KR20230159398A - sorting of plastics - Google Patents

Abstract

Systems and methods for classifying and sorting plastic materials utilizing a vision system and one or more sensor systems, wherein each of the materials can be identified or classified and then sorted into separate groups based on such identification or classification. Systems and methods that can implement a machine learning system.

Description

sorting of plastics

This application claims priority to U.S. Provisional Patent Application No. 63/146,892 and U.S. Provisional Patent Application No. 63/173,301. This application relates to U.S. Provisional Patent Application No. 62/490,219, which is a continuation-in-part of U.S. Patent Application No. 15/213,129 (published as U.S. Patent No. 10,207,296), which claims priority to U.S. Provisional Patent Application No. 62/193,332. U.S. Patent Application No. 16, a continuation-in-part of U.S. Patent Application Serial No. 15/963,755 (published as U.S. Patent No. 10,710,119), which claims priority; It is a continuation-in-part of U.S. Patent Application No. 17/495,291, which is a continuation-in-part of U.S. Patent Application No. 17/227,245, which is a continuation-in-part of U.S. Patent Application No. 17/380,928, which is a continuation-in-part of U.S. Patent Application No. 17/495,291, which is a continuation-in-part of U.S. Patent Application No. Included. This application also claims U.S. Patent Application Serial No. 16, which is a divisional application of U.S. Patent Application Serial No. 16/358,374 (issued U.S. Patent No. 10,625,304), which is a continuation-in-part of U.S. Patent Application Serial No. 15/963,755 (issued U.S. Patent No. 10,710,119) This is a continuation-in-part application of U.S. Patent Application No. 17/491,415, which is a continuation-in-part application of /852,514.

government licensing rights

This disclosure was prepared with support from the U.S. Government under Grant No. DE-AR0000422 granted by the U.S. Department of Energy. The United States Government may have certain rights in this disclosure.

technology field

The present disclosure relates generally to the sorting of solid waste, and in particular to the sorting of plastic pieces from municipal or industrial solid waste.

This section is intended to introduce various aspects that may be related to exemplary embodiments of the present disclosure. It is believed that this discussion will help provide a framework to facilitate a better understanding of certain aspects of the disclosure. Accordingly, this section should be read in this light and should not necessarily be understood as an admission of prior art.

Recycling is the process of collecting and processing materials that could otherwise be discarded as waste (e.g., from waste streams) and turning them into new products or at least enabling more appropriate disposal. Recycling reduces the amount of waste sent to landfills, conserves natural resources such as wood, water and minerals, increases economic stability by utilizing domestic sources of materials, and prevents pollution by reducing the need to collect new raw materials. There are benefits to communities and the environment by saving energy. After collection, recyclables are sent to a materials recovery facility (“MRF”) where they can be sorted, cleaned and processed into materials that can be used in manufacturing. As a result, high-throughput automated sorting platforms that economically sort highly mixed waste streams will be useful across a variety of industries. Therefore, it is cost-effective to identify, analyze and separate mixed industrial or municipal solid waste streams at high throughput to economically generate high-quality feedstocks (which may contain low levels of trace contaminants) for subsequent processing. Efficient sorting platforms are needed. Typically, MRFs are either unable to distinguish between many materials and are therefore limited to markets where the sorted materials are of low quality and low value, or they are so slow, labor-intensive and inefficient that they limit the amount of material that can be economically recycled or recovered.

Municipal solid waste (“MSW”) is a broad term for waste streams encompassing household, commercial and industrial sources. There are thousands of different substances and products in each of these categories. EPA reported that 267.8 million tons of MSW were generated in 2017. Of the total weight of MSW, 35.37 million tons, or 13.2%, consisted of plastics. Of the 35.37 million tons of plastics, 2.96 million tons (8.4%) were recycled, 5.59 million tons (15.8%) were burned through energy recovery, and 26.82 million tons (75.8%) were landfilled. It is clear that more plastics need to be recycled.

Plastic recycling is the reprocessing of plastic waste into new, useful products. Almost all plastics need to be recycled because they are not biodegradable and accumulate in the environment. Currently, almost all recycling is done through so-called mechanical recycling, in which used plastics are re-melted and reborn into new items. This can break down polymers at a chemical level, and requires sorting by color and polymer type before plastic waste can be reprocessed, making it complex and expensive. Failure of this process can produce materials with inconsistent properties, which are unattractive to industry. An alternative approach, known as feedstock recycling, can convert plastic waste back into its original chemicals and then reprocess it into new plastics. This can lead to more recycling, but has the disadvantage of high energy and capital costs. Plastic waste can also be incinerated as an alternative to fossil fuels as part of energy recovery.

Currently, only some plastics can be recycled. When plastics are recycled, they are usually sorted into different types of plastic. Recycling rates also vary depending on the type of plastic. Several types are commonly used, each with different chemical and physical properties. This leads to differences in the ease of sorting and reprocessing, which affects the value and market size of the recovered materials. Plastic packaging and products made from a single material (e.g., polyethylene terephthalate (“PET”), high-density polyethylene (“HDPE”), and polypropylene (“PP”)) can be more easily recycled. Plastics that are rarely or occasionally recyclable include polyvinyl chloride (“PVC”), low-density polyethylene (“LDPE”), linear low-density polyethylene (“LLDPE”), and polystyrene (“PS”). Additionally, plastics have a limited number of recycling possibilities.

Modern single-flow MRFs and plastics recyclers require processing equipment that can move and sort material at high speeds due to the high volume of incoming material. At the same time, the highest value is obtained from the purest and least polluting streams. To achieve these somewhat contradictory goals, today's single-flow MRFs and recyclers use automated equipment that sorts plastic packaging by near-infrared ("NIR") signature through transmission or reflection. These sensors rely on reflection of light from an external source and can only see the surface of the material. Additionally, only polymer information is captured from this sensor. For example, NIR spectroscopy can identify plastics of type #1, which is transparent and light blue PET, and #2 HDPE, but #1 colored PET, #3 PVC, #4 LDPE, #5 PP, #6 PS, and #7 Other plastics such as multilayer polymers, composite polymers, acrylic and nylon can be rejected. Additionally, NIR spectroscopy cannot accurately identify black or dark colored plastics as well as complex materials such as plastic-coated paper and multilayer packaging (made from polymer multilayer films), which can give erroneous readings. Most black plastics are colored using carbon. Black plastics are widely used in the automotive industry, electronics, food packaging, plastic bags, etc. However, since black plastics not only absorb visible light but also the near-infrared part of the spectrum, they have an unfortunate side effect that is not visible in NIR spectroscopy. Therefore, the 'stealth' black plastic goes undetected into the 'other' bin at the end of the conveyor, where it is burned for energy or dumped in landfill.

In closed loop or primary recycling, waste plastic is recycled into new items of similar quality and type (for example, turning beverage bottles into beverage bottles). However, continuous mechanical recycling of plastics without quality loss is very difficult due to the risk of cumulative polymer degradation and contaminant accumulation. Although closed-loop recycling has been studied for many polymers, recycling of PET bottles has been the only industrially successful process to date.

In open loop or secondary recycling (also called downcycling), the quality of the plastic deteriorates with each recycling, so it cannot be recycled indefinitely and eventually becomes waste. Recycling of PET bottles into wool and other fibers is a common example and accounts for the majority of PET recycling. When making new products, mixing recycled plastics with raw materials or compatible plastics can offset the decline in polymer quality.

Thermoset polymers do not melt, but technologies have been developed for their mechanical recycling. This typically involves breaking down the material into crumbs and then mixing them with some type of binder to form a new composite material.

In feedstock or tertiary recycling (also called chemical recycling), polymers can be reduced to their chemical building blocks (monomers), which can then be polymerized to make new plastics. Pyrolysis and chemical depolymerization are two types of feedstock recycling.

Energy recovery, also called energy recycling or quaternary recycling, involves burning plastic waste instead of fossil fuels to produce energy.

A process has been developed that allows certain types of plastic to be used as a carbon source (instead of coke) when recycling scrap metal. Shredded plastic can be used as construction aggregate or filler in certain applications.

Plastic waste can be simply incinerated as Renewable Fuel (“RDF”) in waste-to-energy processes or can first be chemically converted into synthetic fuel. Combustion generates a large amount of hydrogen chloride (HCl), which can corrode equipment and cause undesirable chlorination of fuel products, so any method must be supplemented by excluding PVC or installing dichlorination technologies.

Mixed plastic waste can be depolymerized to make synthetic fuel. It may have higher calorific value and higher combustion efficiency than original plastic, but is less efficient than fossil fuels. Various conversion technologies have been studied, of which pyrolysis is the most common. Using catalysts in pyrolysis can yield better products with higher value. While incineration is widely used, plastic fuel technologies have historically had difficulty securing economic feasibility due to the costs of collecting and sorting plastic and the relatively low value of the produced fuel.

As a result of the foregoing, there are improved processes for sorting all types of plastics, the ability to sort plastics types #3 to #7, the ability to sort PVC and mixtures of plastics into new classifications or fractions. There is a need for the ability to sort and recycle more efficiently.

1 illustrates a schematic diagram of a sorting system constructed in accordance with certain embodiments of the present disclosure.
2 illustrates an example representation of a control set of material pieces used during the training stage in a machine learning system.
3 illustrates a flowchart constructed in accordance with certain embodiments of the present disclosure.
4 illustrates a simplified schematic diagram constructed in accordance with certain embodiments of the present disclosure.
Figures 5 and 6 illustrate examples of chemical signatures.
7 illustrates a flowchart constructed in accordance with certain embodiments of the present disclosure.
8 illustrates a flowchart constructed in accordance with certain embodiments of the present disclosure.
9 illustrates a block diagram of a data processing system constructed in accordance with certain embodiments of the present disclosure.

Various detailed embodiments of the present disclosure are disclosed herein. However, it should be understood that the disclosed embodiments are merely illustrative of the disclosure and that it may be implemented in various alternative forms. The drawings are not necessarily to scale and some features may be exaggerated or minimized to show details of specific components. Accordingly, the specific structural and functional details disclosed herein should not be construed as limiting, but only as a representative basis for teaching those skilled in the art to use the various embodiments of the present disclosure.

As used herein, “materials” include metals (ferrous and non-ferrous), metal alloys, plastics (any of the plastics disclosed herein, known in the industry, or newly created in the future). (including but not limited to plastics), rubber, foam, glass (including but not limited to borosilicate or soda lime glass and various colored glasses), ceramics, paper, cardboard, Teflon, PE, bundled wires, insulated sheathed wires, rare earth elements, leaves, wood, plants, plant parts, textiles, bio-waste, packaging, electronic waste, batteries and accumulators, end-of-life vehicles, Mining, construction, and demolition wastes, crop wastes, forestry residues, purpose-grown grasses, woody energy crops, microalgae, municipal food waste, food waste, hazardous chemical and biomedical wastes, construction debris, farm wastes, Biological items, non-biological items, objects with a certain carbon content, any other objects that can be found within municipal solid waste, and any of the sensor technologies disclosed herein. (but not limited to) additional types or classifications of any of the foregoing that may be distinguished from one another, including (but not limited to) one or more sensor systems. It may include any article or object, including but not limited to any other objects, articles or substances disclosed in the specification.

“Substance” may include a chemical element, a compound or mixture of chemical elements, or any article or object composed of a compound or mixture of chemical elements, where the complexity of the compound or mixture may vary from simple to complex. As used herein, “element” means a chemical element of the Periodic Table of the Elements, including elements that may have been discovered after the filing date of this application. Within this disclosure, the terms “scrap,” “pieces of scrap,” “material,” and “pieces of material” may be used interchangeably.

As is well known in the art, a “polymer” is an ingredient or material composed of very large molecules or macromolecules composed of many repeating subunits. Polymers may be natural polymers found in nature or synthetic polymers.

“Multilayer polymer films” consist of two or more different compositions and can have a thickness of up to about 7.5 ^-8 x 10 ^-4 m. The layers are at least partially adjacent and preferably, but optionally, coexist.

As used herein, the terms “plastic,” “plastic piece,” and “piece of plastic material” (all of which may be used interchangeably) refer to a polymer composition of one or more polymers and/or multilayer polymer films. It refers to any object that includes or consists of these.

As used herein, the term “chemical signature” refers to a unique pattern (e.g., a fingerprint spectrum), as generated by one or more analytical instruments, that identifies one or more specific elements or molecules in a sample. indicates the presence of substances (including polymers). The elements or molecules may be organic and/or inorganic. These analytical devices include any of the sensor systems disclosed herein. In accordance with embodiments of the present disclosure, one or more sensor systems disclosed herein may be configured to generate a chemical signature of a piece of material (e.g., a piece of plastic).

As used herein, “fraction” refers to organic and/or inorganic elements or molecules, polymer types, plastic types, polymer compositions, chemical signatures of plastics, and physical properties of plastic pieces. (e.g., color, transparency, strength, melting point, density, shape, size, manufacturing type, uniformity, response to stimuli, etc.), etc., which refers to any specific combination of the plastics disclosed herein. All various classifications and types are included. Non-limiting examples of fractions include pieces of one or more different types of plastic, including LDPE and a relatively high percentage of aluminum; LDPE and PP and relatively low percentage of iron; PP and zinc; Combinations of PE, PET and HDPE; Pieces of red LDPE plastic of any type; Any combination of plastic pieces other than PVC; Pieces of black plastic; Combinations of types #3 to #7 plastics containing specific combinations of organic and inorganic molecules; Combinations of one or more different types of multilayer polymer films; Combinations of certain plastics that do not contain certain contaminants or additives; Any types of plastics whose melting point is above a certain threshold; Any thermoset plastic of a plurality of specific types; Certain plastics that do not contain chlorine; Combinations of plastics with similar densities; Combinations of plastics with similar polarities; Plastic bottles without attached caps and vice versa are also included.

“Catalytic pyrolysis” involves heating polymeric materials in the absence of oxygen and in the presence of a catalyst to decompose them.

The term “predetermined” means set or determined in advance.

“Spectral imaging” is imaging that uses multiple bands of the electromagnetic spectrum. While a typical camera captures light across three wavelength bands of the visible spectrum: red, green, and blue (RGB), spectral imaging encompasses a wide range of technologies that include but go beyond RGB. Spectral imaging may use the infrared, visible, ultraviolet and/or x-ray spectra, or some combination thereof. Spectral data or spectral image data is a digital data representation of a spectral image. Spectral imaging may include collecting spectral data in visible and non-visible bands simultaneously, illuminating outside the visible range, or using optical filters to capture specific spectral ranges. It is also possible to capture hundreds of wavelength bands for each pixel in a spectral image.

As used herein, the term “image data packet” refers to a packet of digital data associated with a captured spectral image of an individual piece of material.

As used herein, the terms “identify” and “classify,” “identification” and “classification,” and any derivative terms of these terms may be used interchangeably. As used herein, to “classify” a piece of material is to determine (i.e., identify) the types or classes of materials to which the piece of material belongs. For example, according to certain embodiments of the present disclosure, a sensor system (described further herein) may be configured to collect and analyze any type of information to classify substances, and such classifications may be sorted. Utilized within the system to selectively sort material pieces as a function of a set of one or more physical and/or chemical properties (e.g., user-definable), such properties may include color, texture, hue, etc. , shape, brightness, weight, density, composition, size, uniformity, type of manufacture, chemical signature, predetermined fraction, radioactive signature, permeability to light, sound or other signals and emitted and/or reflected electromagnetic waves of the material fragments. Includes (but is not limited to) responses to stimuli such as various fields, including radiation (“EM”). As used herein, “manufacturing type” means formed by a forging process, formed by casting (including, but not limited to, consumable metal casting, permanent metal casting, and powder metallurgy), or forging. Refers to the type of manufacturing process, material removal process, etc. by which a piece of material, such as a metal part, is manufactured.

The types or classes (i.e., classifications) of substances can be defined by the user and are not limited to known classifications of substances. The subdivision of types or classes can vary from very coarse to very fine. For example, types or classes include plastics, ceramics, glasses, metals and other materials—the subdivision of these types or classes is relatively rough; Different metals and metal alloys, for example zinc, copper, brass, chrome plate and aluminum - the subdivision of these types or classes is still finer; or between specific types of plastics—the subdivision of these types or classes is relatively fine. Thus, types or classes distinguish between materials of significantly different compositions, for example, different types of plastics (e.g., between any of the plastics of types #1 to #7) or , may be configured to distinguish between materials of nearly identical composition, for example, subclasses of different plastics that may belong to a particular plastic type. It should be understood that the methods and systems discussed herein can be applied to accurately identify/classify pieces of material whose composition is not fully known prior to classification.

Embodiments of the present disclosure improve plastic sorting functions by fusing multiple sensor technologies and a machine learning system. Limitations of sensor-based sorter technologies arise from the use of a single sensor because each sensor can only detect a narrow range of signals. The most common sorter sensor types are eddy current, visible camera, x-ray transmission, near-infrared, and x-ray fluorescence ("XRF"), and are summarized in the following table.

sensor type associated physics detected signal eddy current magnetic field metals visible camera visible light reflection different colored substances X-ray transmission X-ray intensity Transmission, Density near infrared IR spectrum polymer type XRF XRF spectrum Inorganic elemental composition

However, the plastic pieces in MSW can be composed of one or more organic polymers, one or more inorganic elements, and are available in many different colors, shapes and sizes. Examples of these plastics include potato chip bags, squeeze juice boxes, some beverage containers, and electromagnetic sensitive electronic packaging. Embodiments of the present disclosure create new fractions from this waste stream using sensor-based technology that can sort these different types of plastics into unique classes that can account for their organic polymer composition and/or inorganic elemental composition. . For example, a conversion chemist interested in the relative composition of polymers and inorganic elements can select one or more new fractions to make a particular product from recycled plastics sorted into these fractions. As a result, sorting systems constructed according to embodiments of the present disclosure can produce fractions beyond what is possible with existing state-of-the-art sorting technologies.

For example, certain embodiments of the present disclosure may sort a predetermined fraction from bales of plastics of types #3-#7 to generate new products (e.g., by recycling methods) and/or fuels. and/or sorting. Exemplary end uses of these fractions may include (but are not limited to) gases (e.g., C1 to C4), fuels (e.g., gasoline, diesel) and vacuum gas oils. However, sorting of plastics of types #3 to #7 based on organic and inorganic elemental compositions has never been performed successfully.

Embodiments of the present disclosure may be configured to sort pieces of plastic materials according to a variety of different predetermined fractions or combinations of properties or types, as disclosed below and elsewhere in the disclosure.

Plastics can be classified into three types according to their properties, chemical structure, polarity and applications.

According to their chemical structure and temperature behavior, plastics can be divided into thermoplastics, thermosets, and elastomers.

When atoms with different polarity properties exist, electrons in covalent bonds move toward the most electrically negative atom, creating a dipole. Polymers containing polar electronegative electrons such as CI, O, N, F, etc. can be polar compounds and thus affect the properties of the material. As polarity increases, mechanical resistance, hardness, rigidity, heat resistance, water and moisture resistance, chemical resistance, as well as permeability to polar compounds such as water vapor, adhesion and adhesion to metals increase. At the same time, as polarity increases, thermal expansion, electrical insulating capacity, tendency to accumulate electrostatic charges and permeability to polar molecules (O ₂ , N ₂ ) decrease. In this way, it is possible to distinguish between different product groups such as polyolefins, polyesters, acetals, halogenated polymers, etc.

The third classification applies to thermoplastic materials depending on the application. There are four types of plastics in this third category:

Standard plastics or products: Plastics that are manufactured and used in large quantities due to their cost and many other excellent properties. Some examples include polyethylene (“PE”), polypropylene (“PP”), polystyrene (“PS”), polyvinyl chloride (“PVC”), or the copolymer acrylonitrile butadiene styrene (“ABS”).

Engineering plastics: Used where excellent structure, transparency, self-lubrication and thermal properties are required. Some examples include polyamide (“PA”), polyacetal (“POM”), polycarbonate (“PC”), polyethylene terephthalate (“PET”), polyphenylene ether (“PPE”), and polybutylene ether. There are phthalates (“PBT”).

Specialty plastics: These plastics have a superior degree of special properties, such as polymethyl methacrylate (PMMA), which has high transparency and light stability, or polytetrafluoroethylene (Teflon), which has excellent resistance to temperature and chemicals. .

High-performance plastics: Mostly thermoplastics with high heat resistance. That is, these plastics have excellent mechanical resistance, especially to high temperatures of up to 150°C. Polyimide (“PI”), polysulfone (“PSU”), polyethersulfone (“PES”), polyarylsulfone (“PAS”), polyphenylene sulfide (“PPS”) and liquid crystal polymers (“LCP”) ") These are high-performance plastics.

Many plastic items have symbols identifying the type of polymer from which they are manufactured. These resin identification codes, often abbreviated RIC, are used internationally. There are a total of 7 codes, 6 for the most common types of commodity plastics and 1 code that covers everything else. These types are also referred to herein as polymer types #1 to #7. Polymer type #1 refers to polyethylene terephthalate ("PET"), #2 refers to high-density polyethylene ("HDPE"), #3 refers to polyvinyl chloride ("PVC"), and #4 refers to low-density polyethylene ("PVC"). #5 refers to polypropylene ("PP"), #6 refers to polystyrene ("PS"), #7 refers to other polymers not in polymer types #1 through #6 (e.g. For example, acrylic, polycarbonate ("PC"), polyactic fibers, polylactide, nylon, fiberglass, and ABS). The EU maintains a similar list of nine codes that also includes ABS and polyamides.

PET plastic is used to make many common household items such as beverage bottles, medicine bottles, rope, clothing and carpet fibers. HDPE plastic is frequently used to make containers for milk, motor oil, shampoos and conditioners, soap bottles, detergent, and bleach. PVC is used in all types of pipes and tiles and is most commonly found in plumbing pipes. LDPE products include cling film, sandwich bags, squeeze bottles, and plastic grocery bags. PP is used to make lunch boxes, margarine containers, yogurt containers, syrup bottles, prescription bottles and plastic bottle caps. Polystyrene items include disposable coffee cups, plastic food boxes, plastic cutlery and packaging foam. Polycarbonate is used in baby bottles, compact discs and medical storage containers. Accordingly, according to embodiments of the present disclosure, a vision system implemented with a machine learning system can be trained to identify and sort these different types of plastics based on the type of product manufactured.

Plastic pieces can be classified according to the types of additives they may contain. Additives are compounds that are mixed into plastics to improve performance and include stabilizers, fillers and dyes. Clear plastics are the most valuable because they have not yet been dyed, but black or strongly colored plastics are much less valuable because their inclusion can discolor the product. Therefore, plastics may need to be sorted by polymer type and color to provide materials suitable for recycling.

Plastics may be sorted and sorted based on density. Certain polymers have similar density ranges (for example, PP and PE, or PET, PS and PVC). A high percentage of filler in a piece of plastic can affect its density.

Plastic waste can be broadly divided into two categories: industrial scrap (also known as post-industrial resin) and post-consumer waste.

Plastic pieces can also be sorted/sorted according to recycling method. During mechanical recycling, plastics can be reprocessed at 150 to 320 degrees Celsius depending on the polymer type, and this process can cause unwanted chemical reactions that can cause polymer decomposition. This can degrade the physical properties and overall quality of the plastic, generate volatile low molecular weight compounds that can impart undesirable tastes or odors, as well as cause thermal discoloration. Accordingly, embodiments of the present disclosure may be configured to sort and sort plastic pieces to avoid these unwanted chemical reactions. Additives present in plastics can accelerate this deterioration. For example, oxidative biodegradability additives to improve the biodegradability of plastics can increase the degree of thermal decomposition. Likewise, flame retardants can have unwanted effects. Accordingly, embodiments of the present disclosure may be configured to sort and sort the plastic pieces so that plastic pieces containing certain of these additives are discarded.

The quality of a product can vary greatly depending on how well the plastic is sorted. Many polymers are immiscible when melted and their phases separate (like oil and water) during reprocessing. Products made from these blends contain many boundaries between different polymer types and have poor mechanical properties due to poor cohesion across these boundaries. Accordingly, embodiments of the present disclosure may be configured to sort and sort plastic pieces such that certain unmixed plastic pieces are not sorted together into the same group.

In accordance with certain embodiments of the disclosure, the systems and methods described herein accommodate a heterogeneous mixture of a plurality of material pieces (e.g., any combination of the various plastics disclosed herein), the heterogeneous mixture At least one piece of material within the heterogeneous mixture contains a composition of elements (e.g., chemical signature) that is different from that of one or more other pieces of material, and/or at least one piece of material within this heterogeneous mixture is distinguishable from the other pieces of material. (e.g., visually discernible properties or characteristics, different chemical signatures, etc.), and systems and methods may be used to identify/classify/sort this piece of material into a group separate from other such pieces of material. It is composed. Embodiments of the present disclosure may be utilized to sort any types or classes of materials or fractions as defined herein.

Embodiments of the present disclosure physically deposit (e.g., convert or convert) pieces of material into separate receptacles or bins as a function of user-defined groupings (e.g., material type classifications or fractions). discharge) and sorting the material pieces into such separate groups will be described herein. As an example, within certain embodiments of the present disclosure, pieces of material may have physical characteristics that are distinguishable from the physical properties (e.g., visually discernible properties or characteristics, different chemical signatures, etc.) of other pieces of material. It can be sorted into separate bins to separate pieces of material with properties.

1 illustrates an example of a system 100 constructed in accordance with various embodiments of the present disclosure. Conveyor system 103 is implemented to convey one or more streams of individual pieces of material 101 through system 100 so that each of the individual pieces of material 101 can be tracked, sorted, and sorted into predetermined desired groups. there is. This conveyor system 103 may be implemented as one or more conveyor belts along which pieces of material 101 typically move at a constant predetermined speed. However, certain embodiments of the present disclosure may be used in systems where pieces of material freely fall past the various components of system 100 (or any other type of vertical sorter) or other types of conveyor systems, including vibratory conveyor systems. can be implemented with Hereinafter, where applicable, conveyor system 103 may also be referred to as conveyor belt 103. In one or more embodiments, some or all of the transport, stimulation, detection, sorting, and sorting acts may be performed automatically, i.e., without human intervention. For example, in system 100, one or more sources of stimuli, one or more emission detectors, a classification module, a sorting device and/or other system components may be configured to automatically perform these and other tasks.

Additionally, while FIG. 1 illustrates a single flow of material pieces 101 on conveyor system 103, embodiments of the present disclosure allow multiple flows of such material pieces to flow through various components of system 100 in parallel. It can be implemented by passing through them. For example, as further described in U.S. Pat. No. 10,207,296, the pieces of material may be distributed into two or more parallel single streams traveling on a single conveyor belt or set of parallel conveyor belts. As such, certain embodiments of the present disclosure are capable of simultaneously tracking, sorting, and sorting these flows of multiple, parallel moving pieces of material. According to certain embodiments of the present disclosure, integration or use of a singulator is not necessary. Instead, the conveyor system (e.g., conveyor system 103) may simply convey clumps of randomly deposited material pieces onto conveyor system 103.

According to certain embodiments of the present disclosure, some suitable type of feeder mechanism (e.g., another conveyor system or hopper 102) may be utilized to feed material pieces 101 to conveyor system 103. The conveyor system 103 may transport material pieces 101 past various components within the system 100. After the pieces of material 101 are received by the conveyor system 103, an optional tumbler/vibrator/singulator 106 may be utilized to separate individual pieces of material from the collection of material pieces. Within certain embodiments of the present disclosure, conveyor system 103 is operated to move at a predetermined speed by conveyor system motor 104. This predetermined speed can be programmed and/or adjusted by the operator in any well known manner. Monitoring of the predetermined speed of the conveyor system 103 may alternatively be performed using a position detector 105. Within certain embodiments of the present disclosure, control of conveyor system motor 104 and/or position detector 105 may be performed by automated control system 108. This automated control system 108 may operate under the control of computer system 107 and/or functions for performing automated control may be implemented in software within computer system 107.

Conveyor system 103 may be a conventional endless belt conveyor employing a conventional drive motor 104 suitable for moving the belt conveyor at a predetermined speed. A position detector 105, which may be a conventional encoder, may be operatively coupled to the conveyor system 103 and the automated control system 108 to provide information corresponding to the movement (e.g., speed) of the conveyor belt. . Accordingly, as further described herein, through utilization of controls for the conveyor system drive motor 104 and/or automated control system 108 (and alternatively including position detector 105), the conveyor Once each of the pieces of material 101 moving on the system 103 is identified, it can be tracked by location and time (relative to the various components of the system 100) so that each piece of material 101 has its own Various components of system 100 may be activated/deactivated as they pass through the vicinity. As a result, the automated control system 108 can track the position of each piece of material 101 as it moves along the conveyor system 103.

Referring back to FIG. 1 , certain embodiments of the present disclosure may utilize a vision or optical recognition system 110 and/or a piece of material as a means to track each piece of material 101 as it moves on the conveyor system 103. The tracking device 111 may be utilized. Vision system 110 may utilize one or more stationary or live action cameras 109 to record the position (i.e., location and timing) of each piece of material 101 on moving conveyor system 103. Vision system 110 may be additionally or alternatively configured to perform identification (e.g., classification) of specific types of all or some of the pieces of material 101, as further described herein. . For example, such vision system 110 may be utilized to capture or obtain information about each of the pieces of material 101 . For example, vision system 110 may classify material pieces 101 as a function of a set of one or more properties (e.g., physical and/or chemical and/or radioactive, etc.) as described herein. and/or may be configured (e.g., with a machine learning system) to capture or collect any type of information from pieces of material that may be utilized within system 100 to selectively sort. According to certain embodiments of the present disclosure, the vision system 110 may create visual images (one-dimensional) of each of the pieces of material 101 using, for example, optical sensors utilized in typical digital cameras and video equipment. , including two-dimensional, three-dimensional, or holographic imaging. These visual images captured by the optical sensor are stored as image data in a memory device (eg, formatted as image data packets). In accordance with certain embodiments of the present disclosure, such image data may represent images captured within optical wavelengths of light (i.e., wavelengths of light observable to a typical human eye). However, alternative embodiments of the present disclosure may utilize sensor systems configured to capture images of materials comprised of wavelengths of light outside the visual wavelengths of the human eye.

According to certain embodiments of the present disclosure, system 100 may be implemented with one or more sensor systems 120, which may operate independently with vision system 110 to classify/identify material pieces 101. Or, it can be used in combination. Sensor system 120 utilizes irradiated or reflected electromagnetic radiation (e.g., infrared (“IR”), Fourier transform IR (“FTIR”), forward infrared (“FLIR”), and very near infrared (“VNIR”). ), near-infrared (“NIR”), short-wave infrared (“SWIR”), long-wave infrared (“LWIR”), mid-wave infrared (“MWIR” or “MIR”), X-ray transmission (“XRT”), gamma rays, Ultraviolet (“UV”), Chemical signatures of plastic pieces, including sensor systems utilizing (to any extent), acoustic spectroscopy, NMR spectroscopy, microwave spectroscopy, terahertz spectroscopy, and any one of these, one-dimensional, two-dimensional, or three-dimensional imaging. It may be configured by any type of sensor technology to determine and/or classify plastic pieces for sorting, or any other type of sensor technology, including but not limited to chemical or radiological. Implementations of an exemplary XRF system (e.g., for use as sensor system 120 herein) are further described in U.S. Pat. No. 10,207,296. Within embodiments of the present disclosure, XRF may be used to identify inorganic materials within a piece of plastic (e.g., to incorporate within a chemical signature).

The sensor systems below may also be used within certain embodiments of the present disclosure to determine chemical signatures of plastic pieces and/or sort the plastic pieces for sorting.

The various forms of infrared spectroscopy previously disclosed allow the specific chemical chemistry of each piece of plastic to provide information not only about the base polymer of any plastic material, but also about other components present in the material (mineral fillers, copolymers, polymer mixtures, etc.). It can be used to obtain a signature.

Differential scanning calorimetry (“DSC”) is a thermal analysis technique that obtains, for each material, the heat transitions that occur during heating of the analyzed material.

Thermogravimetric analysis (“TGA”) is another thermal analysis technique that provides quantitative information about the composition of plastic materials in terms of polymer proportions, other organic components, mineral fillers, carbon black, etc.

Capillary and rotational rheology can determine the rheological properties of polymeric materials by measuring creep and strain resistance.

Optical and scanning electron microscopy (“SEM”) determines the number and thickness of layers of multilayer materials (e.g., multilayer polymer films), the size of the dispersion of pigment or filler particles in the polymer matrix, coating defects, and phase separation between components. It can provide information on the structure of the analyzed substances in relation to their form, etc.

Chromatography (e.g. LC-PDA, LC-MS, LC-LS, GC-MS, GC-FID, HS-GC) can be used to detect residual monomers, residual solvents in inks or adhesives, decomposition products, etc. Additionally, minor components of plastic materials such as UV stabilizers, antioxidants, plasticizers, anti-slip agents, etc. can be quantified.

Although Figure 1 illustrates a combination of a vision system 110 and one or more sensor systems 120, embodiments of the present disclosure may be used in any of the sensor technologies disclosed herein or any currently available or developed in the future. It should be noted that any combination of sensor systems utilizing different sensor technologies can be implemented. 1 is illustrated as including one or more sensor systems 120, implementation of such sensor system(s) is optional within certain embodiments of the present disclosure. Within certain embodiments of the present disclosure, a combination of both vision system 110 and one or more sensor systems 120 may be used to classify material pieces 101 . Within certain embodiments of the present disclosure, any combination of one or more of the different sensor technologies disclosed herein may be used to sort the pieces of material 101 without using the vision system 110. Additionally, embodiments of the present disclosure allow the outputs of these sensor/vision systems to be processed within a machine learning system (as further disclosed herein) to classify/identify materials from a mixture of heterogeneous materials and then sort them together. It may include any combination of one or more sensor systems and/or vision systems.

According to alternative embodiments of the present disclosure, vision system 110 and/or sensor system(s) may detect material pieces 101 that are not the type to be sorted by system 100 (e.g., certain contaminants). configured to identify pieces of plastic containing additives, or undesirable physical features (e.g., adhesive container caps formed of a different type of plastic than the container) and transmit a signal to reject pieces of such material. It can be. In this configuration, the identified pieces of material 101 may be diverted/discharged utilizing one of the mechanisms, such as those described below, to physically divert the sorted pieces of material into individual bins.

Within certain embodiments of the present disclosure, the piece of material tracking device 111 and accompanying control system 112 are configured to determine the position (i.e., location and timing) of each piece of material 101 on the moving conveyor system 103. Together, the piece of material tracking device 111 may be utilized and configured to measure the sizes and/or shapes of each of the pieces of material 101 passing within the vicinity. Exemplary operation of this piece of material tracking device 111 and control system 112 is further described in U.S. Pat. No. 10,207,296. Alternatively, as previously disclosed, vision system 110 may be utilized to track the position (i.e., location and timing) of each piece of material 101 as it is transported by conveyor system 103. . As such, certain embodiments of the present disclosure may be implemented without a piece of material tracking device (e.g., piece of material tracking device 111) for tracking the pieces of material.

Within certain embodiments of the present disclosure that implement one or more sensor systems 120, sensor system(s) 120 may allow vision system 110 to pass within proximity of sensor system(s) 120. When material pieces 101 may be configured to assist in identifying the chemical composition, relative chemical compositions, and/or manufacturing types of each. Sensor system(s) 120 may include an energy discharge source 121 , which may be driven, for example, by a power supply 122 to stimulate a response from each of the material pieces 101 . there is.

According to certain embodiments of the present disclosure that implement an XRF system as sensor system 120, source 121 is an in-line ) may include a tube. Such IL-XRF tubes may include separate x-ray sources each dedicated to one or more streams (e.g., singulated) of transported material pieces. In this case, one or more detectors 124 may be implemented as XRF detectors for detecting fluorescence x-rays from the material pieces 101 within each of the unified flows. Examples of such XRF detectors are further described in US Pat. No. 10,207,296.

Within certain embodiments of the present disclosure, as each of the pieces of material 101 passes in close proximity to the emission source 121, the sensor system 120 may emit an appropriate detection signal toward the pieces of material 101. You can. One or more detectors 124 may be positioned and configured to sense/detect one or more properties from the piece of material 101 in a form suitable for the type of sensor technology utilized. One or more detectors 124 and associated detector electronics 125 capture these received sensed characteristics, perform signal processing, and generate digitized information representative of the sensed characteristics (e.g., spectral data). This information is then analyzed according to certain embodiments of the present disclosure, which may be used by the vision system 110 to assist in classification of each of the material pieces 101. This sorting, which may be performed within the computer system 107, involves sorting the material pieces 101 according to the determined classifications into one or more N (N ≥ 1) sorting bins 136...139 (e.g. , switching/discharging) can be used by the automated control system 108 to activate one of N (N > 1) sorting devices 126...129. In Figure 1 four sorting devices 126...129 and four sorting bins 136...139 associated with the sorting devices are illustrated as a non-limiting example only.

Existing plastics sorters are designed to sort materials in a binary manner, with air nozzles at the end of the conveyor discharging the identified classes of plastics into one of two bins. For example, if you need to separate four classes of plastic, you have to pass the entire flow through this binary sorter four different times, which takes four times more time than removing a single object from the flow. . According to embodiments of the present disclosure, system 100 may sort multiple classes of plastics at once.

The sorting device may be configured to include any device for redirecting selected pieces of material 101 to a desired location, including but not limited to diverting the pieces of material 101 from a conveyor belt system to a plurality of sorting bins. May include well-known mechanisms. For example, a sorting device may utilize air jets, each of which may be assigned to one or more classifications. When one of the air jets (e.g., 127) receives a signal from the automation control system 108, it moves the material pieces 101 from the conveyor system 103 into a sorting bin corresponding to that air jet. (e.g. 137) to divert/blow out the air stream.

The pieces of material can be robotically removed from the conveyor belt, the pieces of material can be pushed off the conveyor belt (e.g., using paint brush type plungers), or an opening in the conveyor system 103 through which the material pieces can fall (e.g. For example, trap doors) or other mechanisms can be used to divert/discharge the material pieces, such as using air jets to divert the material pieces into separate bins as they fall from the edge of the conveyor belt. As the term is used herein, a pusher device is any type of device that can be activated to dynamically displace an object on or from a conveyor system/device, including any suitable type of mechanical pushing mechanism (e.g. It may refer to a device that does this using pneumatic, mechanical, or other means, such as an ACME screw drive), a pneumatic pushing mechanism, or an air jet pushing mechanism. Some embodiments may include multiple pusher devices located at different locations along the path of the conveyor system and/or having different transition path orientations. In a variety of different implementations, these sorting systems described herein can determine which pusher device (if any) to activate based on classifications of material pieces performed by a machine learning system. Additionally, the determination of which pusher device to activate may be based on the detected presence and/or characteristics of other objects that may be within the transition path of the pusher device at the same time as the target article. Additionally, even in the case of facilities where singulation along the conveyor system is not perfect, the disclosed sorting systems can recognize cases where multiple objects are not well singulated and determine which pusher device is best for separating potentially adjacent objects. It is possible to dynamically select from a plurality of pusher devices that should be activated based on whether they provide a transition path. In some embodiments, objects identified as target objects may represent material that should be diverted from the conveyor system. In other embodiments, objects identified as target objects represent materials that should remain in the conveyor system so that non-target materials are diverted instead.

In addition to the N sorting bins 136...139 into which the material pieces 101 are diverted/discharged, the system 100 is configured to transfer from the conveyor system 103 to any of the foregoing sorting bins 136...139. It may further include a receptacle or bin 140 for receiving material pieces 101 that are not converted/discharged. For example, if the sorting of a piece of material 101 is not determined (or simply because the sorting devices did not properly divert/discharge the piece), the piece of material 101 is transferred from the conveyor system 103 into the N sorting bins. It may not be converted/discharged to one of (136...139). Accordingly, bin 140 may act as a primary receptacle where unsorted pieces of material are discarded. Alternatively, bin 140 may be used to accommodate one or more classifications of material pieces that are not intentionally assigned to any of the N sorting bins 136...139. These material pieces can then be further sorted according to other properties and/or by other sorting systems.

Depending on the various classifications of desired material pieces, multiple classifications can be mapped to a single sorting device and associated sorting bin. That is, there need not be a one-to-one correlation between categories and sorting bins. For example, a user may wish to sort certain classes of materials into the same sorting bin (e.g., different plastic types falling within a fraction). To achieve this sorting, if a piece of material 101 is classified as belonging to a group of predetermined classes (e.g., a fraction), the same sorting device may be activated to sort them into the same sort bin. This combinatorial sorting can be applied to create any desired combination of sorted material pieces. The mapping of categories may be programmed by the user (e.g., using a sorting algorithm operated by computer system 107 (e.g., see FIG. 7)) to generate such desired combinations. Additionally, classifications of material fractions may be user-defined and are not limited to any particular known classifications of material fragments (eg, fractions disclosed herein).

Conveyor system 103 may include a circular conveyor (not shown) such that unsorted pieces of material are returned to the beginning of system 100 and passed through system 100 again. Additionally, because system 100 can specifically track each piece of material 101 moving on conveyor system 103, some type of sorting device (e.g., sorting device 129) may be implemented. After a predetermined number of cycles through system 100, system 100 may induce/discharge material pieces 101 that fail to sort (or material pieces 101 are collected in bin 140). .

Within certain embodiments of the present disclosure, the conveyor system 103 may be divided into multiple belts configured in series, for example two belts, where the first belt carries the vision system 110. The second belt conveys the specifically sorted pieces of material past the sensor system 120 implemented for the second sorting. Additionally, this second conveyor belt may be located at a lower height than the first conveyor belt, allowing pieces of material to fall from the first belt to the second belt.

Within certain embodiments of the present disclosure implementing sensor system 120, emission source 121 may be located above the detection area (i.e., above conveyor system 103); Certain embodiments of the present disclosure may place the emission source 121 and/or detectors 124 in other positions that still produce acceptable sensed/detected physical characteristics.

The systems and methods described herein may be applied to sorting and/or sorting individual pieces of material of any of a variety of sizes and shapes. Although the systems and methods described herein have been primarily described with respect to sorting individual pieces of material, the systems and methods described herein are not limited thereto. These systems and methods can be used to stimulate and/or detect emissions from multiple substances simultaneously. For example, unlike a singulated flow of materials conveyed in series along one or more conveyor belts, multiple singulated flows may be conveyed in parallel. Each flow may be on the same belt or on different belts arranged in parallel. Additionally, the pieces may be randomly distributed on one or more conveyor belts (eg, generally along the conveyor belt). Accordingly, the systems and methods described herein can be used to stimulate multiple pieces of material simultaneously and/or detect emissions from multiple pieces of material. In other words, multiple pieces of material can be treated as a single piece as opposed to each piece of material being considered individually. Accordingly, multiple pieces of material can be sorted and sorted (eg, diverted/discharged from a conveyor system) together.

Although the systems and methods described herein have been primarily described in the context of sorting pieces of material, these systems and methods are not limited to that application. It may be used for other applications, such as identifying elements (e.g., contaminants) within a piece of material or determining the composition of the piece of material.

As previously mentioned, certain embodiments of the present disclosure may implement one or more vision systems (e.g., vision system 110) to identify, track, and/or classify pieces of material. According to embodiments of the present disclosure, such vision system(s) operate alone to identify and/or classify and/or sort the pieces of material, or operate alone to identify and/or classify and/or sort the pieces of material. It can operate in combination with the above sensor systems (e.g., sensor system(s) 120). If a sorting system (e.g., system 100) is configured to operate solely with such vision system(s) 110, sensor system(s) 120 may be omitted from system 100 (or , can simply be disabled).

Regardless of the type(s) of sensed characteristics/information captured about the pieces of material, the information (e.g., image data packets) is transmitted to a machine learning system to identify and/or classify each piece of material. and may be transmitted to a computer system (e.g., computer system 107) for processing. These machine learning systems include neural networks (artificial neural networks, deep neural networks, convolutional neural networks, recurrent neural networks, autoencoders, reinforcement learning, etc.), fuzzy logic, artificial intelligence (“AI”), deep learning algorithms, deep structure learning, layered learning algorithms. , support vector machines (“SVM”) (e.g., linear SVM, nonlinear SVM, SVM regression, etc.), decision tree learning (e.g., classification and regression tree (“CART”)), ensemble methods ( For example, ensemble learning, random forests, bagging and pasting, patches and subspaces, boosting, stacking, etc.), dimensionality reduction (e.g. projection, manifold learning, principal component analysis, etc.) and/or For example, a system implementing deep machine learning algorithms, such as those described and publicly available on the deeplearning.net website (including all software, publications and hyperlinks to available software referenced within this website) Any well-known machine learning system may be implemented, including, which is incorporated herein by reference. Non-limiting examples of publicly available machine learning software and libraries that can be utilized within embodiments of the present disclosure include Python, OpenCV, Inception, Theano, Torch, PyTorch, Pylon2, Numpy, Blocks, TensorFlow, MXNet, Caffe, Lasagna, Keras, Chainer, Matlab deep learning, CNTK, MatConvNet (MATLAB toolbox for implementing convolutional neural networks for computer vision applications), DeepLearnToolbox (Matlab toolbox for deep learning) 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, Eblearn, cudamat, Gnumpy, 3-way factored RBM and mcRBM, mPoT (Python code using CUDAMat and Gnumpy to train models of natural images), Includes ConvNet, Elektronn, OpenNN, NeuralDesigner, Theano Generalized Hebbian Learning, Apache Singa, Lightnet, and SimpleDNN.

According to certain embodiments of the present disclosure, machine learning may be performed in two stages. For example, training may first be performed offline where system 100 is not utilized to perform the actual sorting/sorting of the material pieces (see, e.g., Figures 3-4). System 100 allows homogeneous sets of material pieces (also referred to herein as control samples) (i.e., having the same types or classes of materials or falling within the same predetermined fraction) to pass through system 100 and (e.g., by conveyor system 103); All such material pieces may be used to train a machine learning system in which all pieces of material are not sorted but can be collected into a common bin (e.g., bin 140). Alternatively, training may be performed at another location remote from system 100, including using some other mechanism for gathering sensed information (properties) of control sets of material pieces. During this training stage, algorithms within the machine learning system extract features from the captured information (e.g., using image processing techniques well known in the art). Non-limiting examples of training algorithms include (but are not limited to) linear regression, gradient descent, feed forward, polynomial regression, learning curves, regularized learning models, and logistic regression. In this training stage, the algorithms within the machine learning system learn relationships between materials and their features/properties (e.g., as captured by a vision system and/or sensor system(s)), thereby creating a system ( 100), which creates a knowledge base for later classifying the heterogeneous mixture of material pieces received, which can then be sorted by desired classifications. This knowledge base may include one or more libraries, each library containing parameters (e.g., neural network parameters) for use by a machine learning system to classify material pieces. For example, one particular library may include parameters configured by the training stage to recognize and classify one or more substances corresponding to a particular type or class of substance or a predetermined fraction. According to certain embodiments of the present disclosure, such libraries may be input to a machine learning system, and a user of system 100 may adjust certain of the parameters to adjust the operation of system 100 (e.g. For example, adjusting the threshold effect on how well a machine learning system recognizes a particular piece of material from a mixture of disparate materials).

As depicted in FIG. 2 , during the training stage, a plurality of material pieces 201 of material(s) of one or more specific types, classes or fractions that are control samples are transferred to a vision system and/or one or more sensor systems ( s) (e.g., via conveyor system 203) to allow algorithms within a machine learning system to detect, extract, and learn features indicative of that type or class of material. For example, each of the pieces of material 201 may be an individual piece of plastic of a particular type, class or predetermined fraction, and passing through this training stage allows the algorithms within the machine learning system to detect, recognize and recognize such pieces of plastic accordingly. Let them “learn” (train) how to classify. When training a vision system (e.g., vision system 110), it is trained to visually distinguish between pieces of material. This creates a library of parameters specific to one or more specific types, classes or fractions of plastic materials. The same process can then be performed on different types, classes or fractions of plastic pieces to create a library of parameters specific to those types, classes or fractions. For each type, class or fraction of plastic to be classified by the machine learning system, any number of exemplary plastic pieces of that type, class or fraction of plastic may be passed through the system. Given captured sensory information as input data, algorithms within a machine learning system can use N classifiers, each of which tests one of N different material types, classes or fractions. A machine learning system can be “learned” (trained) to detect all types, classes or fractions of substances, including all types, classes or fractions of substances found in MSW or any other substance disclosed herein. It should be noted that there is.

After the algorithms are established and the machine learning system has sufficiently learned (e.g., trained) the differences (e.g., visually discernible differences) for the material classes (e.g., within a user-defined statistical confidence level), Libraries for different material classes can be implemented into a material classification/sorting system (e.g., system 100) to identify and identify material pieces from a heterogeneous mixture of material pieces (e.g., as contained within an MSW). /or used to classify, and then sort such classified material pieces when sorting is performed.

Techniques for configuring, optimizing and utilizing machine learning systems are known to those skilled in the art as can be found in the relevant literature. Examples of such literature include Krizhevsky et al., “ ImageNet Classification with Deep Convolutional Networks ,” Proceedings of the 25th International Conference on Neural Information Processing Systems, Dec. 3-6, 2012, Lake Tahoe, Nev.] and LeCun et al., " Gradient-Based Learning Applied to Document Recognition ," Proceedings of the IEEE, Institute of Electrical and Electronic Engineers (IEEE), November 1998. The same publications are included, both of which are hereby incorporated by reference in their entirety.

In one example technique, data captured by a vision or sensor system regarding a particular piece of material may be stored in a data processing system (e.g., data processing system 3400 of FIG. 9) that implements (consists of) a machine learning system. (e.g., data may be captured by a digital camera or other type of sensor system in association with a particular piece of material and processed as an array of data values (e.g., an image data packet) Each data value can be expressed as a single number or as a series of numbers representing the values. These values can be multiplied by neuron weight parameters (e.g., using a neural network). A bias can be added. This value can be fed to the neuron nonlinearity. The result output by the neuron is multiplied by the subsequent neuron weight values and the optionally added bias, and then Each iteration of this process is called a "layer" of the neural network. The final outputs of the final layer are obtained from captured data associated with a piece of material, such that the material is present or not. They can be interpreted as non-existent probabilities. Examples of these processes are described in detail in the previously mentioned references "ImageNet Classification Using Deep Convolutional Networks" and "Gradient-Based Learning Applied to Document Recognition".

According to certain embodiments of the present disclosure in which a neural network is implemented, as a final layer (“classification layer”), a final output set of neurons is trained to indicate the likelihood that a piece of material is associated with the captured data. During operation, if the probability that a piece of material is associated with captured data exceeds a user-specified threshold, it is determined that the piece of material is actually associated with captured data. These techniques can be extended to determine not only the presence or absence of a material type associated with specific captured data, but also whether sub-regions of specific captured data belong to one type of material or a different type of material. This process is called segmentation, and techniques exist in the literature using neural networks, such as "fully convolutional" neural networks or networks that are not fully convolutional but contain a convolutional part (i.e., partially convolutional). Through this, the location and size of the material can be determined.

It should be understood that this disclosure is not limited to machine learning techniques. Other common techniques for material classification/identification may also be used. For example, a sensor system may utilize optical spectroscopy techniques using multiple or hyperspectral cameras to examine the spectral emissions of a substance (i.e., spectral imaging), thereby producing a signal that can indicate the presence or absence of a type, class, or fraction of the substance. can be provided. Spectral images of a piece of material can also be used in a template matching algorithm, where a database of spectral images is compared with the obtained spectral image to find out whether certain types of materials are present. The histogram of the captured spectral image can also be compared with a database of histograms. Similarly, the bag of words model can be used with feature extraction techniques such as scale-invariant feature transformation (“SIFT”) to compare the extracted features between captured spectral images and features in a database.

Accordingly, as disclosed herein, certain embodiments of the present disclosure identify one or more different types, classes or fractions of materials to determine which pieces of material should be diverted from the conveyor system into defined groups. Provides classification. According to certain embodiments, machine learning techniques are utilized to train (i.e., configure) a neural network to identify various one or more different types, classes, or fractions of substances. Spectral images or other types of sensed information are captured from materials (e.g., moving on a conveyor system), and based on the identification/classification of these materials, the systems described herein can determine which piece of material is on the conveyor. It can be determined which pieces of material should be allowed to remain in the system and which pieces of material should be diverted/removed from the conveyor system (e.g., diverted to a collection bin or to another conveyor system).

According to certain embodiments of the present disclosure, a machine learning system for an existing facility (e.g., system 100) replaces a current set of neural network parameters with a new set of neural network parameters to generate new types, classes, or fractions of substances. Can be dynamically reconfigured to identify/classify characteristics.

One point to note here is that, according to certain embodiments of the present disclosure, the detected/captured features/properties (e.g., spectral images) of pieces of material are not necessarily merely specifically identifiable or discernable physical properties. There is no need to spend; They may be abstract formulas that can only be expressed mathematically or not mathematically at all; Nonetheless, a machine learning system can be configured to parse spectral data to find patterns that can classify control samples during the training stage. Additionally, a machine learning system can take subsections of captured information (e.g., spectral images) of a piece of material and attempt to find correlations between predefined classes.

According to certain embodiments of the present disclosure, instead of utilizing a training stage where control samples of material pieces are passed by the vision system and/or sensor system(s), training of the machine learning system may be performed using data/information of the material pieces. This can be accomplished utilizing labeling/annotation techniques where the user enters a label or annotation identifying each piece of material as it is captured by a vision/sensor system, which allows the material to be classified within a mixture of disparate pieces of material. It can be used to create libraries for use in machine learning systems.

3-6, embodiments of the present disclosure utilize multiple sensor technologies (e.g., visual (“VIS”), , any combination of NIR and MWIR) can be combined or fused to allow sorting of plastics into organic and inorganic chemical components. However, because the sizes and shapes of these plastic pieces included in MSW are very different from each other, the signals generated by these different sensors can have large differences between sensors. Therefore, through a combination of machine learning and the convergence of various sensor technologies, the classification accuracy of these signals can be improved despite these large deviations. Because implementing multiple different sensors in a system can increase the cost of the system and also reduce the sorting speed, certain embodiments of the present disclosure require fewer sensors to sufficiently sort materials while increasing economics. A system (e.g., system 100) may be implemented with sensor systems (and therefore lower capital and operating costs).

4 shows a system in which pieces of material (e.g., pieces of plastic) 401 are transported by a conveyor system 403 past sensor system(s) that capture spectral data from each piece of material 401 ( For example, a simplified schematic diagram of system 100 is illustrated. In this non-limiting example, the sensor system(s) may include a camera 410 (e.g., vision system 110), an system 412 and MWIR system 413. However, it should be noted that any of the different sensor systems disclosed herein may be utilized in any combination.

3 and 4, chemical signatures of substances are determined in process block 301 using one or more sensor systems. Signals sensed/detected/captured from the sensor system(s) are combined (e.g., in a multidimensional data array) for each piece of material to create a chemical signature. An XRF sensor system can determine the presence of inorganic elements or molecules within plastic pieces, while a combination of one or more other sensor systems such as NIR and MWIR can determine the presence of organic elements or molecules within plastic pieces. We must remember that there is. At process block 302, a visible image of each piece of material is captured. At process block 303, the captured visible image (i.e., associated image data) of each piece of material is associated with a determined chemical signature (i.e., spectral image data). 5 and 6 illustrate non-limiting example representations of chemical signatures and associated image data for two different types of plastic materials—potato chip bags and electronic product packaging. As can be easily seen, different types or classes of plastic pieces will have different (unique) chemical signatures, which may lead to fractions and/or classifications for plastic waste within embodiments of the present disclosure ( It is used to create (can be defined by the user). According to embodiments of the present disclosure, controlling specific types or classes of plastic pieces via the system illustrated in FIG. 4 to train a machine learning system to associate a particular chemical signature with a particular type or class of plastic pieces. Groups can be run.

For example, with reference to the example illustrated in FIG. 5 , multiple bags of potato chips (which may include bags with different physical conditions or orientations or bags associated with different brands of chips and/or manufacturers) ) can be processed to train a machine learning system.

Process block 304 may include separating the plastic pieces into one or more fractions. There are several ways to produce these fractions. One way is to create a first tier based on major elements and then create second and even third tiers based on minor elements. For example, fractions may be determined first by polymer type and then branched by inorganic elements such as aluminum and zinc. The mixtures of polymers can then be made into different exemplary fractions and then branched by inorganic elemental composition. There are also computational methods that perform this type of clustering to determine fractions, such as principal component analysis, K-means clustering, and unsupervised and semi-supervised learning. Fractions are further defined herein.

At process block 305, after the fractions are determined, the plastic pieces associated with the fractions can be sorted (e.g., manually) to create a control group for each fraction. Since each fraction was measured with sensor system(s), each control group contains chemical information for the fractions. A vision system (e.g., vision system 110) can be used to train a machine learning system to identify these fractions. Using this method, the chemical data of the plastics is transmitted as visual features that a machine learning system can learn to classify. Additionally, when system 100 is used to perform classification based on visual images, it separates plastics by chemical composition. This method works when the two objects look different and have different chemical compositions. When two objects appear identical or very similar but have different chemical compositions, classification can be performed using two or more sensor systems (e.g., VIS and XRF).

Because the determined fractions may contain any of a desired variety of specific organic and/or inorganic elements or molecules, process 300 trains a machine learning system implemented within the sorting system to determine the types of fractions of one or more different types or classes. It can be utilized to arrange for sorting a heterogeneous mixture of different plastic pieces to produce at least one fraction comprising the plastic pieces. For example, if a machine learning system is trained to identify random pieces of plastic that contain a specific combination of organic and/or inorganic elements or molecules, once sorting is complete, the sorted fractions will contain pieces of plastic that are not all identical ( That is, each plastic chip bag is composed of organic and/or inorganic elements or molecules defined by predetermined fractions and thus may contain a plurality of plastic chip bags related to different brands of chips.

FIG. 7 illustrates a flowchart depicting example embodiments of a process 3500 for sorting/sorting pieces of material using a vision system and/or one or more sensor systems in accordance with certain embodiments of the present disclosure. Process 3500 may be performed to classify the heterogeneous mixture of plastic pieces into any combination of predetermined types, classes, and/or fractions. Process 3500 may be configured to operate within any of the embodiments of the disclosure described herein, including system 100 of FIG. 1 . The operation of process 3500 may be performed by a computer system (e.g., the computer of FIG. 9) that controls the system (e.g., computer system 107, vision system 110, and/or sensor system 120 of FIG. 1). It may be performed by hardware and/or software, including within system 3400). At process block 3501, pieces of material may be deposited on a conveyor system. At process block 3502, the location of each piece of material on the conveyor system is detected for tracking of each piece of material as it passes through system 100. This may be performed by the vision system 110 (e.g., by distinguishing the piece of material from the underlying conveyor system material while communicating with a conveyor system position detector (e.g., position detector 105)). Alternatively, a material tracking device 111 can be used to track the pieces. Alternatively, any system that can produce a light source (including but not limited to visible light, UV, IR) and has a detector that can be used to locate the pieces can be used. At process block 3503, as the piece of material moves in proximity to one or more of the vision system and/or sensor system(s), sensed information/characteristics of the piece of material are captured/obtained. At process block 3504, a vision system (e.g., implemented within computer system 107), such as previously disclosed, may perform pre-processing of the captured information, which may detect information about each of the pieces of material. (e.g., from a background (e.g., a conveyor belt); in other words, preprocessing may be utilized to identify differences between a piece of material and the background). Well-known image processing techniques such as dilation, thresholding, and contouring can be utilized to identify a piece of material as distinct from the background. At process block 3505, segmentation may be performed. For example, the captured information may include information related to one or more pieces of material. Additionally, certain pieces of material may be located at the seam of the conveyor belt when the image is captured. Therefore, in such cases it may be desirable to separate the images of individual pieces of material from the background of the image. In the example technique of process block 3505, the first step is to apply high contrast to the image; In this way, the background pixels are reduced to substantially all black pixels, and at least some of the pixels associated with the piece of material are brightened to substantially all white pixels. The image pixels of the white piece of material are then enlarged to cover the entire size of the piece of material. After this step, the location of the piece of material becomes a high-contrast image of all white pixels on a black background. A contouring algorithm can then be used to detect the boundaries of the material pieces. The boundary information is stored and the boundary positions are transferred to the original image. Segmentation is then performed on areas larger than the previously defined boundaries in the original image. In this way, pieces of material are identified and separated from the background.

In optional process block 3506, the pieces of material are conveyed within the vicinity of a piece of material tracking device and/or sensor system to track each of the pieces of material and/or determine the size and/or shape of the pieces of material. It can be transported along the system, which may be useful if an XRF system or some other spectroscopic sensor is implemented within the sorting system. In process block 3507, post-processing may be performed. Post-processing may include resizing the captured information/data to prepare it for use in a machine learning system. This may also include modifying certain characteristics (e.g., enhancing image contrast, changing the image background, or applying filters) in a way that improves the machine learning system's ability to classify material pieces. At process block 3509, the size of the data may be adjusted. Data sizing may be necessary in certain situations to fit the data input requirements for specific machine learning systems, such as neural networks. For example, neural networks may require image sizes that are much smaller than the sizes of images captured by typical digital cameras (eg, 225 x 255 pixels or 299 x 299 pixels). Additionally, the smaller the input data size, the less processing time is required to perform classification. Therefore, smaller data sizes can ultimately increase the throughput of the system 100 and increase its value.

In process blocks 3510 and 3511, each piece of material is identified/classified based on sensed/detected characteristics. For example, process block 3510 may consist of a neural network using one or more machine learning algorithms, which combines the extracted features into a previously generated (e.g., generated in a training stage) knowledge base. The stored features are compared, and based on that comparison, the classification with the highest match is assigned to each piece of material. Algorithms in a machine learning system can process captured information/data in a hierarchical manner using automatically learned filters. The filter responses are then successfully combined in the next levels of the algorithms until the probabilities are obtained in the final step. At process block 3511, these probabilities may be used for each of the N sorts to determine which of the N sorting receptacles the individual pieces of material should be sorted into. For example, each of the N classes may be assigned to one sorting receptacle, and the piece of material under consideration may be sorted into that receptacle corresponding to the class that returns the highest probability greater than a predefined threshold. Within embodiments of the present disclosure, such predefined thresholds may be preset by the user. If none of the probabilities are greater than a predetermined threshold, a particular piece of material may be sorted into an outlier receptacle (e.g., sorting receptacle 140).

Next, at process block 3512, a sorting device corresponding to the classification or classifications of the piece of material is activated. Between the time the image of the piece of material is captured and the time the sorting device is activated, the piece of material has moved from the proximity of the vision system and/or sensor system(s) to a location downstream of the conveyor system (e.g. depending on feed speed). In embodiments of the present disclosure, activation of the sorting device is such that when a piece of material passes through a sorting device mapped to a sort of material, the sorting device is activated and the piece of material is diverted/discharged from the conveyor system to the associated sorting receptacle. The timing is set. Within embodiments of the present disclosure, activation of the sorting device may be timed by an individual position detector that detects when a piece of material passes in front of the sorting device and transmits a signal enabling activation of the sorting device. there is. At process block 3513, a sorting receptacle corresponding to an activated sorting device receives the diverted/ejected material pieces.

8 illustrates a flowchart depicting example embodiments of a process 800 for sorting pieces of material in accordance with certain embodiments of the present disclosure. Process 800 may be configured to operate within any of the embodiments of the disclosure described herein, including system 100 of FIG. 1 . Process 800 may be configured to operate in conjunction with process 3500. For example, according to certain embodiments of the present disclosure, process blocks 803 and 804 may perform machine learning activities of a vision system 110 implemented with a machine learning system to classify and/or sort material pieces. to process block 3500 (e.g., operating in series or parallel with process blocks 3503-3510) for coupling with a sensor system (e.g., sensor system 120) that is not implemented with the system. can be integrated.

Operation of process 800 may include within a computer system (e.g., computer system 3400 of FIG. 9) that controls the system (e.g., computer system 107 of FIG. 1), using hardware and/or Can be performed by software. At process block 801, pieces of material may be deposited on a conveyor system. Next, in optional process block 802, the pieces of material are combined with a piece of material tracking device and/or an optical imaging system to track each piece of material and/or determine the size and/or shape of the pieces of material. It can be transported along a nearby conveyor system. At process block 803, once the piece of material has moved into close proximity to the sensor system, the piece of material may receive information via EM energy (waves) or some other type of stimulus appropriate for the particular type of sensor technology utilized by the sensor system. You can acquire or be stimulated. In process block 804, the physical properties of the piece of material are sensed/detected and captured by a sensor system. At process block 805, for at least some of the pieces of material, the type of material is identified/classified based (at least in part) on the captured characteristics, such that the classification by a machine learning system in conjunction with the vision system 110 can be combined with

Next, if sorting of the pieces of material is to be performed, at process block 806 a sorting device corresponding to the classification, or classifications, of the pieces of material is activated. Between the time a piece of material is detected and the time the sorting device is activated, the piece of material moves from the proximity of the sensor system to a location downstream of the conveyor system, depending on the conveyor system's transport speed. In certain embodiments of the present disclosure, activation of the sorting device is such that when a piece of material passes through a sorting device mapped to a sorting of the piece of material, the sorting device is activated and diverts/discharges the piece of material from the conveyor system to the associated sorting receptacle. Timing is determined as much as possible. Within certain embodiments of the present disclosure, activation of the sorting device may be timed by an individual position detector that detects when a piece of material passes in front of the sorting device and transmits a signal enabling activation of the sorting device. there is. At process block 807, a sorting receptacle corresponding to an activated sorting device receives the diverted/discharged material pieces.

According to certain embodiments of the present disclosure, at least a plurality of portions of system 100 may be connected together in series to perform multiple iterations or sorting layers. For example, when two or more systems 100 are connected in such a way, the conveyor system may be implemented with a single conveyor belt or multiple conveyor belts, sorting the pieces of material (e.g., a first automated A first vision system (and according to certain embodiments a sensor) configured to sort the first set of material pieces of the mixture of heterogeneous materials by means of a control system 108 and associated one or more sorting devices 126...129 system) into a first set of one or more receptacles (e.g., sorting bins 136...139), and then the material pieces are sorted into a second set of a mixture of heterogeneous materials by a second sorter. The pieces of material pass through a second vision system (and, according to certain embodiments, another sensor system) configured to sort and then pass into one or more sorting bins. Additional discussion of this multi-level sorting is in US Published Patent Application No. 2022/0016675, which is incorporated herein by reference.

These continuous systems 100 may include any number of such systems connected together in such a manner. According to certain embodiments of the present disclosure, each successive system may be configured to sort a different class or type of material than the previous system(s).

According to various embodiments of the present disclosure, different types, classes or fractions of materials can each be classified by different types of sensors for use with a machine learning system, and materials in a stream of scrap or waste. Pieces can be combined to sort them.

According to various embodiments of the present disclosure, data (e.g., spectral data) from two or more sensors may be combined using single or multiple machine learning systems to perform classification of material pieces.

According to various embodiments of the present disclosure, multiple sensor systems may be mounted on a single conveyor system, with each sensor system utilizing a different machine learning system. According to various embodiments of the present disclosure, multiple sensor systems may be mounted on different conveyor systems, and each sensor system may utilize a different machine learning system.

Certain embodiments of the present disclosure may be configured to produce a mass of materials having less than a predetermined weight or volume percentage of a particular element or material after sorting.

According to various embodiments of this disclosure, any combination of different types of sensor systems may be utilized to identify/classify, and possibly sort, materials as disclosed in this disclosure. For example, each imaging or spectroscopic sensor disclosed herein can be used to generate data from information/properties sensed in a piece of material for processing by a machine learning system specific to that sensor system. Alternatively, any sensor system may be used without processing by a machine learning system, with processing by a machine learning system, or a combination of the two.

According to various embodiments of the present disclosure, different types, classes and/or fractions of materials can each be classified by different types of sensor systems for use with a machine learning system, in a waste stream. Pieces of material can be combined to sort them.

Referring now to FIG. 9, a block diagram is depicted illustrating a data processing (“computer”) system 3400 in which aspects of embodiments of the present disclosure may be implemented. (The terms “computer,” “system,” “computer system,” and “data processing system” may be used interchangeably herein). Aspects of computer system 107, automation control system 108, sensor system(s) 120, and/or vision system 110 may be configured similarly to computer system 3400. Computer system 3400 may utilize a local bus 3405 (e.g., a Peripheral Component Interconnect (“PCI”) local bus architecture). Any suitable bus architecture may be used, such as Accelerated Graphics Port (“AGP”) and Industry Standard Architecture (“ISA”). One or more processors 3415, volatile memory 3420, and non-volatile memory 3435 may be coupled to local bus 3405 (e.g., via a PCI bridge (not shown)). An integrated memory controller and cache memory may be coupled to one or more processors 3415. One or more processors 3415 may include one or more central processor units and/or one or more graphics processor units 3401 and/or one or more tensor processing units. Additional connections to local bus 3405 may be made through direct component interconnection or add-in boards. In the depicted example, a communications (e.g., network (LAN)) adapter 3425, an I/O (e.g., Small Computer System Interface (“SCSI”) host bus) adapter 3430, and an expansion bus interface ( (not shown) may be connected to local bus 3405 via direct component connections. An audio adapter (not shown), a graphics adapter (not shown), and a display adapter 3416 (coupled to display 3440) (e.g., by add-in boards inserted into expansion slots) It may be connected to a local bus 3405.

User interface adapter 3412 may provide connections for a keyboard 3413 and mouse 3414, a modem (not shown), and additional memory (not shown). I/O input/output adapter 3430 may provide connections to a hard disk drive 3431, a tape drive 3432, and a CD-ROM drive (not shown).

An operating system may run on one or more processors 3415 and may be used to coordinate and control various components within computer system 3400. 9, the operating system may be a commercially available operating system. An object-oriented programming system (e.g., Java, Python, etc.) may run with an operating system, and may provide information about the operating system from programs or programs running on system 3400 (e.g., Java, Python, etc.). A call can be provided. Instructions for the operating system, object-oriented operating system, and programs may be located in non-volatile memory 3435 storage devices, such as hard disk drive 3431, and may be stored in volatile memory 3420 for execution by processor 3415. can be loaded.

Those skilled in the art will recognize that the hardware in FIG. 9 may vary depending on implementation. Other internal hardware or peripheral devices, such as flash ROM (or equivalent non-volatile memory) or optical disk drives, may be used in addition to or instead of the hardware depicted in FIG. 9. Additionally, any of the processes of this disclosure may be applied to a multiprocessor computer system, or may be performed by a plurality of such systems 3400. For example, training of the machine learning system may be performed by the first computer system 3400, and operation of the system 100 for sorting may be performed by the second computer system 3400.

As another example, computer system 3400 may be a standalone system that is configured to be bootable without relying on some type of network communication interface, regardless of whether computer system 3400 includes some type of network communication interface. . As a further example, computer system 3400 may be an embedded controller comprised of ROM and/or flash ROM that provides non-volatile memory to store operating system files or user-generated data.

The example depicted in FIG. 9 and the foregoing examples are not intended to imply structural limitations. Additionally, computer program form of aspects of the present disclosure may reside on any computer-readable storage medium (i.e., floppy disk, compact disk, hard disk, tape, ROM, RAM, etc.) used by a computer system.

As described herein, embodiments of the present disclosure may be implemented to perform various functions described for identifying, tracking, sorting, and/or sorting pieces of material. These functions may be implemented within hardware and/or software, such as aspects of the computer system 107, vision system 110, sensor system(s) 120, and/or automated control system 108, as previously mentioned. It may be implemented within one or more of the same data processing systems (e.g., data processing system 3400 of FIG. 9). Nonetheless, the functions described herein should not be limited for implementation on any particular hardware/software platform.

As those skilled in the art will appreciate, aspects of the present disclosure may be embodied as a system, process, method, and/or computer program product. Accordingly, various aspects of the disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or embodiments combining software and hardware aspects, which are generally described herein. may be referred to as a “circuit”, “network”, “module” or “system”. Additionally, aspects of the present disclosure may take the form of a computer program product embodied in one or more computer-readable storage medium(s) having computer-readable program code implemented 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, an electronic, magnetic, optical, electromagnetic, infrared, biological, atomic or semiconductor system, apparatus, controller or device, or any suitable combination of the foregoing. is not a temporary signal in itself. More specific examples of computer-readable storage media (a non-exhaustive list) include electrical connections having one or more wires, portable computer diskettes, hard disks, random access memory (“RAM”) (e.g., RAM 3420 of FIG. 9 )), read-only memory (“ROM”) (e.g., ROM 3435 in Figure 9), erasable programmable read-only memory (“EPROM” or flash memory), optical fiber, portable compact disk read-only memory. (“CD-ROM”), optical storage devices, magnetic storage devices (e.g., hard drive 3431 of FIG. 9), or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any tangible medium capable of containing or storing a program for use by or in connection with an instruction execution system, apparatus, controller or device. Program code embodied in a computer-readable signal medium may be transmitted using any suitable medium, including but not limited to wireless, wired, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

A computer-readable signal medium may include a propagated data signal embodying computer-readable program code, for example as part of a baseband or carrier wave. This propagated signal may take any of a variety of forms, including but not limited to electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium that is not a computer-readable storage medium and is capable of communicating, propagating or transmitting a program for use by or in connection with an instruction execution system, apparatus, controller or device. .

The flowchart and block diagrams in the drawings illustrate the architecture, functionality and operation of possible implementations of systems, methods, processes and program products in accordance with various embodiments of the present disclosure. In this regard, 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 to implement specified logical function(s). Additionally, it should be noted that in some implementations, functions shown in blocks may appear in a different order than the order shown in the drawings. For example, two blocks shown in succession may actually be executed substantially simultaneously, and sometimes the blocks may be executed in reverse order depending on the functionality involved.

In practice herein, flowchart techniques may be described as a series of sequential actions. The order of actions and the subject performing the actions may be freely changed without departing from the scope of the teachings. Actions can be added, deleted, or changed in several ways. Likewise, actions can be reordered or repeated. Additionally, although processes, methods, algorithms, etc. may be described in a sequential order, such processes, methods, algorithms, or any combination thereof, may be operable to be performed in alternative orders. Additionally, some actions within a process, method, or algorithm may be performed simultaneously (e.g., actions performed in parallel) for at least one point in time, and may be performed in whole, in part, or in any combination thereof.

Modules implemented in software to be executed by various types of processors (e.g., GPU 3401, CPU 3415) may be configured as, for example, objects, procedures, or functions. It may include physical or logical blocks of one or more computer instructions. Nonetheless, the executables of an identified module need not be physically located together, but may contain disparate instructions stored in different locations that, when logically combined together, encompass the module and achieve the module's stated purpose. . In reality, a module of executable code may be a single instruction or many instructions, distributed over several different code segments, different programs, and multiple memory devices. Likewise, operational data (e.g., material classification libraries described herein) may be identified within modules and illustrated herein, embodied in any suitable form and within any suitable type of data structure. It can be configured. Operational data may be collected as a single data set, or it may be distributed across different locations, including different storage devices. Data can provide electronic signals in a system or network.

These 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 device (e.g., a controller) to operate on the processors of the computer or other programmable data processing device. Creates a machine such that instructions executed via (e.g., GPU 3401, CPU 3415) create a flowchart and/or block diagram block or circuitry or means for implementing the functions/acts specified in the blocks. can do.

Additionally, each block of the block diagrams and/or flowchart examples and combinations of blocks of the block diagrams and/or flowchart examples may be used to describe special-purpose hardware-based systems (e.g., one or more graphics Note that it may be implemented by processing units (which may include processing units (e.g., GPU 3401)) or combinations of special purpose hardware and computer instructions. For example, a module may be implemented with hardware circuitry including custom VLSI circuits or off-the-shelf semiconductors such as gate arrays, logic chips, transistors, controllers or other discrete components. A module may also be implemented with programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, etc.

Computer program code, i.e., instructions, for performing the operations of the aspects of the present disclosure may be written in an object-oriented programming language such as Java, Smalltalk, Python, C++, etc., a conventional procedure such as the "C" programming language, or similar programming languages. It may be written in any combination of one or more programming languages, including any of the programming languages or any of the machine learning software disclosed herein. The program code may reside entirely on your computer system, partially on your computer system, as a stand-alone software package, partially on your computer system (e.g., the computer system utilized for sorting), and on remote computer systems (e.g. For example, it may run partially on a computer system utilized to train a sensor system, or entirely on a remote computer system or server. In the latter scenario, the remote computer system is connected to the user's computer system through any type of network, including a local area network ("LAN") or wide area network ("WAN"), or to an external computer system (e.g., providing Internet service). You can connect to the Internet (via the Internet using your provider).

These program instructions may be stored on a computer-readable storage medium that can instruct a computer system, other programmable data processing device, controller, or other device to operate in a particular manner, and the instructions stored on the computer-readable medium may include flowcharts and/or Alternatively, the block also creates an artifact containing the block or instructions that implement the function/behavior specified in the blocks.

Program instructions are also instructions that are loaded into a computer, other programmable data processing device, controller, or other devices and executed on the computer or other programmable device by causing a series of operational steps to be performed on the computer, other programmable device, or other devices. Computer-implemented processes may be created to provide a flowchart and/or block diagram block or processes for implementing the functions/acts specified in the blocks.

One or more databases may be included in the host to store and provide access to data for various implementations. Those skilled in the art will also understand that, for security reasons, any of the databases, systems or components of this disclosure may include any combination of databases or components at a single location or multiple locations, and each database or It will be appreciated that the system may include any of a variety of suitable security features such as firewalls, access codes, encryption, decryption, etc. The database may be relational, hierarchical, object-oriented, and/or any other type of database such. Common database products that can be used to implement databases include DB2 from IBM, any database product available from Oracle Corporation, and Microsoft Access from Microsoft Corporation. or any other database product. The database may be organized in any suitable manner, including data tables or lookup tables.

Association of specific data (e.g., for each piece of material processed by the sorting system described herein) may be accomplished through any data association technique known and practiced in the art. For example, association can be performed manually or automatically. Auto-association techniques may include, for example, database search, database merge, GREP, AGREP, SQL, etc. The association step can be performed, for example, with a database merge function using key fields from each of the manufacturer and retailer data tables. Key fields partition the database according to the high-level classes of entities defined by the key fields. For example, a particular class can be designated as a key field in both a first data table and a second data table, and then the two data tables can be merged based on the class data in the key field. In these embodiments, the data corresponding to the key field of each of the merged data tables is preferably the same. However, data tables with similar but not identical data in key fields may be merged using, for example, AGREP.

Aspects of the present disclosure include capturing a first visual image of a first piece of material and generating a first image data packet associated with the first piece of material; Capturing a second visual image of the second piece of material to generate a second image data packet associated with the second piece of material, wherein the first piece of material has a first chemical signature, the second piece of material has a first chemical signature and have a different second chemical signature; Processing the first and second image data packets with a machine learning system previously trained to visually distinguish between pieces of material having different chemical signatures; and classifying the first and second material pieces into two different classes with a machine learning system as a function of a learned visual discrimination between the material pieces having different chemical signatures. The method may further include sorting the first piece of material from the second piece of material as a function of classifications. The pieces of material may be pieces of plastic. The first chemical signature may be spectral data measured by a plurality of different sensor systems from at least one sample of the same type of plastic piece as the first piece of plastic, and the second chemical signature may be of the same type as the second piece of plastic. It may be spectral data measured by a plurality of different sensor systems from at least one sample of a piece of plastic. Spectral data may relate to the non-visible spectrum. The plurality of different sensor systems may be selected from the group consisting of near-infrared (“NIR”), mid-wave infrared (“MWIR”), and x-ray fluorescence (“XRF”) systems. A plurality of different sensor systems can be used for infrared (“IR”), Fourier transform IR (“FTIR”), forward infrared (“FLIR”), very near infrared (“VNIR”), near infrared (“NIR”), and shortwave infrared (“FTIR”). SWIR"), long-wave infrared ("LWIR"), mid-wave infrared ("MWIR" or "MIR"), X-ray transmission ("XRT"), gamma ray, ultraviolet ("UV"), and "XRF"), laser induced breakdown spectroscopy ("LIBS"), Raman spectroscopy, anti-Stokes Raman spectroscopy, gamma spectroscopy, hyperspectral spectroscopy (e.g. any range beyond visible wavelengths), acoustic spectroscopy, NMR spectroscopy, microwave Can be selected from the group consisting of spectroscopy, terahertz spectroscopy, differential scanning calorimetry ("DSC"), thermogravimetric analysis ("TGA"), capillary and rotational rheology, optical and scanning electron microscopy ("SEM"), and chromatography. there is. The first chemical signature may include measurements of organic and inorganic elements or molecules from at least one sample of the same type of plastic piece as the first piece of plastic, and the second chemical signature may include measurements of organic and inorganic elements or molecules from at least one sample of the same type of plastic piece as the first piece of plastic. It may include measurements of organic and inorganic elements or molecules from at least one sample of the plastic piece. Plastic pieces include Type #1 polyethylene terephthalate (“PET”), Type #2 high-density polyethylene (“HDPE”), Type #3 polyvinyl chloride (“PVC”), Type #4 low-density polyethylene (“LDPE”), Type #1 #5 polypropylene (“PP”), type #6 polystyrene (“PS”) and type #7 other polymers. The first piece of material may be polyvinyl chloride. The two different classes may be different fractions.

Aspects of the disclosure include capturing a first visual image of a first piece of material to generate a first image data packet associated with the first piece of material, capturing a second visual image of the second piece of material and a camera configured to generate a second associated image data packet, wherein the first piece of material has a first chemical signature and the second piece of material has a second chemical signature that is different from the first chemical signature; A data processing system configured to process the first and second image data packets with a machine learning system that has previously learned to visually distinguish between pieces of material having different chemical signatures, wherein the machine learning system has different chemical signatures. Sorting the first and second pieces of material into two different fractions as a function of learned visual discrimination between the pieces of material; and a sorting device configured to sort the first piece of material from the second piece of material as a function of the fractions. The pieces of material may be pieces of plastic. The first chemical signature may be spectral data related to a non-visible spectrum measured by a plurality of different sensor systems from at least one sample of the same type of plastic piece as the first piece of plastic, and the second chemical signature may be a 2 may be spectral data relating to a non-visible spectrum measured by a plurality of different sensor systems from at least one sample of the same type of plastic piece. The plurality of different sensor systems may be from the group of near infrared (“NIR”), mid-wave infrared (“MWIR”) and x-ray fluorescence (“XRF”) systems. A plurality of different sensor systems can be used for infrared (“IR”), Fourier transform IR (“FTIR”), forward infrared (“FLIR”), very near infrared (“VNIR”), near infrared (“NIR”), and shortwave infrared (“FTIR”). SWIR"), long-wave infrared ("LWIR"), mid-wave infrared ("MWIR" or "MIR"), X-ray transmission ("XRT"), gamma ray, ultraviolet ("UV"), and "XRF"), laser induced breakdown spectroscopy ("LIBS"), Raman spectroscopy, anti-Stokes Raman spectroscopy, gamma spectroscopy, hyperspectral spectroscopy (e.g. any range beyond visible wavelengths), acoustic spectroscopy, NMR spectroscopy, microwave Spectroscopy, terahertz spectroscopy, differential scanning calorimetry (“DSC”), thermogravimetric analysis (“TGA”), capillary and rotational rheology, optical and scanning electron microscopy (“SEM”) and chromatography. The first chemical signature may include measurements of organic and inorganic elements or molecules from at least one sample of the same type of plastic piece as the first piece of plastic, and the second chemical signature may include measurements of organic and inorganic elements or molecules from at least one sample of the same type of plastic piece as the first piece of plastic. It may include measurements of organic and inorganic elements or molecules from at least one sample of plastic pieces, wherein the plastic pieces include Type #1 polyethylene terephthalate (“PET”), Type #2 high density polyethylene (“HDPE”), Type #3 polyvinyl chloride (“PVC”), Type #4 low-density polyethylene (“LDPE”), Type #5 polypropylene (“PP”), Type #6 polystyrene (“PS”), and Type #7 other polymers. is selected from the group.

Aspects of the present disclosure include determining the chemical signature of each of a mixture of different plastic pieces using a plurality of different sensor systems; Capturing visual images for each piece of plastic; Digitally correlating the visual images with the chemical signature for each piece of plastic; determining a specific fraction for sorting the plastic pieces; Using visual images to identify a piece of plastic with a chemical signature belonging to a particular fraction of the pieces of plastic in the mixture; and training a machine learning system to visually identify plastic pieces belonging to specific fractions, wherein training is performed with control groups created from the identified plastic pieces. The control group may consist of captured visual image data for each identified piece of plastic. A fraction may consist of a specific combination of organic and inorganic elements or molecules. The plurality of different sensor systems may be selected from the group of near infrared (“NIR”), mid-wave infrared (“MWIR”) and x-ray fluorescence (“XRF”) systems. A mixture of different plastic pieces is Type #1 polyethylene terephthalate (“PET”), Type #2 high-density polyethylene (“HDPE”), Type #3 polyvinyl chloride (“PVC”), and Type #4 low-density polyethylene (“LDPE”). "), Type #5 polypropylene ("PP"), Type #6 polystyrene ("PS"), and Type #7 other polymers. A plurality of different sensor systems can be used for infrared (“IR”), Fourier transform IR (“FTIR”), forward infrared (“FLIR”), very near infrared (“VNIR”), near infrared (“NIR”), and shortwave infrared (“FTIR”). SWIR"), long-wave infrared ("LWIR"), mid-wave infrared ("MWIR" or "MIR"), X-ray transmission ("XRT"), gamma ray, ultraviolet ("UV"), and "XRF"), laser induced breakdown spectroscopy ("LIBS"), Raman spectroscopy, anti-Stokes Raman spectroscopy, gamma spectroscopy, hyperspectral spectroscopy (e.g. any range beyond visible wavelengths), acoustic spectroscopy, NMR spectroscopy, microwave may be selected from the group of spectroscopy, terahertz spectroscopy, differential scanning calorimetry (“DSC”), thermogravimetric analysis (“TGA”), capillary and rotational rheology, optical and scanning electron microscopy (“SEM”) and chromatography. .

In this specification, reference is made to a device being "configured" to perform some function or to "configuring" a device. It should be understood that this may include selecting predefined logical blocks and logically associating them to provide specific logical functions, including monitoring or control functions. It may also include programming the computer software-based logic of the retrofit control device, wiring individual hardware components, or combining any or all of the foregoing.

In the description herein, numerous specific details such as examples of programming, software modules, user selections, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, controllers, etc. are provided. provided to provide a thorough understanding of embodiments of the present disclosure. However, one skilled in the relevant arts will recognize that the present disclosure may be practiced without one or more of the specific details or using other methods, components, materials, etc. In other instances, well-known structures, materials, or acts may not be shown or described in detail so as not to obscure aspects of the disclosure.

Those skilled in the art will appreciate that the various settings and parameters (including neural network parameters) of the components of system 100 include the types of materials being classified and sorted, the desired classification and sorting results, the type of equipment used, and the empirical results of previous classifications. , it can be customized, optimized, and reconfigured over time based on available data and other factors.

Reference throughout this specification to “one embodiment,” “embodiments,” or similar language indicates that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the disclosure. it means. Accordingly, the occurrences of the phrases “in one embodiment,” “in one embodiment,” “embodiments,” “particular embodiments,” “various embodiments,” and similar language throughout this specification are Although they may refer to the same embodiment, this is not necessarily the case. Additionally, the described features, structures, aspects and/or characteristics of the disclosure may be combined in any suitable way in one or more embodiments. Accordingly, although features are initially claimed to operate in specific combinations, one or more features from the claimed combination may in some cases be omitted from the combination, and the claimed combination may be indicated as a sub-combination or variation of a sub-combination. there is.

Advantages, advantages, and solutions to problems are described herein with respect to specific embodiments. However, the advantages, advantages, solutions to problems and any element(s) that may give rise to or make more pronounced the advantage, advantage or solution are important to any or all of the claims; They should not be construed as essential or essential features or elements. Additionally, no element described herein is required to practice the present disclosure unless explicitly described as essential or critical.

Although many details are included in this specification, they should not be construed as limitations on the scope of the disclosure or of what may be claimed, but rather as descriptions of features specific to particular implementations of the disclosure. . The subject matter herein may not be intended to limit the disclosure, embodiments of the disclosure, or other matter disclosed in accordance with the subject matter.

As used herein, the term “or” is intended to be inclusive, where “A or B” includes either A or B and also includes both A and B. As used herein, the term “and/or” when used in the context of a list of entities refers to the entities existing alone or in combination. Thus, for example, the phrase “A, B, C, and/or D” includes not only A, B, C, and D individually, but also all combinations and subcombinations of A, B, C, and D. .

The terminology used herein is for the purpose of describing specific embodiments only and is not intended to limit the disclosure. As used herein, singular forms may be taken to include plural forms as well, unless the context clearly dictates otherwise.

In the claims below, all means or steps plus corresponding structures, materials, acts and equivalents of functional elements are defined as any structure, material or element for performing the function in combination with other specifically claimed elements. May be intended to include actions.

As used herein, “controller”, “processor”, “memory”, “neural network”, “interface”, “sorter”, “device”, “pushing mechanism”, “pusher devices”, “imaging” Terms such as "sensor", "barrel", "receptacle", "system", and "circuitry" each refer to non-generic device elements that can be recognized and understood by those skilled in the art, and are used herein as defined in 35 U.S.C. Not to be used as temporary words or temporary terms for purposes of invoking 112(f).

As used herein in relation to an identified characteristic or circumstance, 'substantially' refers to a degree of deviation small enough not to measurably impair the identified characteristic or circumstance. The exact degree of deviation permitted may in some cases vary depending on the specific circumstances.

As used herein, plural articles, structural elements, components, exemplary fractions and/or substances may be presented in a common list for convenience. However, these lists should be construed as if each member on the list were individually identified as a separate and unique member. Accordingly, individual members in such lists should not be construed as being effectively equivalent to other members in the same list simply because they appear in a common group without indications to the contrary.

Unless otherwise defined, all technical and scientific terms used herein (e.g., abbreviations used for polymers or chemical elements in the periodic table) generally refer to those skilled in the art to which the presently disclosed subject matter pertains. It has the same meaning as understood. All publications, patent applications, patents and other references mentioned herein are incorporated by reference in their entirety unless specific passages are cited. In case of conflict, the present specification, including definitions, will control. Additionally, the materials, methods, and examples (e.g., listed fractions, plastics) are illustrative only and are not intended to be limiting.

To the extent not described herein, much detail regarding specific materials, processes and circuits is conventional and can be found in textbooks and other sources in the fields of computing, electronics and software technologies.

Unless otherwise specified, all numbers representing quantities of ingredients, reaction conditions, etc. used in the specification and claims are to be understood in all instances as modified by the term “about.” Accordingly, unless otherwise indicated, the numerical parameters set forth in this specification and the appended claims are approximations that may vary depending on the desired properties sought to be achieved by the presently disclosed subject matter.

Claims (23)

As a method,
Capturing a first visual image of a first piece of material to generate a first image data packet associated with the first piece of material;
Capturing a second visual image of a second piece of material to generate a second image data packet associated with the second piece of material, wherein the first piece of material has a first chemical signature, and the second piece of material has the first chemical signature. 1 has a second chemical signature that is different from the chemical signature;
processing the first and second image data packets with a machine learning system previously trained to visually distinguish between pieces of material having different chemical signatures; and
Classifying the first and second pieces of material into two different classes by the machine learning system as a function of the learned visual discrimination between pieces of material with different chemical signatures.
Method, including. According to claim 1,
Sorting the first piece of material from the second piece of material as a function of the classifications. According to clause 2,
The method of claim 1, wherein the pieces of material are pieces of plastic. According to clause 3,
The first chemical signature includes spectral data measured by a plurality of different sensor systems from at least one sample of the same type of plastic piece as the first piece of plastic, and the second chemical signature includes spectral data measured by a plurality of different sensor systems. A method comprising spectral data measured by the plurality of different sensor systems from at least one sample of a piece of plastic of the same type as the piece. According to clause 4,
The method of claim 1, wherein the spectral data relates to the non-visible spectrum. According to clause 4,
The method of claim 1, wherein the plurality of different sensor systems are selected from the group consisting of near-infrared (“NIR”), mid-wave infrared (“MWIR”), and x-ray fluorescence (“XRF”) systems. According to clause 4,
The plurality of different sensor systems may include infrared (“IR”), Fourier transform IR (“FTIR”), forward infrared (“FLIR”), very near infrared (“VNIR”), near infrared (“NIR”), and shortwave infrared (“FTIR”). “SWIR”), long-wave infrared (“LWIR”), mid-wave infrared (“MWIR” or “MIR”), X-ray transmission (“XRT”), gamma ray, ultraviolet (“UV”), and “XRF”), laser induced breakdown spectroscopy (“LIBS”), Raman spectroscopy, anti-Stokes Raman spectroscopy, gamma spectroscopy, hyperspectral spectroscopy (e.g. any range beyond visible wavelengths), acoustic spectroscopy, NMR spectroscopy, selected from the group consisting of microwave spectroscopy, terahertz spectroscopy, differential scanning calorimetry (“DSC”), thermogravimetric analysis (“TGA”), capillary and rotational rheology, optical and scanning electron microscopy (“SEM”), and chromatography. , method. According to clause 3,
The first chemical signature includes measurements of organic and inorganic elements or molecules from at least one sample of the same type of plastic piece as the first piece of plastic, and the second chemical signature is the same as the second piece of plastic. A method comprising measurements of organic and inorganic elements or molecules from at least one sample of a tangible piece of plastic. According to clause 3,
The plastic pieces include Type #1 polyethylene terephthalate (“PET”), Type #2 high-density polyethylene (“HDPE”), Type #3 polyvinyl chloride (“PVC”), Type #4 low-density polyethylene (“LDPE”), selected from the group consisting of Type #5 polypropylene (“PP”), Type #6 polystyrene (“PS”), and Type #7 other polymers. According to clause 3,
The method of claim 1, wherein the first piece of material comprises polyvinyl chloride. According to claim 1,
The method of claim 1, wherein the two different fractions are different fractions. As a system,
Capturing a first visual image of a first piece of material to generate a first image data packet associated with the first piece of material, and capturing a second visual image of a second piece of material to generate a second image associated with the second piece of material a camera configured to generate a data packet, wherein the first piece of material has a first chemical signature and the second piece of material has a second chemical signature that is different from the first chemical signature;
A data processing system configured to process the first and second image data packets with a machine learning system that has previously learned to visually distinguish between pieces of material having different chemical signatures, the machine learning system comprising: classifying the first and second pieces of material into two different fractions as a function of the learned visual discrimination between pieces of material having chemical signatures; and
A sorting device configured to sort the first piece of material from the second piece of material as a function of the fractions.
system, including. According to claim 12,
The system according to claim 1, wherein the pieces of material are pieces of plastic. According to claim 13,
The first chemical signature includes spectral data relating to a non-visible spectrum measured by a plurality of different sensor systems from at least one sample of the same type of plastic piece as the first piece of plastic, and The system of claim 1, wherein the signature includes spectral data relating to a non-visible spectrum measured by the plurality of different sensor systems from at least one sample of the same type of plastic piece as the second piece of plastic. According to claim 14,
The system of claim 1, wherein the plurality of different sensor systems are selected from the group consisting of near-infrared (“NIR”), mid-wave infrared (“MWIR”), and x-ray fluorescence (“XRF”) systems. According to claim 14,
The plurality of different sensor systems may include infrared (“IR”), Fourier transform IR (“FTIR”), forward infrared (“FLIR”), very near infrared (“VNIR”), near infrared (“NIR”), and shortwave infrared (“FTIR”). “SWIR”), long-wave infrared (“LWIR”), mid-wave infrared (“MWIR” or “MIR”), X-ray transmission (“XRT”), gamma ray, ultraviolet (“UV”), and “XRF”), laser induced breakdown spectroscopy (“LIBS”), Raman spectroscopy, anti-Stokes Raman spectroscopy, gamma spectroscopy, hyperspectral spectroscopy (e.g. any range beyond visible wavelengths), acoustic spectroscopy, NMR spectroscopy, selected from the group consisting of microwave spectroscopy, terahertz spectroscopy, differential scanning calorimetry (“DSC”), thermogravimetric analysis (“TGA”), capillary and rotational rheology, optical and scanning electron microscopy (“SEM”), and chromatography. , system. According to claim 13,
The first chemical signature includes measurements of organic and inorganic elements or molecules from at least one sample of the same type of plastic piece as the first piece of plastic, and the second chemical signature is the same as the second piece of plastic. It includes measurements of organic and inorganic elements or molecules from at least one sample of a piece of plastic of type #1 polyethylene terephthalate (“PET”), type #2 high-density polyethylene (“HDPE”). , Type #3 polyvinyl chloride (“PVC”), Type #4 low-density polyethylene (“LDPE”), Type #5 polypropylene (“PP”), Type #6 polystyrene (“PS”), and Type #7 other polymers. A system selected from a group consisting of: As a method,
determining a chemical signature for each mixture of different plastic pieces using a plurality of different sensor systems;
capturing visual images for each of the plastic pieces;
digitally correlating the visual images with a chemical signature for each piece of plastic;
determining a specific fraction for sorting the plastic pieces;
using the visual images to identify plastic pieces with a chemical signature belonging to the specific fraction of plastic pieces in the mixture; and
Training a machine learning system to visually identify plastic pieces belonging to the specific fractions.
Including,
The method of claim 1, wherein the training is performed with a control group created from the identified pieces of plastic. According to clause 18,
The method of claim 1, wherein the control group consists of captured visual image data of each of the identified pieces of plastic. According to clause 18,
The method of claim 1, wherein the fraction consists of a specific combination of organic and inorganic elements or molecules. According to clause 18,
The method of claim 1, wherein the plurality of different sensor systems are selected from the group consisting of near-infrared (“NIR”), mid-wave infrared (“MWIR”), and x-ray fluorescence (“XRF”) systems. According to claim 21,
A mixture of different plastic pieces is Type #1 polyethylene terephthalate (“PET”), Type #2 high-density polyethylene (“HDPE”), Type #3 polyvinyl chloride (“PVC”), and Type #4 low-density polyethylene (“LDPE”). "), Type #5 polypropylene ("PP"), Type #6 polystyrene ("PS"), and Type #7 other polymers. According to clause 18,
The plurality of different sensor systems may include infrared (“IR”), Fourier transform IR (“FTIR”), forward infrared (“FLIR”), very near infrared (“VNIR”), near infrared (“NIR”), and shortwave infrared (“FTIR”). “SWIR”), long-wave infrared (“LWIR”), mid-wave infrared (“MWIR” or “MIR”), X-ray transmission (“XRT”), gamma ray, ultraviolet (“UV”), and “XRF”), laser induced breakdown spectroscopy (“LIBS”), Raman spectroscopy, anti-Stokes Raman spectroscopy, gamma spectroscopy, hyperspectral spectroscopy (e.g. any range beyond visible wavelengths), acoustic spectroscopy, NMR spectroscopy, selected from the group consisting of microwave spectroscopy, terahertz spectroscopy, differential scanning calorimetry (“DSC”), thermogravimetric analysis (“TGA”), capillary and rotational rheology, optical and scanning electron microscopy (“SEM”), and chromatography. , method.