Classifications

• • B—PERFORMING OPERATIONS; TRANSPORTING
  • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
  • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
  • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
  • B07C5/36—Sorting apparatus characterised by the means used for distribution
• • B—PERFORMING OPERATIONS; TRANSPORTING
  • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
  • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
  • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
  • B07C5/34—Sorting according to other particular properties
  • B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
  • B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras

Definitions

• the present disclosure relates in general to the sorting of materials, and in particular, to the sorting of certain valuables from scrap.
• Recycling is the process of collecting and processing materials that would otherwise be thrown away as trash, and turning them into new products. Recycling has benefits for communities and for the environment, since it reduces the amount of waste sent to landfills and incinerators, conserves natural resources, increases economic security by tapping a domestic source of materials, prevents pollution by reducing the need to collect new raw materials, and saves energy. After collection, recyclables are generally sent to a material recovery facility to be sorted, cleaned, and processed into materials that can be used in manufacturing.
• PCBs printed circuit boards
• valuable metals e.g., copper, gold, silver, etc.
• FIG. 1 illustrates a schematic of a sorting system configured in accordance with embodiments of the present disclosure.
• FIG. 2 illustrates a flowchart diagram of an operation of a sorting device configured in accordance with embodiments of the present disclosure.
• FIG. 3 A shows a visual image of various exemplary monetary coins.
• FIG. 3B shows a visual image of exemplary monetary coins mixed with other scrap pieces.
• FIG. 3C shows a visual image of various exemplary pieces of jewelry.
• FIG. 3D shows a visual image of exemplary pieces of jewelry mixed with other scrap pieces.
• FIG. 4 illustrates a flowchart diagram configured in accordance with embodiments of the present disclosure.
• FIG. 5 illustrates a block diagram of a data processing system configured in accordance with embodiments of the present disclosure.
• FIG. 6 illustrates a flowchart diagram of exemplary configurations for a machine learning system in accordance with embodiments of the present disclosure.
• Embodiments of the present disclosure effectively recycle specified valuable scrap pieces (e.g., monetary coins, jewelry, PCBs, copper, brass, etc.) from shredded scrap (e.g., automobile (automotive) scrap) by utilizing a machine learning based vision system as described herein.
• specified valuable scrap pieces e.g., monetary coins, jewelry, PCBs, copper, brass, etc.
• a“material” may include any physical item, including but not limited to a scrap piece.
• Classes or types of materials may include metals (ferrous and nonferrous), metal alloys, monetary coins, jewelry (e.g., rings, earrings, necklaces, bracelets, etc.), pieces of gold or silver, buttons, electrical box knockouts, washers, plastics (including, but not limited to PCB, HDPE, UHMWPE, and various colored plastics), rubber, foam, glass (including, but not limited to borosilicate or soda lime glass, and various colored glass), ceramics, paper, cardboard, Teflon, PE, bundled wires, insulation covered wires, rare earth elements, etc.
• the terms “scrap” and“scrap pieces” refer to material pieces in a solid state. Within this disclosure, the terms“scrap,”“scrap pieces,”“materials,” and“material pieces” may be used interchangeably.
• a heterogeneous mixture of materials means a collection of different individual classes or types of materials.
• a homogeneous set of materials means a collection of individual materials of a same or substantially similar class or type.
• Zorba is the collective term for shredded nonferrous metals, including, but not limited to, those originating from end-of-life vehicles (“ELVs”) or waste electronic and electrical equipment (“WEEE”).
• EUVs end-of-life vehicles
• WEEE waste electronic and electrical equipment
• ISRI Institute Of Scrap Recycling Industries, Inc.
• each scrap piece may be made up of a combination of the nonferrous metals (e.g., aluminum, copper, lead, magnesium, stainless steel, nickel, tin, and zinc, in elemental or alloyed (solid) form).
• the term“Twitch” shall mean fragmented aluminum scrap. Twitch may be produced by a float process whereby the aluminum scrap floats to the top because heavier metal scrap pieces sink (for example, in some process, sand may be mixed in to change the density of the water in which the scrap is immersed).
• a vision system may be configured (e.g., with a machine learning system) to collect any type of information that can be utilized within a sorting system to selectively sort materials (e.g., scrap pieces) as a function of a set of one or more (user-defined) physical characteristics, including, but not limited to, color, size, shape, texture, physical appearance, uniformity, hue, and/or manufacturing type, of the materials. It should be noted that at least some of the materials to be sorted may have irregular sizes and shapes (e.g., see FIGS.
• such material e.g., Zorba and/or Twitch
• some sort of shredding mechanism that chops up the materials into such irregularly shaped and sized pieces (producing scrap pieces), which may then be fed onto a conveyor system.
• Embodiments of the present disclosure will be described herein as sorting materials (e.g., scrap pieces) into such separate groups by physically depositing (e.g., ejecting) the materials (e.g., scrap pieces) into separate receptacles or bins as a function of user-defined classifications.
• materials e.g., scrap pieces
• materials may be sorted into separate bins in order to separate specified valuable scrap pieces from other scrap materials.
• Such specified (by the user of the system 100) valuable scrap pieces may be monetary coins, jewelry (e.g., rings, earrings, necklaces, bracelets, etc.), precious metals (e.g., gold, silver, platinum, copper, brass, etc.), or PCBs (which can contain valuable metals (e.g., gold, silver, copper).
• jewelry e.g., rings, earrings, necklaces, bracelets, etc.
• precious metals e.g., gold, silver, platinum, copper, brass, etc.
• PCBs which can contain valuable metals (e.g., gold, silver, copper).
• FIG. 1 illustrates an example of an automated material sorting system 100 configured in accordance with various embodiments of the present disclosure to automatically (i.e., does not require human manual intervention) sort materials.
• a conveyor system 103 may be implemented to convey one or more streams of individual scrap pieces 101 through the sorting system 100 so that each of the individual scrap pieces 101 can be tracked, classified, and sorted into predetermined desired groups.
• Such a conveyor system 103 may be implemented with one or more conveyor belts on which the scrap pieces 101 travel, typically at a predetermined constant speed.
• conveyor system 103 will simply be referred to as the conveyor belt 103.
• FIG. 1 depicts a single stream of scrap pieces 101 on a conveyor belt 103
• embodiments of the present disclosure may be implemented in which a plurality of such streams of scrap pieces are passing by the various components of the sorting system 100 in parallel with each other, or a collection of scrap pieces deposited in a random manner onto the conveyor belt 103 are passed by the various components of the sorting system
• certain embodiments of the present disclosure are capable of simultaneously tracking, classifying, and sorting a plurality of such parallel travelling streams of scrap pieces, or scrap pieces randomly deposited onto a conveyor belt.
• singulation of the scrap pieces 101 is not required for the vision system to track, classify, and sort the scrap pieces.
• some sort of suitable feeder mechanism may be utilized to feed the scrap pieces 101 onto the conveyor belt 103, whereby the conveyor belt 103 conveys the scrap pieces 101 past various components within the sorting system 100.
• the conveyor belt 103 is operated to travel at a predetermined speed by a conveyor belt motor 104. This predetermined speed may be programmable and/or adjustable by the operator in any well-known manner. Monitoring of the predetermined speed of the conveyor belt 103 may alternatively be performed with a belt speed detector 105.
• control of the conveyor belt motor 104 and/or the belt speed detector 105 may be performed by an automation control system 108.
• Such an automation control system 108 may be operated under the control of a computer system 107 and/or the functions for performing the automation control may be implemented in software within the computer system 107.
• the conveyor belt 103 may be a conventional endless belt conveyor employing a conventional drive motor 104 suitable to move the conveyor belt 103 at the predetermined speeds.
• a belt speed detector 105 which may be a conventional encoder, may be operatively coupled to the conveyor belt 103 and the automation control system 108 to provide information corresponding to the movement (e.g., speed) of the conveyor belt 103.
• the automation control system 108 is able to track the location of each of the scrap pieces 101 while they travel along the conveyor belt 103.
• a tumbler and/or a vibrator may be utilized to separate the individual scrap pieces from a collection of scrap pieces.
• the scrap pieces may be positioned into one or more singulated (i.e., single file) streams, which may be performed by an optional active or passive singulator 106.
• singulated i.e., single file
• the conveyor system e.g., the conveyor belt 103 may simply convey a collection of scrap pieces, which have been positioned on the conveyor belt 103 in a random manner.
• embodiments of the present disclosure may utilize a vision, or optical recognition, system 110 as a means to begin tracking each of the scrap pieces 101 as they travel on the conveyor belt 103.
• the vision system 110 may utilize one or more still or live action cameras 109 (which may include one or more three-dimensional cameras) to note the position (i.e., location and timing) of each of the scrap pieces 101 on the moving conveyor belt 103.
• the vision system 110 may be further configured to perform certain types of identification (e.g., classification) of all or a portion of the scrap pieces 101. For example, such a vision system 110 may be utilized to acquire information about each of the scrap pieces 101.
• the vision system 110 may be configured (e.g., with a machine learning system) to collect any type of information that can be utilized within the system 100 to selectively sort the scrap pieces 101 as a function of a set of one or more (user-defined) physical characteristics, including, but not limited to, color, size, shape, texture, overall physical appearance, uniformity, composition, and/or manufacturing type of the scrap pieces 101.
• the vision system 110 captures images of each of the scrap pieces 101, for example, by using an optical sensor as utilized in typical digital cameras and video equipment. Such images captured by the optical sensor may then be stored in a memory device as image data.
• such image data represents images captured within optical wavelengths of light (i.e., the wavelengths of light that are observable by the typical human eye).
• optical sensors that are configured to capture an image of a material made up of wavelengths of light outside of the visual wavelengths of the typical human eye.
• Such a vision system 110 may be configured to identify which of the scrap pieces 101 are not of the kind to be sorted by the sorting system 100 (e.g., scrap pieces classified as other than specified valuable scrap pieces), and send a signal to reject such scrap pieces.
• Such identified scrap pieces 101 may be ejected utilizing one of the mechanisms as described herein for physically moving sorted scrap pieces into individual bins.
• FIG. 2 there is illustrated a system and process 200 for activation of each one of the automatic sorting devices (e.g., the sorting devices 126, 127, 128, 129) for ejecting a classified scrap piece into a sorting bin.
• a system and process 200 may be implemented within the automation control system 108 previously described with respect to FIG. 1, or within an overall computer system (e.g., the computer system 107) controlling the sorting system.
• a signal is received from the automation control system 108 that a specified and tracked scrap piece is in position for sorting.
• a determination is made whether the timing associated with this signal is equal to the current time.
• the system and process 200 determines whether the timing associated with the classified scrap piece corresponds to the expected time in which the classified scrap piece is passing within the proximity of the particular sorting device (e.g., air jet, pneumatic plunger, paint brush type plunger, etc.) associated with the classification pertaining to the classified scrap piece. If the timing signals do not correspond, a determination is made in the process block 203 whether the signal is greater than the current time. If YES, the system may return an error signal 204. In such an instance, the system may not be able to eject the piece into the appropriate bin.
• the particular sorting device e.g., air jet, pneumatic plunger, paint brush type plunger, etc.
• the system and process 200 determines that a classified scrap piece is passing within the vicinity of a sorting device associated with that classification, it will activate that sorting device in the process block 205 in order to eject the classified scrap piece into the sorting bin associated with that classification. This may be performed by activating a pneumatic plunger, paint brush type plunger, air jet, etc. In the process block 206, the selected sorting device is then deactivated.
• the sorting devices may include any well-known mechanisms for redirecting selected scrap pieces towards a desired location, including, but not limited to, ejecting the scrap pieces from the conveyor belt system into the plurality of sorting bins.
• a sorting device may utilize air jets, with each of the air jets assigned to one or more of the classifications.
• one of the air jets e.g., 127) receives a signal from the automation control system 108, that air jet emits a stream of air that causes a scrap piece 101 to be ejected from the conveyor belt 103 into a sorting bin (e.g., 137) corresponding to that air jet.
• High speed air valves e.g., commercially available from Mac Industries
• FIG. 1 uses air jets to eject scrap pieces
• other mechanisms may be used to eject the scrap pieces, such as robotically removing the scrap pieces from the conveyor belt, pushing the scrap pieces from the conveyor belt (e.g., with paint brush type plungers), causing an opening (e.g., a trap door) in the conveyor belt from which a scrap piece may drop, using one or more air jets to separate the scrap pieces into separate bins as they fall from the edge of the conveyor belt, or using robotic arms and grapples to pick specified scrap pieces from the conveyor belt 103.
• robotically removing the scrap pieces from the conveyor belt e.g., pushing the scrap pieces from the conveyor belt (e.g., with paint brush type plungers), causing an opening (e.g., a trap door) in the conveyor belt from which a scrap piece may drop
• using one or more air jets to separate the scrap pieces into separate bins as they fall from the edge of the conveyor belt, or using robotic arms and grapples to pick specified scrap pieces from the conveyor belt
• the system 100 may also include a receptacle or bin 140 that receives scrap pieces 101 not ejected from the conveyor belt 103 into any of the aforementioned sorting bins 136, 137, 138, 139.
• a scrap piece 101 may not be ejected from the conveyor belt 103 into one of the N sorting bins 136, 137, 138, 139 when the classification of the scrap piece 101 is not determined (or simply because the sorting devices failed to adequately eject a piece).
• the bin 140 may serve as a default receptacle into which unclassified scrap pieces are dumped.
• the bin 140 may be used to receive one or more classifications of scrap pieces that have deliberately not been assigned to any of the N sorting bins 136, 137, 138, 139.
• scrap pieces not classified as specified valuable scrap pieces may be allowed to pass into the bin 140.
• a set of one or more air jets may be configured to direct scrap pieces classified as specified valuable scrap pieces into a first receptacle as they drop off of the edge of the conveyor belt 103, while those scrap pieces not classified as the specified valuable scrap pieces are permitted to merely drop off of the edge of the conveyor belt 103 into a separate second receptacle (e.g., bin 140). Or, the reverse may be performed where the scrap pieces classified as the specified valuable scrap pieces are permitted to merely drop off of the edge of the conveyor belt 103.
• monetary coins may be separately classified based on their different denominations, and therefore sorted into separate bins accordingly.
• multiple classifications may be mapped to a single sorting device and associated sorting bin.
• it may be desired by the user to sort certain classes or types of materials e.g., one or more different denominations of monetary coins, or both monetary coins and copper and/or brass, etc.
• a scrap piece 101 when a scrap piece 101 is classified as falling into a predetermined grouping of classifications (e.g., one or more different denominations of monetary coins, or both monetary coins and copper and/or brass, etc.), the same sorting device may be activated to sort these into the same sorting bin.
• Such combination sorting may be applied to produce any desired combination of sorted scrap pieces.
• the mapping of classifications may be programmed by the user (e.g., using the sorting algorithm (e.g., see FIG. 4) operated by the computer system 107) to produce such desired combinations.
• the classifications of scrap pieces are user- definable, and not limited to any particular known classifications of scrap pieces.
• the machine learning system of the present disclosure may be configured to separately classify two or more monetary coin denominations for sorting into the same bin (e.g., one or more of the bins 136, 137, 138, 139), or to classify certain denomination(s) (e.g., U.S. pennies) for sorting in the same bin as the scrap pieces not classified as monetary coins.
• the same bin e.g., one or more of the bins 136, 137, 138, 139
• certain denomination(s) e.g., U.S. pennies
• the machine learning system of the present disclosure may be configured to classify and sort both monetary coins and another class or type of valuable into a common bin.
• the other class(es) or type(s) of valuable(s) may be jewelry (e.g., rings, earrings, parts of bracelets, parts of necklaces, etc., such as shown in FIG. 3C), pieces of specified classes or types of metals (e.g., gold, silver, copper, brass, etc.), and/or any scrap pieces that are identified by the machine learning system to contain certain specified metals (e.g., PCBs that can contain copper, gold, or silver).
• jewelry e.g., rings, earrings, parts of bracelets, parts of necklaces, etc., such as shown in FIG. 3C
• pieces of specified classes or types of metals e.g., gold, silver, copper, brass, etc.
• any scrap pieces that are identified by the machine learning system to contain certain specified metals e.g., PCBs that can contain copper, gold, or silver.
• scrap pieces collected into a common bin may be passed through the system 100 again (or such scrap pieces may be conveyed to a second similar system like the system 100, such as further disclosed herein) in order to sort apart the collected valuable scrap pieces (e.g., sort between monetary coins and copper and/or brass).
• the conveyor system 103 may include a circular conveyor (not shown) so that unclassified scrap pieces (or scrap pieces of two or more classes or types of materials for sorting again) are returned to the beginning of the sorting system 100 to be ran through the system 100 again.
• some sort of sorting device e.g., the sorting device 129) may be implemented to eject a scrap piece 101 that the system 100 has failed to classify (e.g., as a monetary coin, jewelry, PCB, PCB and jewelry, etc.) after a predetermined number of cycles through the sorting system 100.
• the conveyor belt 103 may be divided into multiple belts configured in series such as, for example, two belts, where a first belt conveys the scrap pieces past the vision system, and a second belt conveys the scrap pieces from the vision system to the sorting devices. Moreover, such a second conveyor belt may be at a lower elevation than the first conveyor belt, such that the scrap pieces fall from the first belt onto the second belt.
• embodiments of the present disclosure may implement one or more vision systems (e.g., vision system 110) in order to identify, track, and/or classify scrap pieces.
• vision system 110 e.g., vision system 110
• Such a vision system may be configured with one or more devices for capturing or acquiring images of the scrap pieces as they pass by on a conveyor system.
• the devices may be configured to capture or acquire any desired range of wavelengths reflected by the scrap pieces, including, but not limited to, visible, infrared (“IR”), ultraviolet (“UV”) light.
• the vision system may be configured with one or more cameras (still and/or video, either of which may be configured to capture two-dimensional, three-dimensional, and/or holographical images) positioned in proximity (e.g., above) the conveyor system so that visual images of the scrap pieces are captured as they pass by the vision system(s).
• the images may then be sent to a computer system (e.g., computer system 107) to be processed by a machine learning system in order to identify and/or classify each of the scrap pieces for subsequent sorting of the scrap pieces in a desired manner.
• a computer system e.g., computer system 107
• Such a machine learning system may implement one or more any well-known machine learning algorithms, including one that implements a neural network (e.g., artificial neural network, deep neural network, convolutional neural network, recurrent neural network, autoencoders, reinforcement learning, etc.), fuzzy logic, artificial intelligence (“AI”), deep learning algorithms, deep structured learning hierarchical learning algorithms, support vector machine (“SVM”) (e.g., linear SVM, nonlinear SVM, SVM regression, etc.), decision tree learning (e.g., classification and regression tree (“CART”), ensemble methods (e.g., ensemble learning, Random Forests, Bagging and Pasting, Patches and Subspaces, Boosting, Stacking, etc.), dimensionality reduction (e.g., Projection, Manifold Learning, Principal Components Analysis, etc.) and/or deep machine learning algorithms, such as those described in and publicly available at the deeplearning.net website (including all software, publications, and hyperlinks to available software referenced within this website), which is hereby incorporated by reference here
• Non-limiting examples of publicly available machine learning algorithms, software, and libraries that could be utilized within embodiments of the present disclosure include Python, OpenCV, Inception, Theano, Torch, PyTorch, Pyleam2, Numpy, Blocks, TensorFlow, MXNet, Caffe, Lasagne, Keras, Chainer, Matlab Deep Learning, CNTK, MatConvNet (a MATLAB toolbox implementing convolutional neural networks for computer vision applications), DeepLearnToolbox (a Matlab toolbox for Deep Learning (from Rasmus Berg Palm)), BigDL, Cuda-Convnet (a fast C++/CUDA implementation of convolutional (or more generally, feed-forward) neural networks), Deep Belief Networks, RNNLM, RNNLIB-RNNLIB, matrbm, deeplearning4j , Eblearn.lsh, deepmat, MShadow, Matplotlib, SciPy, CXXNET, Nengo- Nengo, Ebleam, cudamat, Gnumpy, 3-
• Machine learning often occurs in two stages, or phases. For example, first, training occurs offline in that the sorting system 100 is not being utilized to perform actual sorting of scrap pieces.
• a portion of the system 100 may be utilized to train the machine learning system in that one or more homogenous sets of scrap pieces (i.e., monetary coins of one or more denominations (e.g., see FIG. 3A), exemplary sets of rings, bracelets, necklaces, and/or earrings, exemplary scrap pieces of PCBs, or exemplary scrap pieces of certain types of precious metals (e.g., gold, silver, copper, brass, etc.)) are passed by the vision system 110 using the conveyor system 103 (each set of homogenous scrap pieces is not sorted, but may be collected in a common bin (e.g., bin 140)).
• the training may be performed at another location remote from the system 100, including using some other mechanism for collecting images of homogenous sets of specified valuable scrap pieces.
• a homogeneous set of monetary coins may be a collection of monetary coins of the same denomination (and thus having the same shape, size, color, hue, etc.), or may be a collection of monetary coins of different denominations (and thus having different shapes, sizes, colors, or hues, etc.), but sharing at least one physical characteristic that is the same or substantially the same, such as shape (e.g., circular, polygonal).
• shape e.g., circular, polygonal
• the machine learning algorithm(s) extract features from the captured images using image processing techniques well known in the art.
• training algorithms include, but are not limited to, linear regression, gradient descent, feed forward, polynomial regression, learning curves, regularized learning models, and logistic regression. It is during this training stage that the machine learning algorithm(s) may be configured to learn the relationships between specified valuable scrap pieces (e.g., monetary coins).
• such a knowledge base may include a requirement that scrap pieces to be classified as monetary coins have a substantially circular and/or polygonal shape (e.g., within a predetermined threshold of being substantially circular and/or polygonal since the coins may have become somewhat damaged within the vehicles or by an automobile shredder, such as shown by some of the coins in FIG. 3A).
• Such a knowledge base may include a rejection of circular scrap pieces having a hole formed therein in order to not classify metal washers as monetary coins.
• Such a knowledge based may further include a rejection of circular scrap pieces having a certain color or hue (e.g., in order to not sort U.S. pennies with other monetary coins).
• Such a knowledge base may include one or more libraries, wherein each library includes parameters for utilization by the vision system 110 in classifying and sorting scrap pieces during the second stage or phase.
• each library includes parameters for utilization by the vision system 110 in classifying and sorting scrap pieces during the second stage or phase.
• one particular library may include parameters configured by the training stage to recognize and classify a particular denomination of monetary coin.
• such libraries may be inputted into the vision system and then the user of the system 100 may be able to adjust certain ones of the parameters in order to adjust an operation of the system 100 (for example, adjusting the threshold effectiveness of how well the vision system recognizes a particular denomination of monetary coin from a heterogeneous mixture of materials (e.g., see FIG. 3B)).
• FIG. 3A shows captured or acquired images of a homogenous set of exemplary monetary coins that may be used during the aforementioned training stage.
• a plurality of such monetary coins which are the control samples (e.g., a homogenous set of exemplary monetary coins of one or more specified denominations)
• the vision system e.g., by the conveyor system 103
• the machine learning system detects, extracts, and leams what features visually represent such exemplary monetary coins.
• images of monetary coins such as shown in FIG.
• 3A may be first passed through such a training stage so that the machine learning system“learns” how to detect, recognize, and classify monetary coins among a heterogeneous mixture of scrap pieces (e.g., such as shown in FIGS. 3B and 3D). This creates a library of parameters particular to specified monetary coins.
• the detected/extracted features are not necessarily simply colors, or brightness, or circular or polygonal shapes; they can be abstract formulations that can only be expressed mathematically, or not mathematically at all; nevertheless, the machine learning system parses all of the data to look for patterns that allow the control samples (e.g., actual monetary coins) to be classified during the training stage.
• the machine learning system may take subsections of a captured image of a scrap piece and attempt to find correlations between the pre defined classifications (e.g., one or more various monetary coin denominations).
• the machine learning system may be configured so that it classifies as monetary coins those scrap pieces that are nearly circular but not exactly circular. For example, when monetary coins contained within a scrap yard vehicle are processed (for example, ran through a shredder), they may become damaged (e.g., slightly bent or a notch formed therein). FIG. 3A shows examples of some such damaged coins.
• the machine learning system may have its tolerance parameters adjusted to classify such scrap pieces as monetary coins. For example, a scrap piece is classified as a monetary coin even though it is not perfectly circular or does not have a completely closed circular shape, but its overall size (e.g., diameter) and/or color, hue, texture, etc.
• the machine learning system may be trained to classify scrap pieces as monetary coins by including exemplary samples of damaged (e.g., notched, bent, etc.) coins within the aforementioned control samples (see FIG. 3A).
• the machine learning system of the present disclosure may be configured to classify such objects in a stream of scrap pieces as monetary coins.
• the scrap pieces may include circular knockouts, which look similar to monetary coins.
• a machine learning system configured in accordance with embodiments of the present disclosure can be configured to not classify such knockouts as monetary coins. This may be accomplished by passing a homogenous set of such knockouts through the machine learning system during the training stage. The machine learning system may“learn” to not classify such knockouts as monetary coins by how the knockouts have a different appearance from monetary coins, such as their texture, color, the lack of a stamped pattern on their face, etc.
• the machine learning system may be configured to not classify as monetary coins any circular-shaped scrap piece that does not have a diameter equivalent to one or more specified monetary coins (e.g., a U.S. quarter, nickel, dime, etc.), including but not limited to, any scrap piece with a diameter that is greater than and/or less than a predetermined diameter. This, for example, could result in clothing buttons not classified as monetary coins. Such diameter specifications may be utilized to sort monetary coins by denomination.
• specified monetary coins e.g., a U.S. quarter, nickel, dime, etc.
• training of the machine learning system to identify monetary coins for sorting using a homogenous set of exemplary coins enables the machine learning system 100 to sort specified monetary coins from a heterogeneous mixture of scrap pieces (e.g., see FIG. 3B).
• the machine learning system may be trained to identify specified types of jewelry by passing exemplary samples of jewelry pieces (e.g., see FIG. 3C) through the machine learning system as previously disclosed in order to enable the machine learning system 100 to sort specified jewelry scrap pieces from a heterogeneous mixture of scrap pieces (e.g., see FIG. 3D).
• the machine learning system is capable of identifying and sorting jewelry scrap pieces from such a heterogeneous mixture of scrap pieces by learning the particular physical characteristics of such specified jewelry scrap pieces.
• FIG. 3D provides a non-limiting example of how such jewelry scrap pieces can be visually distinguished from other scrap pieces.
• exemplary pieces of PCBs may be ran through a machine learning system as a homogenous set in order to enable the machine learning system 100 to identify and sort out such PCB scrap pieces from a heterogeneous mixture of scrap pieces.
• the machine learning system may do so by looking for scrap pieces that are green or appear like green plastic boards.
• FIG. 6 represents at an abstract level examples of various possible embodiments of the present disclosure.
• a machine learning algorithm, or algorithms may essentially embody one or more aspects of the system and process 600, though not necessarily exactly as outlined in the flow diagram of FIG. 6.
• the vision system 110 acquires images of the scrap pieces 101 as described herein.
• Block 602 abstractly represents that the machine learning system may be configured to identify those scrap pieces that resemble certain specified valuable scrap pieces (e.g., monetary coins, whether they be circular or of a polygonal shape).
• Other physical features e.g., color, tint, hue, texture, stamped features, diameter, etc.
• specified features e.g., coin-related
• Optional block 603 abstractly represents how the machine learning system may be configured to exclude from the monetary coin classification those scrap pieces 101 that look similar to (i.e., have physical characteristics similar to) electrical box knockouts.
• Optional block 604 abstractly represents how the machine learning system may be further configured to not classify as monetary coins those scrap pieces that are not of a desired denomination to be sorted (e.g., have the color of a U.S. penny, are smaller than a dime, are larger than a quarter, etc.)
• Block 604 also abstractly represents how the machine learning system may separately sort different denominations of monetary coins.
• the libraries for the different classes or types of materials are then implemented into the material sorting system (e.g., the system 100) to be used for identifying and/or classifying and then sorting specified scrap pieces from a heterogeneous mixture of scrap pieces.
• FIG. 4 illustrates a flowchart diagram depicting exemplary embodiments of a process 400 of sorting scrap pieces utilizing a vision system in accordance with certain embodiments of the present disclosure.
• Aspects of the process 400 may be configured to operate within any of the embodiments of the present disclosure described herein, including the sorting system 100 of FIG. 1. Operation of the process 400 may be performed by hardware and/or software, including within a computer system (e.g., computer system 3400 of FIG. 5) controlling the sorting system (e.g., the computer system 107 and/or the vision system 110 of FIG. 1).
• a computer system e.g., computer system 3400 of FIG. 5
• controlling the sorting system e.g., the computer system 107 and/or the vision system 110 of FIG. 1).
• the scrap pieces may be passed through some sort of well-known sieve (not shown), which may be configured so that scrap pieces smaller than a predetermined size are permitted to pass through the sieve.
• some sort of well-known sieve (not shown), which may be configured so that scrap pieces smaller than a predetermined size are permitted to pass through the sieve.
• slots formed in the sieve may be configured to pass objects with similar sizes as monetary coins.
• any device or even another sorting system as described herein may be utilized to first separate smaller scrap pieces from larger ones.
• the scrap pieces may be deposited onto a conveyor belt.
• FIG. 3B shows a digital photograph of an exemplary heterogeneous collection of such scrap pieces, including various monetary coins, deposited onto a conveyor belt.
• FIG. 3A shows a digital photograph of an exemplary heterogeneous collection of scrap pieces, including various jewelry scrap pieces, deposited onto a conveyor belt.
• the sieve may be located so that the scrap pieces that pass through deposit onto the conveyor belt. For example, referring to FIG. 1, such a sieve may be positioned between the ramp or chute 102 and the conveyor belt
• each scrap piece 101 is detected for tracking of each scrap piece as it travels through the sorting system. This may be performed by the vision system 110 (for example, by distinguishing a scrap piece from the underlying conveyor belt material while in communication with a conveyor belt speed detector (e.g., the belt speed detector
• a linear sheet laser beam can be used to locate the pieces, (or, any system that can create a light source (including, but not limited to, visual light, UV, VIS, and IR) and have a detector that can be used to locate the pieces).
• a machine learning system such as previously disclosed, may perform pre-processing of the images, which may be utilized to detect or discern
• the image pre-processing may be utilized to identify the difference between the scrap piece and the background.
• Well-known image processing techniques such as dilation, thresholding, and contouring may be utilized to identify the scrap piece as being distinct from the background.
• image segmentation may be performed.
• one or more of the images captured by the camera of the vision system may include images of one or more scrap pieces.
• a particular scrap piece may be located on a seam of the conveyor belt when its image is captured. Therefore, it may be desired in such instances to isolate the image of an individual scrap piece from the background of the image.
• a first step is to apply a high contrast of the image; in this fashion, background pixels are reduced to substantially all black pixels, and at least some of the pixels pertaining to the scrap piece are brightened to substantially all white pixels.
• the image pixels of the scrap piece that are white are then dilated to cover the entire size of the scrap piece.
• the location of the scrap piece is a high contrast image of all white pixels on a black background.
• a contouring algorithm can be utilized to detect boundaries of the scrap piece.
• the boundary information is saved, and the boundary locations are then transferred to the original image. Segmentation is then performed on the original image on an area greater than the boundary that was earlier defined. In this fashion, each scrap piece is identified and separated from the background.
• the size and shape of each scrap piece may be determined.
• image post processing may be performed.
• Image post processing may involve resizing the image to prepare it for use in the neural networks. This may also include modifying certain image properties (e.g., enhancing image contrast, changing the image background, or applying filters) in a manner that will yield an enhancement to the capability of the machine learning system to classify the scrap pieces.
• normalization of the various images may be performed in the process block 408 so that the images of the various different scrap pieces can be more easily compared to each other.
• the data representing each of the images may be resized. Image resizing may be necessary under certain circumstances to match the data input requirements for certain machine learning systems, such as neural networks.
• Neural networks require much smaller image sizes (e.g., 225 x 255 pixels or 299 x 299 pixels) than the sizes of the images captured by typical digital cameras. Moreover, the smaller the image size, the less processing time is needed to perform the classification. Thus, smaller image sizes can ultimately increase the throughput of the sorter system and increase its value.
• each scrap piece is identified/classified based on the detected features.
• the process block 410 may be configured with a neural network employing one or more machine learning algorithms, which compare the extracted features (e.g., circular/polygonal shape, no hole, color, etc.) with those stored in the knowledge base generated during the training stage, and assign the classification with the highest match to each of the scrap pieces based on such a comparison.
• the machine learning algorithm(s) may process the captured image in a hierarchical manner by using automatically trained filters. The filter responses are then successfully combined in the next level(s) of the algorithm(s) until a probability is obtained in the final step.
• these probabilities may be used for each of the N (N>l) classifications to decide into which of the N sorting bins the respective scrap pieces should be sorted.
• each of the N classifications may be assigned to a respective sorting bin, and the scrap piece under consideration is sorted into that bin that corresponds to the classification returning the highest probability larger than a predefined threshold.
• predefined thresholds may be preset by the user.
• a particular scrap piece may be sorted into an outlier bin (e.g., sorting bin 140) if none of the probabilities is larger than the predetermined threshold (e.g., the scrap piece is not classified as a monetary coin).
• a sorting device corresponding to the classification, or classifications, of the scrap piece is activated (e.g., see FIG. 2). Between the time at which the image of the scrap piece 101 was captured by the vision system 110 and the time at which the sorting device is activated, the scrap piece 101 has moved from the proximity of the vision system 110 to a location downstream on the conveyor belt 103, at the rate of conveying of the conveyor belt 103.
• the activation of the sorting device (e.g., 126, 127, 128, 129) is timed such that as the scrap piece 101 passes the sorting device mapped to the classification of the scrap piece, the sorting device is activated, and the scrap piece is directed into its associated sorting bin (e.g., 136, 137, 138, 139).
• the activation of a sorting device may be timed by the automation control system in communication with the belt speed detector 105 that detects when a scrap piece is passing before the sorting device and sends a signal to enable the activation of the sorting device.
• the sorting bin corresponding to the sorting device that was activated receives the directed scrap piece.
• a plurality of at least a portion of the system 100 may be linked together in succession in order to perform multiple iterations or layers of sorting.
• the conveyor system may be implemented with a single conveyor belt, or multiple conveyor belts, conveying the scrap pieces past a first vision system configured for sorting scrap pieces of a first set of a heterogeneous mixture of materials by a sorter (e.g., the first automation control system 108 and associated one or more sorting devices 126, 127, 128, 129) into a first set of one or more receptacles (e.g., sorting bins 136, 137, 138, 139), and then conveying the scrap pieces past a second vision system configured for sorting scrap pieces of a second set of a heterogeneous mixture of materials by a second sorter into a second set of one or more sorting bins.
• a sorter e.g., the first automation control system 108 and associated one or more sorting devices 126, 127, 128, 129
• each successive vision system may be configured to sort out a different material than previous vision system(s) (e.g., initially sort coins and copper/brass from scrap, then sort between the coins and the copper/brass pieces).
• embodiments of the present disclosure may be implemented to perform the various functions described for identifying, tracking, classifying, and sorting materials, such as scrap pieces.
• Such functionalities may be implemented within hardware and/or software, such as within one or more data processing systems (e.g., the data processing system 3400 of FIG. 5), such as the previously noted computer system 107, the vision system 110, and/or automation control system 108. Nevertheless, the functionalities described herein are not to be limited for implementation into any particular hardware/software platform.
• aspects of the present disclosure may be embodied as a system, process, method, and/or program product. Accordingly, various aspects of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.), or embodiments combining software and hardware aspects, which may generally be referred to herein as a “circuit,”“circuitry,”“module,” or“system.” Furthermore, aspects of the present disclosure may take the form of a program product embodied in one or more computer readable storage medium(s) having computer readable program code embodied thereon. (However, any combination of one or more computer readable medium(s) may be utilized. The computer readable medium may be a computer readable signal medium or a computer readable storage medium.)
• a computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, biologic, atomic, or semiconductor system, apparatus, controller, or device, or any suitable combination of the foregoing, wherein the computer readable storage medium is not a transitory signal per se. More specific examples (a non-exhaustive list) of the computer readable storage medium may include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (“RAM”) (e.g., RAM 3420 of FIG. 5), a read-only memory (“ROM”)
• RAM random access memory
• ROM read-only memory
• a computer readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, controller, or device.
• Program code embodied on a computer readable signal medium may be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
• a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electro magnetic, optical, or any suitable combination thereof.
• a computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instmction execution system, apparatus, controller, or device.
• each block in the flowcharts or block diagrams may represent a module, segment, or portion of code, which includes one or more executable program instructions for implementing the specified logical function(s).
• the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
• CPU 3415 may, for instance, include one or more physical or logical blocks of computer instructions, which may, for instance, be organized as an object, procedure, or function.
• the executables of an identified module need not be physically located together, but may include disparate instructions stored in different locations which, when joined logically together, include the module and achieve the stated purpose for the module.
• a module of executable code may be a single instruction, or many instructions, and may even be distributed over several different code segments, among different programs, and across several memory devices.
• operational data e.g., material classification libraries described herein
• the operational data may be collected as a single data set, or may be distributed over different locations including over different storage devices.
• the data may provide electronic signals on a system or network.
• program instructions may be provided to one or more processors and/or controller(s) of a general purpose computer, special purpose computer, or other programmable data processing apparatus (e.g., controller) to produce a machine, such that the instructions, which execute via the processor(s) (e.g., GPU 3401, CPU 3415) of the computer or other programmable data processing apparatus, create circuitry or means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
• processors e.g., GPU 3401, CPU 3415
• each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by special purpose hardware -based systems (e.g., which may include one or more graphics processing units (e.g., GPU 3401, CPU 3415)) that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
• a module may be implemented as a hardware circuit including custom VLSI circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, controllers, or other discrete components.
• a module may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, or the like.
• Computer program code i.e., instructions, for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, Python, C++, or the like, conventional procedural programming languages, such as the“C” programming language or similar programming languages, or any of the machine learning software disclosed herein.
• the program code may execute entirely on the user’s computer system, partly on the user’s computer system, as a stand-alone software package, partly on the user’s computer system (e.g., the computer system utilized for sorting) and partly on a remote computer system (e.g., the computer system utilized to train the machine learning system), or entirely on the remote computer system or server.
• the remote computer system may be connected to the user’s computer system through any type of network, including a local area network (“LAN”) or a wide area network (“WAN”), or the connection may be made to an external computer system (for example, through the Internet using an Internet Service Provider).
• LAN local area network
• WAN wide area network
• various aspects of the present disclosure may be configured to execute on one or more of the computer system 107, automation control system 108, and the vision system 110.
• program instructions may also be stored in a computer readable storage medium that can direct a computer system, other programmable data processing apparatus, controller, or other devices to function in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
• the program instructions may also be loaded onto a computer, other programmable data processing apparatus, controller, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
• One or more databases may be included in a host for storing and providing access to data for the various implementations.
• any databases, systems, or components of the present disclosure may include any combination of databases or components at a single location or at multiple locations, wherein each database or system may include any of various suitable security features, such as firewalls, access codes, encryption, de-encryption and the like.
• the database may be any type of database, such as relational, hierarchical, object-oriented, and/or the like. Common database products that may be used to implement the databases include DB2 by IBM, any of the database products available from Oracle Corporation, Microsoft Access by Microsoft Corporation, or any other database product.
• the database may be organized in any suitable manner, including as data tables or lookup tables.
• Association of certain data may be accomplished through any data association technique known and practiced in the art.
• the association may be accomplished either manually or automatically.
• Automatic association techniques may include, for example, a database search, a database merge, GREP, AGREP, SQL, and/or the like.
• the association step may be accomplished by a database merge function, for example, using a key field in each of the manufacturer and retailer data tables. A key field partitions the database according to the high-level class of objects defined by the key field.
• a certain class may be designated as a key field in both the first data table and the second data table, and the two data tables may then be merged on the basis of the class data in the key field.
• the data corresponding to the key field in each of the merged data tables is preferably the same.
• data tables having similar, though not identical, data in the key fields may also be merged by using AGREP, for example.
• FIG. 5 a block diagram illustrating a data processing (“computer”) system 3400 is depicted in which aspects of embodiments of the disclosure may be implemented.
• the computer system 107, the automation control system 108, and/or the vision system 110 may be configured similarly as the computer system 3400.
• the computer system 3400 may employ a local bus 3405 (e.g., a peripheral component interconnect (“PCI”) local bus architecture). Any suitable bus architecture may be utilized such as Accelerated
• processors 3415, volatile memory 3420, and non-volatile memory 3435 may be connected to the local bus 3405 (e.g., through a PCI Bridge (not shown)).
• An integrated memory controller and cache memory may be coupled to the one or more processors 3415.
• SCSI Serial Bus
• expansion bus interface (not shown)
• SCSI host bus
• An audio adapter (not shown), a graphics adapter (not shown), and display adapter 3416 (coupled to a display 3440) may be connected to the local bus 3405 (e.g., by add-in boards inserted into expansion slots).
• the user interface adapter 3412 may provide a connection for a keyboard 3413 and a mouse 3414, modem (not shown), and additional memory (not shown).
• the I/O adapter 3430 may provide a connection for a hard disk drive 3431, a tape drive 3432, and a CD-ROM drive (not shown).
• An operating system may be ran on the one or more processors 3415 and used to coordinate and provide control of various components within the computer system 3400.
• the operating system may be a commercially available operating system.
• An object-oriented programming system e.g., Java, Python, etc.
• Java, Python, etc. may ran in conjunction with the operating system and provide calls to the operating system from programs or programs (e.g., Java, Python, etc.) executing on the system 3400.
• Instructions for the operating system, the object-oriented operating system, and programs may be located on non-volatile memory 3435 storage devices, such as a hard disk drive 3431, and may be loaded into volatile memory 3420 for execution by the processor 3415.
• FIG. 5 may vary depending on the implementation.
• Other internal hardware or peripheral devices such as flash ROM (or equivalent nonvolatile memory) or optical disk drives and the like, may be used in addition to or in place of the hardware depicted in FIG. 5.
• any of the processes of the present disclosure may be applied to a multiprocessor computer system, or performed by a plurality of such systems 3400. For example, training of the vision system 110 may be performed by a first computer system 3400, while operation of the vision system 110 for sorting may be performed by a second computer system 3400.
• the computer system 3400 may be a stand-alone system configured to be bootable without relying on some type of network communication interface, whether or not the computer system 3400 includes some type of network communication interface.
• the computer system 3400 may be an embedded controller, which is configured with ROM and/or flash ROM providing non-volatile memory storing operating system files or user generated data.
• the term“or” may be intended to be inclusive, wherein“A or B” includes A or B and also includes both A and B.
• the term“and/or” when used in the context of a listing of entities refers to the entities being present singly or in combination.
• the phrase“A, B, C, and/or D” includes A, B, C, and D individually, but also includes any and all combinations and subcombinations of A, B, C, and D.
• the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure.
• the singular forms“a,”“an,” and“the” may be intended to include the plural forms as well, unless the context clearly indicates otherwise.
• substantially refers to a degree of deviation that is sufficiently small so as to not measurably detract from the identified property or circumstance.
• the exact degree of deviation allowable may in some cases depend on the specific context.
• the term“about,” when referring to a value or to an amount of mass, weight, time, volume, concentration or percentage is meant to encompass variations of in some embodiments ⁇ 20%, in some embodiments ⁇ 10%, in some embodiments ⁇ 5%, in some embodiments ⁇ 1%, in some embodiments ⁇ 0.5%, and in some embodiments ⁇ 0.1% from the specified amount, as such variations are appropriate to perform the disclosed method.

Landscapes

• Engineering & Computer Science (AREA)
• Multimedia (AREA)
• Sorting Of Articles (AREA)

Priority Applications (3)

Applications Claiming Priority (2)

Publications (1)

Family

ID=68294223

Family Applications (1)

Country Status (4)

Cited By (3)

Families Citing this family (1)

Citations (12)

Family Cites Families (13)

• 2019
  • 2019-03-19 WO PCT/US2019/022995 patent/WO2019209428A1/en active Application Filing
  • 2019-03-19 CN CN201980043725.XA patent/CN112543680A/zh active Pending
  • 2019-03-19 JP JP2021509947A patent/JP2021522070A/ja active Pending
  • 2019-03-19 EP EP19792330.3A patent/EP3784419A4/en active Pending

Patent Citations (12)

Also Published As

Similar Documents

Legal Events