders) to generate a feature vector from the concatenated attribute values. A classification neural network utilizes a second set of neural network layers (e.g., decoders) to generate a battery classification 826 that forms a feature vector.

[0060] Furthermore, in one or more embodiments, if the classifier machine learning model 802 is unable to determine the battery classification within a threshold confidence level, the battery classification system 704 issues an error signal to the sorting mechanism 828. In such cases, for example, the sorting mechanism 828 may reroute the target battery for an iterative classification attempt, or replace the battery with a bin designated for batteries with an uncertain classification.

[0061] Furthermore, in some embodiments, the battery classification system 704 directs the battery classification 826 to a sorting mechanism 828 for sorting the target batteries. In one or more implementations, for example, the battery classification system 704 provides the location of the classified batteries, such as coordinates related to a conveyor belt, and the sorting mechanism 828 utilizes the transmitted location to inform the sorting actuator when moving the batteries into the corresponding sorting bin or, as described above, onto the corresponding additional conveyor. In some embodiments, the classifier machine learning model 802 includes a machine learning model trained to predict battery classification as described herein. Alternatively, some embodiments include a combination of a classical (e.g., mathematical) model and one or more machine learning models.

[0062] As described above, in one or more embodiments, the battery classification system 704 uses images from one or more RGB cameras as input for determining the battery classification of the target battery. For example, Figure 9 illustrates a battery classification system 704 that uses images from one or more RGB cameras 904 to determine the battery type inference 920 for the target battery 902.

[0063] For example, one or more RGB cameras 904 provide one or more images 908 of labels contained on the target battery 902, from which the classifier model 912 performs character recognition 914 (e.g., OCR) and compares the recognized characters with a database 918. For example, the characters recognized by character recognition 914 can be compared with characters in the database 918, or can be used to retrieve other relevant information that may be useful in determining the model number, serial number, and battery type inference 920 of the target battery 902.

[0064] Additionally or alternatively, one or more RGB cameras 904 provide one or more profile images 906 of the target battery 902, and one or more profile images 906 show or include shape factors 910 of the target battery 902. Accordingly, the classifier model 912 compares the visual attributes of the target battery 902 with data stored in the database 918 and utilizes an object detection machine learning model 916 to determine a battery type inference 920 for the target battery 902. Furthermore, the classifier model 912 may be trained to recognize known shape factors or other battery attributes based on the shape factors and attributes of the battery configuration found in the database 918.

[0065] For example, in one or more embodiments, the classifier model 912 comprises an object detection machine learning model 916 for classifying batteries in a digital image. In one or more embodiments, the object detection machine learning model 916 comprises a deep learning convolutional neural network (CNN). For example, in some embodiments, the object detection machine learning model 916 comprises a region-based (R-CNN). Specifically, the object detection machine learning model 916 comprises lower neural network layers and upper neural network layers. Generally, the lower neural network layers collectively form an encoder, and the upper neural network layers collectively form a decoder. In one or more embodiments, the encoder comprises a convolutional layer that encodes the digital image into feature vectors, which are output from the encoder and provided as input to the decoder. In various implementations, the decoder comprises a fully connected layer that analyzes the feature vectors and outputs a battery classification. In one or more implementations, the object detection machine learning model 916 gives a prediction that a battery in an image is one of several battery classifications. For example, the object detection machine learning model 916 generates a classification vector with predictions (e.g., numbers between 0 and 1) that indicate a predicted percentage (e.g., between 1 and 100%) that a battery in an image belongs to one of several battery classifications. Therefore, if there are 100 different battery classifications, the object detection machine learning model 916 can generate a classification vector with 100 entries. The classifier model 912 then selects the battery type inference 920 as the battery classification with the best predicted percentage.

[0066] As described above, some embodiments of the battery classification system 704 utilize an X-ray scanning array and / or a 3D scanner to determine one or more attributes of a target battery, such as battery chemical composition, in order to predict the battery classification. For example, Figure 10 shows a battery classification system 704 that utilizes input from a 3D scanner and an X-ray scanning array 1006 to determine a battery chemical composition inference 1018 for a target battery 1002.

[0067] For example, in the exemplary embodiment, the battery classification system 704 receives or infers dimensions 1008 from the 3D scanner 1004 and receives or infers high-energy attenuation 1010 and low-energy attenuation 1012 measured from the X-ray scanning array 1006. Accordingly, the battery classification system 704 utilizes the attenuation model 1016 of the classifier model 1014 to determine the battery chemical composition inference 1018. In one or more embodiments, the X-ray scanning array 1006 includes a differential X-ray scanning array consisting of multiple X-ray scanning arrays positioned at different angles or positions relative to the target battery 1002.

[0068] In one or more embodiments, the battery classification system 704 jointly processes signals from the X-ray scanning array 1006 and the 3D scanner 1004 for the target battery 1002 when determining the battery chemical composition inference 1018. Once the target battery 1002 is segmented, for example, the battery classification system 704 can utilize the images provided by the 3D scanner 1004 to determine the dimensions 1008, including the area, centroid, and / or one or more rectangular crops of the target battery 1002. In one or more embodiments, the battery classification system 704 utilizes the dimensions 1008 and signals from the X-ray scanning array 1006 to generate an array (e.g., a hash map) of the high-energy decay 1010, low-energy decay 1012, and the dimensions 1008 of the target battery 1002. In such embodiments, the battery classification system 704 can utilize the decay model 1016 of the classifier model 1014 to generate a battery chemical composition inference 1018 based on the arrangement of dimensions 1008, high-energy decay 1010, and low-energy decay 1012 for the target battery 1002.

[0069] Furthermore, as described above, embodiments of the battery classification system 704 determine the battery classification of a target battery by utilizing various signals from various sensors. For example, in some embodiments, the battery classification system 704 utilizes both the battery type inference 920 in Figure 9 and the battery chemical composition inference 1018 in Figure 10 to determine the battery classification of a target battery. In fact, embodiments of the battery classification system 704 can utilize any combination of data from various sensors in conjunction with the classifier model to predict the battery classification of a target battery.

[0070] Figures 1-10, their corresponding descriptions, and embodiments provide several different methods, systems, devices, and non-temporary computer-readable media of the battery classification system 704. In addition to the foregoing, one or more embodiments may also be described in relation to flowcharts involving actions to achieve a particular result, as shown in Figure 11. Figure 11 may be performed with more or fewer actions. Furthermore, the actions may be performed in a different order. In addition, the actions described herein may be repeated or performed in parallel with each other, or in parallel with different instances of the same or similar actions.

[0071] As described above, Figure 11 illustrates a flowchart of a series of operations 1100 for classifying and sorting batteries according to one or more embodiments. While Figure 11 illustrates operations according to one embodiment, alternative embodiments may omit, add, rearrange, and / or modify any of the operations shown in Figure 11. The operations in Figure 11 may be performed as part of a method. Alternatively, a non-temporary computer-readable medium may, when executed by one or more processors, provide instructions that cause one or more processors to perform the operations in Figure 11. In some embodiments, the system may perform the operations in Figure 11.

[0072] As shown, Figure 11 illustrates an example of a series of operations 1100 for classifying and sorting batteries according to multiple battery classifications. The series of operations 1100 may include operations 1102 for scanning the target battery using multiple sensors. For example, in some embodiments, operation 1102 includes receiving multiple signals from the multiple sensors corresponding to the target battery. In one or more embodiments, operation 1102 may include receiving multiple signals from the multiple sensors corresponding to one or more detected attributes of the target battery, where one or more detected attributes include one or more of the dimensions of the target battery, battery chemical composition, printed characters, or shape factors. Furthermore, in some embodiments, the multiple sensors include two or more of the following: X-ray scanning arrays, three-dimensional (3D) scanners, RGB cameras, or infrared cameras.

[0073] Furthermore, as shown in Figure 11, the sequence of operations 1100 may include an operation 1104 for determining the battery classification using a classifier machine learning model. For example, in some embodiments, operation 1104 includes using a classifier machine learning model to determine the predicted battery classification of a target battery from multiple battery classifications based on multiple signals. In one or more implementations, operation 1104 may include using a classifier machine learning model to determine the predicted battery classification of a target battery from multiple battery classifications based on one or more detected attributes of the target battery.

[0074] Furthermore, in some embodiments, operation 1104 may include determining the material attributes (e.g., battery chemical composition) of the target battery based on one or more X-ray attenuation measurements received from an X-ray scanning array for the target battery, and determining the predicted battery classification of the target battery based on the material attributes. For example, in some embodiments, operation 1104 may include receiving X-ray attenuation data for the target battery from an X-ray scanning array of multiple sensors, and determining the predicted battery classification of the target battery based on the X-ray attenuation data.

[0075] In one or more embodiments, operation 1104 may include determining the dimensions of the target battery based on scan data received from a three-dimensional (3D) scanner of the target battery, and determining the predicted battery classification of the target battery based on those dimensions. In connection with this, in one or more embodiments, operation 1104 may include receiving scan data about the target battery from three-dimensional (3D) scanners of multiple sensors, determining multiple dimensions of the target battery based on the scan data, and determining the predicted battery classification of the target battery based on the multiple dimensions.

[0076] In some embodiments, operation 1104 may include determining a plurality of printed characters or codes placed on the target battery based on image data received from an RGB camera for the target battery, and determining the predicted battery classification of the target battery based on the plurality of printed characters or codes. In connection with this, in some embodiments, operation 1104 may include receiving one or more label images from RGB cameras of multiple sensors, using optical character recognition (OCR) to identify a plurality of printed characters or codes from one or more label images, and determining the predicted battery classification of the target battery based on the plurality of printed characters or codes.

[0077] Furthermore, in one or more embodiments, operation 1104 includes receiving one or more label images and one or more profile images of the target battery from the RGB cameras of multiple sensors, using optical character recognition to determine the printed characters of the target battery from one or more label images, determining the shape factors of the target battery from one or more profile images, and using a classifier machine learning model to determine the predicted battery classification of the target battery based on the printed characters and shape factors. In some embodiments, operation 1104 may also include receiving one or more profile images of the target battery from the RGB cameras of multiple sensors, determining the shape factors of the target battery based on one or more profile images of the target battery, and determining the predicted battery classification of the target battery based on the shape factors.

[0078] Furthermore, in some embodiments, operation 1104 may include determining the dimensions of the target battery based on scanning data from 3D scanners of multiple sensors, determining the battery chemical composition of the target battery based on X-ray attenuation data from X-ray scanning arrays of multiple sensors, and determining the predicted battery classification of the target battery based on the dimensions and battery chemical composition using a classifier machine learning model.

[0079] As shown in Figure 11, the sequence of operations 1100 may include an operation 1106 for indicating the battery classification to the battery sorting mechanism. For example, in some embodiments, operation 1106 includes indicating the predicted battery classification to the battery sorting mechanism. In some embodiments, operation 1106 also includes using the battery sorting mechanism to transfer the target battery to the bin corresponding to the predicted battery classification of the target battery.

[0080] In some embodiments, operation 1106 may also include indicating to the battery sorting mechanism the predicted battery classification of the target battery and the additional predicted battery classification of the additional batteries, and using the battery sorting mechanism to individually transfer each of the target battery and the additional batteries to a plurality of bins, each associated with a plurality of battery classifications.

[0081] Furthermore, in one or more embodiments, the sequence of operations 1100 may include receiving additional signals from multiple sensors corresponding to additional batteries, and using a classifier machine learning model to determine the additional predicted battery classification of the additional batteries from multiple battery classifications based on the additional signals. Also, in some embodiments, the sequence of operations 1100 may include using a battery sorting mechanism to transfer the target batteries to a first bin corresponding to the predicted battery classification of the target batteries, determining the predicted battery classification of the additional target batteries based on additional signals from multiple sensors, and using the battery sorting mechanism to transfer the additional target batteries to a second bin corresponding to the predicted battery classification of the additional target batteries.

[0082] Furthermore, in some embodiments, the sequence of operations 1100 may include determining the temperature or temperature gradient of the target battery from signals received from an infrared camera for that battery, and activating an alarm if it is determined that the temperature or temperature gradient exceeds a threshold. In addition, in one or more embodiments, the sequence of operations 1100 may include receiving an indication of a dangerous anomaly detected in at least one of the additional batteries from an infrared camera among a plurality of sensors, and, accordingly, transferring at least one battery to a dunk tank containing a flame retardant.

[0083] Embodiments of the present disclosure may include or utilize a dedicated or general-purpose computer, for example, one or more processors and system memory, among other computer hardware, as will be described in more detail below. Embodiments within the scope of the present disclosure also include physical and other computer-readable media for carrying or storing computer-executable instructions and / or data structures. In particular, one or more of the processes described herein may be implemented, at least in part, as instructions that are embodied in a non-temporary computer-readable medium and are executable by one or more computer devices (e.g., any of the media content access devices described herein). Generally, a processor (e.g., a microprocessor) receives instructions from a non-temporary computer-readable medium (e.g., memory), executes those instructions, and thereby executes one or more processes, including one or more of the processes described herein.

[0084] A computer-readable medium can be any available medium accessible by a general-purpose or dedicated computer system. A computer-readable medium that stores computer-executable instructions is a non-temporary computer-readable storage medium. A computer-readable medium that carries computer-executable instructions is a transmission medium. Thus, embodiments of the disclosure may comprise at least two distinctly different types of computer-readable mediums, namely, a non-temporary computer-readable storage medium (device) and a transmission medium.

[0085] Non-temporary computer-readable storage media (devices) include RAM, ROM, EEPROM, CD-ROM, solid-state drives ("SSDs") (e.g., RAM-based), flash memory, phase-change memory ("PCM"), other types of memory, other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, or other media that can be used to store desired program code means in the form of computer-executable instructions or data structures and are accessible by general-purpose or special-purpose computers.

[0086] A “network” is defined as one or more data links that enable the transmission of electronic data between computer systems and / or modules and / or other electronic devices. When information is transferred to or provided to a computer via a network or another communication connection (wired, wireless, or a combination of wired and wireless), the computer appropriately recognizes that connection as a transmission medium. A transmission medium can include networks and / or data links that can be used to carry desired program code means in the formation of computer executable instructions or data structures and can be accessed by general-purpose or special-purpose computers. It is desirable to include the above combinations within the scope of computer-readable media.

[0087] Furthermore, upon reaching various computer system components, program code means in the form of computer-executable instructions or data structures are automatically (or vice versa) transferred from the transmission medium to a non-temporary computer-readable storage medium (device). For example, computer-executable instructions or data structures received via a network or data link can be buffered in RAM within a network interface module (e.g., a "network interface card") and ultimately transferred to computer system RAM and / or a less volatile computer storage medium (device) within the computer system. Thus, it should be understood that non-temporary computer-readable storage mediums (devices) can be included in computer system components that similarly (or primarily) utilize the transmission medium.

[0088] Computer executable instructions include, for example, instructions and data that, when executed by a processor, cause a function or group of functions located in a general-purpose computer, a special-purpose computer, or a special-purpose processing unit. In some embodiments, computer executable instructions are executed by a general-purpose computer to transform that general-purpose computer into a special-purpose computer that implements elements of the disclosure. Computer executable instructions can be, for example, binaries, intermediate format instructions such as assembly language, or even source code. While the subject matter has been described in language specific to structural features and / or methodological behaviors, it should be understood that the subject matter as defined in the appended claims is not necessarily limited to the features or behaviors described above. Rather, the features and behaviors described are disclosed as exemplary forms of implementing the claims.

[0089] Those skilled in the art will understand that the present invention can be implemented in network computing environments having many types of computer system configurations, including personal computers, desktop computers, laptop computers, message processors, handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, mobile phones, PDAs, tablets, pagers, routers, switches, and the like. The disclosure can also be implemented in a distributed system environment in which local and remote computer systems linked over a network (by hardwired data links, wireless data links, or a combination of hardwired and wireless data links) perform tasks. In a distributed system environment, program modules may be located in both local and remote memory storage devices.

[0090] Embodiments of this disclosure may also be implemented in a cloud computing environment. As used herein, the term “cloud computing” refers to a model for enabling on-demand network access to a shared pool of configurable computing resources. For example, cloud computing may be used in the market to provide ubiquitous and convenient on-demand access to a shared pool of configurable computing resources. A shared pool of configurable computing resources can be rapidly provisioned through virtualization, released with low administrative effort or interaction with a service provider, and scaled accordingly.

[0091] A cloud computing model can comprise various characteristics, such as on-demand self-service, broad network access, resource pooling, rapid scalability, and measurable services. A cloud computing model can also expose various service models, including Software as a Service ("SaaS"), Platform as a Service ("PaaS"), and Infrastructure as a Service ("LaaS"). A cloud computing model can also be deployed using different deployment models, such as private clouds, community clouds, public clouds, and hybrid clouds. Furthermore, in this specification, "cloud computing environment" refers to the environment in which cloud computing is used.

[0092] Figure 12 illustrates a block diagram of an exemplary computer device 1200 that may be configured to perform one or more of the processes described above. It should be understood that one or more computer devices, such as computer device 1200, may represent the computer devices described above (e.g., computer device 702). In one or more embodiments, computer device 1200 may be a mobile device (e.g., a mobile phone, smartphone, PDA, tablet, laptop, camera, tracker, watch, wearable device, etc.). In some embodiments, computer device 1200 may be a non-mobile device (e.g., a desktop computer or another type of client device). Furthermore, computer device 1200 may be a server device that includes cloud-based processing and storage functions (e.g., a local server that processes custom TCP or HTTP messages).

[0093] As shown in Figure 12, the computer device 1200 may include one or more processors 1202, memory 1204, storage device 1206, input / output interface 1208 (or "VO interface 1208"), and communication interface 1210 which can be communicatively coupled via a communication infrastructure (e.g., bus 1212). Although the computer device 1200 is shown in Figure 12, the components shown in Figure 12 are not intended to be limiting. Additional or alternative components may be used in other embodiments. Furthermore, in some embodiments, the computer device 1200 includes fewer components than those shown in Figure 12. The components of the computer device 1200 shown in Figure 12 will now be described in more detail.

[0094] In certain embodiments, the processor 1202 includes hardware for executing instructions, such as instructions that constitute a computer program. As an example, and not as a limitation, to execute instructions, the processor 1202 may search (or fetch) instructions from internal registers, internal cache, memory 1204, or storage device 1206, decode them, and execute them.

[0095] The computer device 1200 includes memory 1204 coupled to the processor 1202. Memory 1204 may be used to store data, metadata, and programs for execution by the processor. Memory 1204 may include one or more volatile and non-volatile memories, such as random access memory, read-only memory, solid-state hard disk, flash, phase-change memory, and other types of data storage devices. Memory 1204 may be internal or distributed memory.

[0096] Computer device 1200 includes a storage device 1206, which stores data or instructions. For example, but not limited to, the storage device 1206 may include the non-temporary storage media described above. The storage device 1206 may include a hard disk drive, flash memory, a universal serial bus drive, or a combination of these or other storage devices.

[0097] In some embodiments, the data storage within the storage device 1206 may include a remote dictionary server (Redis) data structure with an in-memory key-value database for storing and indexing data cached throughout the battery classification and sorting processes described herein. In one embodiment, for example, each sensor array of a plurality of sensor arrays (e.g., RGB cameras, 3D scanners, X-ray scanning arrays) stores images and / or associated information having time-dependent key values ​​(e.g., "rgb:390:8910") representing the x and y coordinates of their respective images. Thus, when the battery classification system 704 aggregates sensor signals to determine the battery classification of a target battery, it can associate information from each sensor array pipeline with its respective physical coordinates. Alternatively, or additionally, the battery classification system 704 may store a sorted list of coordinates for each image, so that all images within a given range of coordinates are readily accessible when filtering for signals corresponding to the target battery.

[0098] As shown, the computer device 1200 includes one or more I / O interfaces 1208, which are provided to allow the user to provide input (such as user strokes), receive output from the computer device 1200, and transfer data in other ways. These I / O interfaces 1208 may include a mouse, keypad or keyboard, touchscreen, camera, optical scanner, network interface, modem, other known I / O devices, or a combination of such I / O interfaces 1208. The touchscreen may be operated with a stylus or a finger.

[0099] The I / O interface 1208 may include, but is not limited to, a graphics engine, a display (e.g., a display screen), one or more output drivers (e.g., display drivers), one or more audio speakers, and one or more audio drivers, one or more devices for presenting output to the user. In one embodiment, the input / output interface 1208 is configured to provide graphical data to a display for presentation to the user. The graphical data may include one or more graphical user interfaces and / or any other graphical content that may serve a specific role in the implementation.

[0100] The computer device 1200 may further include a communication interface 1210. The communication interface 1210 may include hardware, software, or both. The communication interface 1210 provides one or more interfaces for communication (e.g., packet-based communication) between the computing device and one or more other computing devices or one or more networks. As an example, but not limited to, the communication interface 1210 may include Ethernet, other wired-based networks, or a network interface controller (NIC) or network adapter for communicating with wireless networks such as Wi-Fi, or wireless adapters for communicating with wireless networks such as Wi-Fi. The computer device 1200 may further include a bus 1212. The bus 1212 may include hardware, software, or both for connecting the components of the computer device 1200 to each other.

[0101] In the above-described specification, the present invention is described with reference to specific example embodiments. Various embodiments and aspects of the present invention are described with reference to the details discussed herein, and the accompanying drawings illustrate various embodiments. The above description and drawings are illustrative of the present invention and should not be construed as limiting the present invention. Numerous specific details are described in order to provide a complete understanding of the various embodiments of the present invention.

[0102] The present invention can be embodied in other specific forms without departing from the spirit and basic features of the invention. The embodiments described herein should be considered in all respects to be illustrative and not limiting. For example, the methods described herein may be performed in fewer or more steps / operations, or the steps / operations may be performed in a different order. In addition, the steps / operations described herein may be repeated or performed in parallel or in parallel with each other for different instances of the same or similar steps / operations. Accordingly, the scope of the invention is indicated not by the foregoing description but by the appended claims. All modifications that fall within the meaning and scope of the equivalents of the claims should be encompassed within those scopes.

Claims

1. A device for sorting batteries, A feeding mechanism configured to discharge multiple batteries individually onto a conveyor, A scanner mechanism arranged around the conveyor, comprising a plurality of types of sensors configured to acquire one or more attributes of each of the plurality of batteries, An apparatus comprising: an array of sorting mechanisms arranged around the conveyor and configured to transfer the plurality of batteries from the conveyor to a plurality of bins based on the predicted battery configuration of each of the plurality of batteries determined based on one or more attributes of each battery.

2. The apparatus according to claim 1, wherein the feeding mechanism comprises a hopper positioned above the conveyor and configured to guide the individual batteries of the plurality of batteries onto the conveyor.

3. The apparatus according to claim 1, further comprising one or more scanning bays configured to receive individual batteries from the plurality of batteries scanned by the plurality of types of sensors via the conveyor.

4. The apparatus according to claim 1, wherein the plurality of types of sensors comprises two or more of the following: X-ray scanning arrays, three-dimensional (3D) scanners, RGB cameras, or infrared cameras.

5. The apparatus according to claim 1, further comprising one or more processors configured to determine the predicted battery configuration for each battery based on sensor data from one or more sensors among the plurality of types of sensors.

6. The apparatus according to claim 1, further comprising a return mechanism positioned at the end of the conveyor and configured to return unsorted batteries to the starting point of the conveyor.

7. The apparatus according to claim 1, further comprising a safety mechanism including one or more of an alarm, a fire extinguisher, a battery dunk tank, or an emergency power off (EPO), wherein the safety mechanism is configured to be activated in response to a signal from at least one of the plurality of types of sensors.

8. A device for classifying batteries, One or more scan bays configured to receive batteries with multiple battery configurations, One or more scanner mechanisms associated with one or more scanning bays, each comprising a sensor configured to scan each battery as each battery passes through the one or more scanning bays, An apparatus comprising: one or more processors configured to determine a predicted battery configuration for each battery based on sensor data from sensors of one or more scanner mechanisms.

9. The apparatus according to claim 8, further comprising a hopper mechanism configured to discharge the batteries individually onto a conveyor.

10. The apparatus according to claim 9, wherein one or more scanning bays are arranged around the conveyor to receive batteries discharged individually by the hopper mechanism.

11. The apparatus according to claim 10, further comprising, downstream of one or more scanning bays, an array of sorting mechanisms arranged around the conveyor, wherein the array of sorting mechanisms is configured to transfer each battery from the conveyor to each of the bins of a plurality of bins based on the predicted battery configuration for each battery.

12. The apparatus according to claim 8, wherein one or more scanner mechanisms comprises an X-ray scanning array configured to determine the material attributes of each battery.

13. The apparatus according to claim 8, wherein the one or more scanner mechanisms comprises at least one of a three-dimensional (3D) scanner or an RGB camera configured to determine the dimensions of each battery.

14. The apparatus according to claim 8, wherein one or more processors are configured to determine the predicted battery configuration for each battery by utilizing a machine learning model that processes the sensor data from the sensors of the one or more scanner mechanisms.

15. A device for sorting batteries of various configurations, A feeding mechanism configured to discharge multiple batteries individually onto a conveyor, One or more scanner mechanisms, wherein each of the one or more scanner mechanisms is configured to scan each battery as each battery passes over the conveyor, The apparatus comprises one or more sorting mechanisms positioned around the conveyor and configured to transfer the batteries of the plurality of batteries from the conveyor to a plurality of bins based on the predicted battery configuration of each battery determined based on the attributes of each battery acquired using the one or more scanner mechanisms.

16. The apparatus according to claim 15, wherein one or more scanner mechanisms comprises an X-ray scanning array comprising an X-ray generator positioned above the conveyor and an X-ray detector positioned below the conveyor.

17. The apparatus according to claim 15, wherein the one or more scanner mechanisms comprises two or more of the following: an X-ray scanning array, a three-dimensional (3D) scanner, an RGB camera, or an infrared camera.

18. The apparatus according to claim 15, further comprising a return mechanism after one or more scanner mechanisms, wherein the return mechanism is configured to return a battery for which an accurate predicted battery configuration cannot be determined to the one or more scanner mechanisms.

19. The apparatus according to claim 15, wherein one or more sorting mechanisms comprises one or more actuators configured to push, pull, or guide batteries into each of the plurality of bins.

20. The apparatus according to claim 15, further comprising a safety mechanism configured to be activated in response to the detection of a dangerous abnormality in the batteries of the plurality of batteries.

21. A method that is performed on a computer, Receiving multiple signals corresponding to the target battery from multiple sensors, Using a classifier machine learning model, determine the predicted battery classification of the target battery from multiple battery classifications based on the multiple signals, and A method comprising indicating the predicted battery classification of the target battery in a battery sorting mechanism.

22. A method performed on a computer according to claim 21, wherein the plurality of sensors comprises two or more of the following: an X-ray scanning array, a three-dimensional (3D) scanner, an RGB camera, or an infrared camera.

23. A method performed on a computer according to claim 21, The method further comprises determining the material attributes of the target battery based on one or more X-ray attenuation measurement results received from an X-ray scanning array for the target battery, A method comprising: determining the predicted battery classification of the target battery from the plurality of battery classifications based on the plurality of signals using the classifier machine learning model, and determining the predicted battery classification of the target battery based on at least a portion of the material attributes.

24. A method performed on a computer according to claim 23, comprising obtaining a first set of X-ray attenuation measurement results using a first X-ray scanning array oriented in a first orientation with respect to the target battery, and The method further comprises obtaining a second set of X-ray attenuation measurement results using a second X-ray scanning array oriented in a second orientation relative to the target battery, A method for determining the material attributes of the target battery based on one or more X-ray attenuation measurement results, comprising determining the material attributes based on the first set of X-ray attenuation measurement results and the second set of X-ray attenuation measurement results.

25. A method performed on a computer according to claim 21, The process further comprises determining the dimensions of the target battery based on scanning data received from a three-dimensional (3D) scanner for the target battery, A method comprising: determining the predicted battery classification of the target battery from the plurality of battery classifications based on the plurality of signals using the classifier machine learning model, and determining the predicted battery classification of the target battery based on at least a portion of the dimensions.

26. A method performed on a computer according to claim 21, The system further comprises determining a plurality of printed characters or codes placed on the target battery based on image data of the target battery received from one or more RGB cameras, A method comprising determining the predicted battery classification of a target battery from a plurality of battery classifications based on a plurality of signals using the classifier machine learning model, and determining the predicted battery classification of a target battery based on at least a portion of a plurality of printed characters or codes.

27. A method performed on a computer according to claim 21, From the signal received from the infrared camera regarding the target battery, the temperature or temperature gradient of the target battery is determined, and A method further comprising activating an alarm or transferring the target battery to a safety bin in response to a determination that the temperature or temperature gradient exceeds a threshold.

28. A method performed on a computer according to claim 21, comprising: using a classifier machine learning model to determine the predicted battery classification of a target battery from a plurality of battery classifications based on a plurality of signals; and using an object detection neural network to determine the predicted battery classification from one or more images of the target battery.

29. It is a system, A classifier machine learning model and one or more memory devices with multiple battery classifications, Determining one or more attributes of a target battery from multiple signals from multiple sensors, wherein the one or more attributes include one or more of the dimensions of the target battery, the battery's chemical composition, printed characters, or shape factors, and A system comprising: one or more processors configured to cause the system to perform an operation which includes using the classifier machine learning model to determine the predicted battery classification of the target battery from the plurality of battery classifications based on one or more attributes of the target battery that have been determined.

30. The system according to claim 29, wherein the operation further comprises: The battery sorting mechanism indicates the predicted battery classification of the target battery, and A system comprising using the battery sorting mechanism to transfer the target battery to a bin corresponding to the predicted battery classification of the target battery.

31. The system according to claim 29, The operation further includes receiving one or more label images and one or more profile images of the target battery from the RGB cameras of the plurality of sensors, Determining one or more attributes of the aforementioned target battery is: Using optical character recognition, determine the printed characters of the target battery from one or more label images, and The method includes determining the shape factor of the target battery from one or more profile images, The system uses the aforementioned classifier machine learning model to determine the predicted battery classification of the target battery, based on the printed characters and shape factors.

32. The system according to claim 29, Determining one or more attributes of the aforementioned target battery is: Based on the scanning data from the 3D scanners of the multiple sensors, one or more dimensions of the target battery are determined, and The system includes determining the battery chemical components of the target battery based on X-ray attenuation data from the X-ray scanning array of the plurality of sensors, A system that uses the aforementioned classifier machine learning model to determine the predicted battery classification of the target battery, based on one or more dimensions and battery chemical composition of the target battery.

33. The system according to claim 29, wherein the operation further comprises: Receiving additional signals corresponding to additional batteries from the aforementioned multiple sensors, and A system comprising using the classifier machine learning model to determine an additional predicted battery classification of the additional battery from the plurality of battery classifications based on the additional signal.

34. The system according to claim 33, wherein the operation further comprises: The battery sorting mechanism indicates the predicted battery classification of the target battery and the additional predicted battery classification of the additional battery, and A system comprising using the battery sorting mechanism to individually transfer each of the target batteries and the additional batteries to a plurality of bins associated with the plurality of battery classifications.

35. The system according to claim 33, wherein the operation further comprises: Based on signals from the infrared cameras of the plurality of sensors, a dangerous abnormality is determined in at least one of the batteries of the additional battery, and Accordingly, the system comprises transferring the at least one battery into a dunk tank containing a flame retardant.

36. When executed by at least one processor, at least one processor, Receiving multiple signals corresponding to the target battery from multiple sensors, Using a classifier machine learning model, determine the predicted battery classification of the target battery from multiple battery classifications based on the multiple signals, and A non-temporary computer-readable medium that stores executable instructions for causing a battery sorting mechanism to perform an operation comprising indicating the predicted battery classification of the target battery.

37. A non-temporary computer-readable medium according to claim 36, wherein the operation further comprises: To acquire one or more labeled images using the RGB camera among the multiple sensors, and A non-temporary computer-readable medium comprising identifying multiple printed characters or codes from one or more label images using optical character recognition (OCR).

38. A non-temporary computer-readable medium according to claim 37, wherein the operation further comprises: To acquire one or more profile images of the target battery using one or more RGB cameras among the plurality of sensors, and A non-temporary computer-readable medium comprising determining the shape factors of the target battery based on one or more profile images of the target battery.

39. A non-temporary computer-readable medium according to claim 38, wherein the operation further comprises acquiring X-ray attenuation data for the target battery using the X-ray scanning array of the plurality of sensors.

40. A non-temporary computer-readable medium according to claim 39, wherein determining the predicted battery classification of the target battery based on the plurality of signals using the classifier machine learning model, or using a decision tree to determine the predicted battery classification based on the X-ray attenuation data, the shape factor of the target battery, and the plurality of printed characters or codes from one or more label images.

Images