Waste plastic sorting system and waste plastic sorting method

The waste plastic sorting system addresses the accuracy issues in conventional methods by surface-treating plastics to enhance reflection spectra, using machine learning for precise material discrimination and sorting.

JP7577914B2Active Publication Date: 2024-11-06DAIO PAPER CORP
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2021130724
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-08-10
Publication Date
2024-11-06
Estimated Expiration
2041-08-10

AI Technical Summary

Technical Problem

Conventional waste plastic sorting methods using light reflection, such as infrared irradiation, face challenges with halation and insufficient reflected light, leading to reduced sorting accuracy, particularly for black plastics.

Method used

A waste plastic sorting system that includes a surface treatment process to roughen the plastic surfaces, followed by infrared light irradiation and spectral analysis, using a combination of machine learning algorithms to enhance material discrimination and sorting accuracy.

Benefits of technology

The system achieves high-precision sorting of waste plastics by improving the reflection spectrum quality, allowing for accurate material identification and separation of various plastic types, including black plastics.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007577914000006
    Figure 0007577914000006
  • Figure 0007577914000007
    Figure 0007577914000007
  • Figure 0007577914000008
    Figure 0007577914000008
Patent Text Reader

Abstract

To provide a selection system that can accurately select waste plastic by material.SOLUTION: A selection system 1A comprises: discrimination device 5A that irradiates waste plastic pieces S1, S2, S1A with light to determine material based on the spectrum of reflected light; a selection unit 12A that selects the waste plastic piece S1 based on a result of determination made by the discrimination device 5A; a surface treatment device 20 that executes treatment of surfaces of the remaining waste plastic pieces S2, S1A other than the waste plastic piece selected by the selection unit 12A; a discrimination device 5B that irradiates, with light, the waste plastic pieces S2, S1A on which the surface treatment is executed by the surface treatment device 20 to determine material based on the spectrum of reflected light; and a selection unit 12B that selects the waste plastic piece S1A on which the surface treatment is executed based on a result of determination made by the discrimination device 5B.SELECTED DRAWING: Figure 11
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a waste plastic sorting system and a waste plastic sorting method. [Background technology]

[0002] Material recycling, in which new materials or products are produced using waste plastics, is known as the main method for reusing waste plastics derived from discarded home appliances, discarded automobiles, etc. Since collected waste plastics usually contain various types (materials) of plastics, in material recycling, the waste plastics must be sorted by material according to the regenerated products to be produced.

[0003] As a means for sorting waste plastics, for example, a method is known in which pieces of waste plastic are irradiated with light such as infrared light and the material of the plastic is determined by utilizing the spectrum of the reflected light obtained by the irradiation (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2018-100903 A Summary of the Invention [Problem to be solved by the invention]

[0005] In order to produce high-quality products in material recycling, it is necessary to sort waste plastics with high accuracy. However, in conventional waste plastic sorting using reflection of infrared light or the like, halation may occur depending on the intensity of the irradiated light, the irradiation distance, etc., and there are cases where reflected light capable of generating a reflection spectrum effective for determining the material cannot be obtained sufficiently. Therefore, there is a demand for improved sorting accuracy in a waste plastic sorting device or sorting method using light reflection.

[0006] Therefore, one aspect of the present invention has an objective of providing a sorting system that sorts waste plastics based on their material with high accuracy. [Means for solving the problem]

[0007] A waste plastic sorting system according to one embodiment of the present invention comprises a first discrimination unit that irradiates light onto waste plastic pieces transported on a conveying path and determines their material based on the spectrum of the reflected light, a first sorting unit that sorts the waste plastic pieces based on the judgment result of the first discrimination unit, a surface treatment unit that treats the surfaces of the remaining waste plastic pieces from the waste plastic pieces sorted by the first sorting unit, a second discrimination unit that irradiates light onto the waste plastic pieces that have been surface-treated by the surface treatment unit and determines their material based on the spectrum of the reflected light, and a second sorting unit that sorts the waste plastic pieces that have been surface-treated based on the judgment result of the second discrimination unit. Effect of the Invention

[0008] According to the present disclosure, a sorting system can be provided that can sort waste plastic by material with high accuracy. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a perspective view showing a schematic configuration of a waste plastic sorting device; [Diagram 2] A side view of the waste plastic sorting device shown in Figure 1. [Diagram 3] Plan view of the waste plastic sorting device shown in Figure 1. [Figure 4] Schematic diagram showing an example of a surface treatment device [Diagram 5] Functional block diagram of the sorting device [Figure 6] Flowchart of waste plastic material discrimination process using a sorting device [Figure 7] Diagram showing the method of extracting spectra for correction [Figure 8] FIG. 13 is a diagram showing an example of a process for extracting a characteristic wavelength region from a reflected wave spectrum. [Figure 9] A diagram showing an example of feature data extraction [Figure 10] An example of material discrimination using a decision tree [Figure 11] FIG. 1 is a side view showing a schematic configuration of a waste plastic sorting system according to a first embodiment. [Figure 12] FIG. 11 is a side view showing a schematic configuration of a waste plastic sorting system according to a second embodiment. [Figure 13] FIG. 11 is a plan view showing a schematic configuration of a waste plastic sorting system according to a third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment will be described with reference to the accompanying drawings. In order to facilitate understanding of the description, the same components in each drawing are denoted by the same reference numerals as much as possible, and duplicated description will be omitted.

[0011] In the following description, the x, y, and z directions are perpendicular to each other. The x and y directions are horizontal, and the z direction is vertical. The x direction is the conveying direction of the conveying path 3 of the conveyor 2. The y direction is the width direction of the conveying path 3 of the conveyor 2. For convenience of explanation, the positive z direction side may be referred to as the upper side, and the negative z direction side as the lower side. Also, the negative x direction side may be referred to as the upstream side, and the positive x direction side as the downstream side.

[0012] [First embodiment] <Waste plastic piece sorting device> First, with reference to Figs. 1 to 10, a sorting device 1 that can constitute a waste plastic piece sorting system 1A according to a first embodiment will be described.

[0013] The schematic configuration of the waste plastic sorting device 1 will be described with reference to Figs. 1 to 3. Fig. 1 is a perspective view showing the schematic configuration of the waste plastic sorting device 1. Fig. 2 is a side view of the waste plastic sorting device 1 shown in Fig. 1. Fig. 3 is a plan view of the waste plastic sorting device 1 shown in Fig. 1. As shown in Figs. 1 to 3, the waste plastic sorting device 1 is equipped with a surface treatment device 20 (surface treatment unit) upstream of the device.

[0014] The waste plastics sorted by the sorting device 1 according to this embodiment are aggregates of waste plastic pieces (a group of waste plastic pieces) obtained by crushing waste home appliances, discarded automobiles, etc. Each waste plastic piece may have a plate-like or layer-like shape, and may have an average maximum length of 5 to 50 mm and an average area in a plan view of 20 to 2500 mm. 2 In this embodiment, waste plastic pieces of a predetermined material are selected from a collection of waste plastic pieces (a group of waste plastic pieces) including black waste plastic pieces, preferably from a collection of black waste plastic pieces (a group of black waste plastic pieces). In addition, the waste plastic pieces selected by this embodiment may contain colored waste plastic pieces of another color, such as blue or red, in addition to the black waste plastic pieces.

[0015] In this specification, black refers to a color with a brightness of 6 or less, expressed in Munsell notation according to JIS 8721. The black color of black waste plastic pieces usually comes from the carbon black (carbon filler) contained in the black waste plastic pieces.

[0016] 1 to 3 show, as an example, an apparatus for determining and separating waste plastic pieces of one material from a group of waste plastic pieces S1 made of one type of material and waste plastic pieces S2 made of a different type of material from the waste plastic pieces. In the following, the waste plastic pieces S1 and S2 may be collectively represented by the symbol S. The number of materials (types) of the waste plastic pieces separated from the group of waste plastic pieces is not particularly limited, and may be 2 to 10 types. Specific examples of plastic materials include polyethylene (PE), polypropylene (PP), polycarbonate / acrylonitrile-butadiene-styrene (PCABS), acrylonitrile-butadiene-styrene (ABS), polystyrene (PS), polyphenylene ether / polystyrene (PPEPS), polyamide (PA), polycarbonate (PC), polyacetal (POM), polyethylene terephthalate (PET), polyvinyl chloride (PVC), polymethyl methacrylate (PMMA), etc.

[0017] In the waste plastic sorting device 1 according to this embodiment, the material of the waste plastic is determined based on the reflection spectrum detected from the reflected light obtained by irradiating the waste plastic with infrared light or the like, and the material is identified (details on the determination will be described later). In the conventional configuration, when light is applied, strong regular reflection (specular reflection) occurs depending on the intensity of the irradiated light, irradiation distance, etc., and there are cases where reflected light (diffuse reflected light) effective for determining the material is not obtained in sufficient quantity. In contrast, the sorting device 1 according to this embodiment has a surface treatment device 20, which treats the surface of the waste plastic pieces, making it possible to obtain appropriate reflected light.

[0018] In particular, black plastics have a weaker level (strength) of the absorption region specific to the material than plastics of other colors, and are therefore more affected by the surface condition. In particular, when the glossiness of the plastic surface is relatively high, the influence of infrared reflection on the plastic surface, especially the influence of regular reflection (specular reflection), becomes large, making it difficult to see the absorption level and to distinguish the material. Therefore, by performing a surface treatment to roughen the surface to a specified roughness, the influence of regular reflection of infrared rays on the plastic surface can be suppressed, the spectral intensity of the reflected light spectrum can be increased, and the difference in reflection spectrum intensity due to the material can be properly observed. As a result, the accuracy of sorting black plastic pieces can be improved.

[0019] The surface treatment by the surface treatment device 20 may be a treatment that changes the surface state to such an extent that a reflection spectrum effective for identifying the material can be obtained when light is irradiated. For example, the surface treatment according to this embodiment may be a treatment that changes the surface state of the waste plastic pieces so that the glossiness (specular glossiness) (Gs60(%)) at an incident angle of 60° measured in accordance with JIS Z 8741 is 10 or less. The glossiness at an incident angle of 60° may be preferably 8 or less, more preferably 6 or less, and even more preferably 1.5 or less. The glossiness at the incident angle of 60° may be 0.1 or more. Furthermore, the surface treatment according to this embodiment may be a treatment that changes the surface state so that the glossiness (specular glossiness) (Gs75(%)) at an incident angle of 75° measured in accordance with JIS Z 8741 is 25 or less. The glossiness at an incident angle of 75° may be preferably 15 or less, more preferably 10 or less, and even more preferably 5 or less. The glossiness at the incident angle of 75° may be 0.1 or more. The surface treatment in this embodiment is preferably carried out so as to have a glossiness at an incidence angle of 60° within the above range, and also a glossiness at an incidence angle of 75° within the above range. By having the above glossiness, particularly a glossiness at an incidence angle of 60° and / or a glossiness at an incidence angle of 75°, it is possible to impart an appropriate rough surface state to the plastic surface, thereby improving the sorting accuracy even when the waste plastic pieces are black plastic pieces.

[0020] The surface treatment according to the present embodiment may be a treatment for changing the surface condition of the waste plastic pieces so that the surface roughness mean deviation (SMD) is 1 μm or more. The surface roughness mean deviation may be preferably 1.1 μm or more, more preferably 1.2 μm or more. The surface roughness mean deviation may be preferably 6 μm or less, preferably 3 μm or less, more preferably 2.5 μm or less. By performing the surface treatment so that the surface roughness mean deviation (SMD) is in the above range, the plastic surface can be given an appropriate rough surface condition. Therefore, even if the waste plastic pieces are black plastic pieces, the reflection spectrum can be appropriately obtained, and the sorting accuracy can be improved.

[0021] In addition, by making 50% or more, and preferably 80% or more, of the total surface area of ​​the waste plastic pieces satisfy one or more of the following conditions: gloss (specular gloss (%)) at an incident angle of 60° measured in accordance with JIS Z 8741 is 10 or less, gloss (specular gloss (%)) at an incident angle of 75° measured in accordance with JIS Z 8741 is 25 or less, and surface roughness mean deviation (SMD) is 1 μm or more, the sorting accuracy of waste plastic pieces using infrared rays can be improved.

[0022] The surface treatment in this embodiment may be a roughening treatment or a smoothening treatment depending on the surface condition of the original waste plastic pieces. The surface treatment may be a wet treatment using a liquid or a dry treatment not using a liquid. Specific examples of surface treatment include polishing (or grinding) using an abrasive tool such as a wire brush or sandpaper and / or an abrasive, and surface treatment using chemicals. Of these, polishing is preferred because the amount of waste that may be generated by the treatment is relatively small and the disposal of the waste is easy.

[0023] FIG. 4 is a schematic diagram of an example of the surface treatment device 20. The surface treatment device 20 shown in FIG. 4 is equipped with a plurality of rollers having rough surfaces. By passing the waste plastic pieces S' before surface treatment between the plurality of rollers, the surface of the waste plastic pieces S' is scraped, forming fine irregularities and / or eliminating excessively large irregularities, thereby obtaining waste plastic pieces S with appropriate irregularities. The surface of the waste plastic pieces with appropriate irregularities has the above-mentioned predetermined glossiness, and the plastic type can be determined with higher accuracy by using light irradiation in the sorting device 1.

[0024] In the surface treatment device 20 shown in FIG. 4, a large roller 21 that rotates in the direction of transporting the waste plastic pieces and small-diameter rough-surface rollers 23, 23, 23 that face the large roller 21 and rotate in the opposite direction to the large roller 21 are arranged. Brushes or sandpaper are attached to the surfaces of the rough-surface rollers 23, 23, 23. The waste plastic pieces S' before surface treatment supplied from the supply unit 28 are supplied between the large roller 21 and the rough-surface rollers 23, 23, 23, and are transported in the transport direction, while the surface facing the rough-surface rollers 23, 23, 23 is roughened. In the surface treatment device 20, downstream of the large roller 21 and the rough-surface rollers 23, 23, 23, another large roller 22 that rotates in the direction of transporting the waste plastic pieces and small-diameter rough-surface rollers 25, 25, 25 that face the large roller 22 and rotate at high speed in the opposite direction to the large roller 22 are arranged. The rough-surface rollers 25, 25, 25 are fitted with brushes or sandpaper, similar to the rough-surface rollers 23, 23, 23. The large roller 22 and the rough-surface rollers 25, 25, 25 are arranged so that the surface of the waste plastic pieces S' opposite to the surface roughened by the rough-surface rollers 23, 23, 23 is roughened. With this configuration, both sides of the waste plastic pieces S' have a surface condition appropriate for the material determination in the sorting device 1, allowing for highly accurate sorting by material. The rotation speeds of the rough-surface rollers 23, 23, 23 and the rough-surface rollers 25, 25, 25 can be set according to the desired surface condition of the waste plastic pieces. The appropriate surface condition can be one that satisfies one or more of the following conditions: gloss (specular gloss (%)) at an incidence angle of 60° measured in accordance with JIS Z 8741 is 10 or less, gloss (specular gloss (%)) at an incidence angle of 75° measured in accordance with JIS Z 8741 is 25 or less, and the mean deviation of surface roughness (SMD) is 1 μm or more. In the case of waste plastic pieces that contain or consist of black plastic pieces, the above surface condition can improve the sorting accuracy.

[0025] The waste plastic pieces are obtained by removing plastic parts from discarded home appliances, discarded automobiles, etc., and then crushing them to reduce their size so as to facilitate recycling. The surface treatment in this embodiment may be incorporated into the crushing step.

[0026] Referring again to Figs. 1 to 3, the processing of the waste plastic pieces S after surface treatment in the sorting device 1 will be described. The main components include a vibration feeder 8 as an example of a supply unit that sequentially supplies the waste plastic pieces S1 and S2 after surface treatment obtained from the surface treatment device 20, and a conveyor 2 as an example of a transport unit that transports the waste plastic pieces S1 and S2 supplied by the vibration feeder 8. The crushed (surface-treated) waste plastic pieces S1 and S2 are supplied to the vibration feeder 8, for example, via an input hopper or the like. The vibration feeder 8 vibrates the placement surface on which the waste plastic pieces S1 and S2 are placed, thereby supplying the waste plastic pieces S1 and S2 to the conveyor 2 while preventing them from overlapping with each other. The conveyor 2 has a conveying path 3 on its upper surface, and transports the waste plastic pieces S1 and S2 on the conveying path 3 in a direction away from the vibration feeder 8.

[0027] The sorting device 1 also includes a light 10 as an example of an irradiation unit that irradiates infrared rays onto the waste plastic pieces S1 and S2, a mid-infrared camera 4 as an example of a reflection spectrum detection unit that detects the reflection spectrum from the waste plastic pieces S1 and S2, and a discrimination device 5 (discrimination unit) that determines or identifies the material of the waste plastic pieces S1 and S2 based on the reflection spectrum detected by the mid-infrared camera 4.

[0028] The lighting 10 has a lamp 10A (see FIG. 7) that is an infrared light source such as a halogen tungsten lamp, and irradiates (emits) infrared rays from the lamp 10A toward the waste plastic pieces S1, S2. The lighting 10 is also installed so that reflected light from the waste plastic pieces S1, S2 enters the mid-infrared camera 4, and is installed on both upper sides (or one upper side) of the conveyor 2 in the flow direction relative to the mid-infrared camera 4.

[0029] The light irradiated to the waste plastic pieces may include infrared rays of 2 to 8 μm, preferably mid-infrared rays of more than 3 μm, more specifically infrared rays of more than 3 μm and 8 μm or less. The mid-infrared rays in the above wavelength range include a region where the light absorption rate of black plastic is relatively low, so that even for black waste plastic, a reflected light spectrum effective for determining the material of the plastic (a reflected light spectrum in which a significant difference can be observed depending on the material) can be obtained.

[0030] As shown in FIG. 1, for example, one mid-infrared camera 4 can measure the entire width direction (y direction) of the conveyor 2, divide the conveyor 2 into a plurality of (e.g., 318) regions along the width direction, receive near-infrared reflected light from the black waste plastic pieces S1 and S2, and measure the spectrum of the reflected light for each region. The mid-infrared camera 4 may be, for example, a camera equipped with a spectrometer for an infrared wavelength region of 3 μm or more or more than 3 μm. The mid-infrared camera 4 performs measurements at a scan frequency of, for example, 230 Hz, and transmits 318 pieces of spectrum data to the discrimination device 5 for each scan. The discrimination device 5 outputs the material judgment results for each of the 318 regions based on the 318 pieces of spectrum data received from the mid-infrared camera 4 to the injection control unit 6 described below.

[0031] The reflected light received by the mid-infrared camera 4 may preferably include infrared rays in a wavelength region of more than 3 μm, more preferably more than 3 μm and 8 μm or less, and even more preferably more than 3 μm and 5 μm or less. By receiving reflected light in the above wavelength region, data useful for determining the material of black waste plastic can be obtained. In other words, a significant difference due to the material can be observed in the spectral intensity of reflected light in the above wavelength region.

[0032] Furthermore, the sorting device 1 is equipped with an injection nozzle row 7 that injects air laterally or obliquely in a direction intersecting the conveying direction (x direction) downstream of the conveying direction of the conveyor 2. The injection nozzle row 7 is composed of a plurality of injection nozzles (e.g., 318) arranged in the width direction (y direction) of the conveyor 2, and the operation of each injection nozzle is controlled by the injection control unit 6. The injection control unit 6 can inject air from the injection nozzles of the injection nozzle row 7 or not inject air according to the material judgment result received from the discrimination device 5. That is, it is possible to select the target waste plastic pieces and blow air onto them (selective blowing). Then, for example, the black waste plastic pieces S1 and S2 are sorted and dropped into a plurality of areas (e.g., a collection hopper or container) divided by a partition plate 9 (FIG. 2), and the waste plastics of the desired material are separated and collected. In other words, in this embodiment, the injection control unit 6 and the injection nozzle row 7 function as a sorting unit 12 that collects waste plastic pieces of a desired material from those flowing on the conveying path 3 of the conveyor 2 based on the material determination result by the discrimination device 5.

[0033] 1 to 3, the sorting unit 12 uses a jet of air or a predetermined gas to selectively blow or not blow away the waste plastic pieces S on the conveyor 2, but the sorting form is not limited to that shown in the figures. For example, information on the material determination result by the discrimination device 5 may be sent to a robot arm, and the robot arm may sort the waste plastic pieces by their material, thereby separating the waste plastic pieces.

[0034] The operation of the sorting device 1, that is, the processing of the waste plastic pieces supplied from the surface treatment device 20, will be described. For example, when the crushed waste plastic pieces S1, S2 are supplied to the vibrating feeder 8 via an input hopper or the like, the vibrating feeder 8 vibrates the supplied waste plastic pieces S1, S2 to prevent them from overlapping, transports them downstream, and supplies them to the conveyor 2.

[0035] The waste plastic pieces S1 and S2 supplied to the transport path 3 on the upper surface of the conveyor 2 are irradiated with infrared light from the lighting 10 at a position where they can be imaged by the mid-infrared camera 4 while being transported in the transport direction on the x-positive side. The mid-infrared camera 4 receives the infrared light emitted from the lighting 10 and reflected by the waste plastic pieces S1 and S2, and outputs the light reception result (data of the received light spectrum) to the discrimination device 5.

[0036] The discrimination device 5 identifies the material of the waste plastic pieces S1, S2 based on the light reception result input from the mid-infrared camera 4. The material determination method by the discrimination device 5 will be described in detail later with reference to Figs. 5 to 10. The discrimination device 5 outputs the material identification result to the injection control unit 6.

[0037] The injection control unit 6 selects an injection nozzle corresponding to the material from among the multiple injection nozzles arranged in the injection nozzle row 7, and transmits a control signal at the appropriate timing. Each injection nozzle in the injection nozzle row 7 that receives the control signal opens its nozzle opening and injects air. By injecting air from the injection nozzle at an appropriate timing according to the discrimination result of the discrimination device 5, the material to be sorted can be separated from other materials and collected.

[0038] In the example shown in Figures 1 to 3, the waste plastic pieces S1 on the conveyor 2 receive air from the air injection nozzle that has received the control signal, are blown off, fall, and are collected in a collection container or the like. Also, the black waste plastic pieces S2 on the conveyor 2 do not receive air from the injection nozzle, so are collected in a collection container or the like different from the black waste plastic pieces S1. In this way, by individually injecting and stopping the injection nozzles included in the injection nozzle row 7, it is possible to separate and collect waste plastic pieces of a predetermined material from a group of waste plastic pieces of multiple materials.

[0039] According to this embodiment, the waste plastic pieces to be sorted are surface-treated and have a predetermined surface roughness, preferably on both sides, so that they can have an appropriate friction coefficient against the conveyor 2. Therefore, in the sorting section 12, the targeted waste plastic pieces are reliably blown away, and the non-targeted waste plastic pieces are reliably not blown away, which also contributes to improving the sorting accuracy.

[0040] 5 to 10, the material determination and discrimination of waste plastics by the discrimination device 5 will be described. FIG.

[0041] As shown in FIG. 5, the discrimination device 5 has a pre-processing unit 51, and further has a first judgment unit 52 (first judgment means), a second judgment unit 53 (second judgment means), and a third judgment unit 54 (third judgment means) (collectively referred to as the judgment units).

[0042] The pre-processing unit 51 performs pre-processing such as correction and processing of the reflection spectrum of the black waste plastic pieces S1, S2 detected by the mid-infrared camera 4. For example, the pre-processing unit 51 corrects the detected reflection spectrum using a spectrum measured under conditions where the reflected light is bright and a spectrum measured under conditions where the reflected light is dark. "Dark conditions (dark conditions)" refers to conditions that are relatively darker than the above-mentioned "bright conditions (light conditions)." In addition, the pre-processing unit 51 performs processing to cut out a predetermined frequency range from the corrected reflection spectrum.

[0043] The first determination unit 52 determines whether the spectrum detected by the mid-infrared camera 4 is from the waste plastic pieces S1, S2 or the conveying path 3 of the conveyor 2. The first determination unit 52 makes the determination using a trained One Class SVM (Support Vector Machine).

[0044] One Class SVM is a type of SVM, which is a type of machine learning classification algorithm. In SVM, the support vectors of each class (the ones closest to other classes in the training data) are used as the basis, and the classification boundary is set to maximize the Euclidean distance between them. In addition, if the features are nonlinear, a kernel is used to map the data into the feature space. By appropriately selecting the kernel, it is possible to draw the classification boundary even with complex data arrangements.

[0045] In One Class SVM, a method called the kernel trick is used to map one type of training data into a high-dimensional feature space. At this time, the training data is mapped so that it is placed far away from the origin, so data that is not similar to the original training data is gathered near the origin. This property is used to distinguish between normal data (conveyor 2) and abnormal data (objects (waste plastic pieces S1, S2)).

[0046] By using One Class SVM, which has excellent pattern recognition ability, in the first determination unit 52, it is possible to accurately determine whether the reflection spectrum is reflected by the waste plastic pieces S1, S2 or the transport path 3 of the conveyor 2. Note that the first determination unit 52 may apply a classification method of supervised learning of machine learning other than One Class SVM.

[0047] The second judgment unit 53 extracts feature data Score1 and Score2 (feature amount) from the spectrum judged to be a waste plastic piece by the first judgment unit 52. The feature amount may be, for example, the maximum value, average value, integral value, etc. of the spectral intensity in a predetermined wavelength region, but it is preferable to extract the feature amount using a trained PLS (Partial Least Squares) method.

[0048] PLS is a type of regression algorithm for supervised learning in machine learning, and performs regression analysis between only a small number of principal components calculated from explanatory variables and the objective variable. In PLS, the principal components are calculated so that the covariance with the objective variable is large. In this embodiment, two types of feature data Score1 and Score2 are calculated using PLS based on the explanatory variables of the reflection spectra determined to be reflected by the waste plastic pieces S1 and S2.

[0049] By using PLS in the second judgment unit 53, it is possible to reduce the multidimensional explanatory variables of the reflectance spectrum to a small number of feature quantities, and therefore it is possible to extract more easily distinguishable appropriate feature data Score1 and Score2. Note that the second judgment unit 53 may apply a machine learning multivariate analysis method other than PLS.

[0050] The third judgment unit 54 judges the material of the waste plastic pieces S1, S2 corresponding to the spectrum based on the two feature values ​​Score1 and Score2 of the reflection spectrum extracted by the second judgment unit 53. The third judgment unit 54 makes the judgment using a trained decision tree. A decision tree is a type of classification algorithm for supervised learning. A decision tree represents the rules for classifying the objective variables in a tree structure, and is frequently used in classification problems.

[0051] By using a decision tree in the third judgment unit 54, the materials of the waste plastic pieces S1 and S2 can be accurately determined from the two feature amounts Score1 and Score2 of the reflection spectrum. Note that a classification method of supervised learning of machine learning other than the decision tree may be applied to the third judgment unit 54.

[0052] The discrimination device 5 can be physically configured as a computer system including a CPU (Central Processing Unit), a RAM (Random Access Memory) and a ROM (Read Only Memory) as main storage devices, a communication module, an auxiliary storage device, and the like. Each function of the discrimination device 5 shown in Fig. 5 is realized by loading a predetermined computer software (material determination program) into the CPU, RAM, and the like, thereby operating various hardware under the control of the CPU and reading and writing data in the RAM. That is, by executing the material determination program according to this embodiment on a computer, the discrimination device 5 functions as a pre-processing unit 51, a first determination unit 52, a second determination unit 53, and a third determination unit 54 in Fig. 5.

[0053] The material discrimination program of this embodiment is stored, for example, in a storage device provided in a computer. Note that the material discrimination program may be configured so that a part or all of it is transmitted via a transmission medium such as a communication line, and is received and recorded (including installed) by a communication module or the like provided in the computer. Also, the material discrimination program may be configured so that a part or all of it is recorded (including installed) in the computer from a state in which it is stored in a portable storage medium such as a CD-ROM, DVD-ROM, or flash memory.

[0054] The discrimination device 5 may be a circuit configured with an analog circuit, a digital circuit, or an analog-digital mixed circuit. It may also include a control circuit that controls each function of the discrimination device 5. Each circuit may be implemented using an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like.

[0055] Similarly, the injection control unit 6 can also be physically configured as a computer system including a CPU, RAM and ROM, a communication module, an auxiliary storage device, etc., and its functions are realized by loading predetermined computer software into the CPU, RAM, etc.

[0056] 6 is a flowchart of the process of determining the material of waste plastic by the sorting device 1. Each step of the flowchart shown in FIG.

[0057] In step S01, the pre-processing unit 51 processes the spectrum S org (n, w) is acquired. Here, n is the number of sensors (the number of spectrum detection areas divided in the width direction of the conveyor 2 by the mid-infrared camera 4), and when the number of sensors is 318, an integer from 0 to 317 corresponding to each detection area is used. w is the wavelength of the spectrum, and in this embodiment, a total of 131 wavelengths are set at intervals of 20 (nm) between 2700 (nm) and 5300 (nm), and an integer from 0 to 130 corresponding to each wavelength is used. In other words, S org (n, w) represents the numerical value of the spectral intensity of wavelength w in the nth spectral detection region along the width direction of the conveyor 2.

[0058] In step S02, the preprocessing unit 51 processes the spectrum S obtained in step S01. org (n,w) is corrected to obtain the corrected spectrum S cor (n, w) is calculated. This correction absorbs the difference in the spectral intensity characteristics due to the influence of the concentration changes of water vapor and carbon dioxide in the measurement space, the temperature of the black waste plastic pieces S1 and S2 to be measured, the aging of the lighting 10 and the mid-infrared camera 4, the position on the conveyor 2, etc. The corrected spectrum S cor (n, w) can be calculated, for example, by the following equation (1).

[0059]

number

[0060] Figure 7 shows the correction spectrum W ref (n,w), D ref 7 is a diagram showing a method for extracting (n, w). As shown in FIG. 7, a calibration plate 11 for acquiring a correction spectrum is placed in the imaging area of ​​the mid-infrared camera 4 on the conveying path 3 of the conveyor 2, and the spectrum of reflected light is detected by the mid-infrared camera 4, thereby obtaining the correction spectrum W ref (n,w), D ref (n,w) can be obtained.

[0061] The first correction spectrum W measured under bright reflected light conditions ref In the case of (n, w), a calibration plate 11 (aluminum, stainless steel, etc.) that reflects all wavelengths in the mid-infrared region is placed, and with the light 10 turned on, data is acquired for all wavelengths (w = 0 (2700), 1 (2720), 2 (2740), ..., 130 (5300)) for all sensors (n = 0, 1, 2, ..., 317).

[0062] Second correction spectrum D measured under low reflected light conditions ref In the case of (n, w), a calibration plate 11 (aluminum, stainless steel, etc.) that reflects all wavelengths in the mid-infrared region is placed, and with the lighting 10 turned off (or the camera shutter closed), data is acquired for all wavelengths (w = 0 (2700), 1 (2720), 2 (2740), ..., 130 (5300)) for all sensors (n = 0, 1, 2, ..., 317).

[0063] The calibration plate 11 is, for example, as shown by the dotted arrow in FIG. ref (n,w), D ref It is preferable that the calibration plate 11 is installed so as to be movable between the position of the imaging area of ​​the mid-infrared camera 4 on the transport path 3 of the conveyor 2, where the calibration plate 11 is placed when acquiring (n, w), and a standby position that is outside the imaging area of ​​the mid-infrared camera 4 and the irradiation range of the illumination light 10. In other words, it is preferable that the calibration plate 11 can be fixed to a predetermined position within the field of view of the mid-infrared camera 4 and a predetermined position outside the field of view, and can be moved between these two predetermined positions. It is preferable that the calibration plate 11 is processed so that the main surface that receives the light from the illumination light 10 has a large surface roughness that is rough. This makes it possible to suppress the occurrence of halation of reflected light on the calibration plate 11.

[0064] Furthermore, the conveyor 2 may be stopped when the correction spectrum is acquired. In this case, if the calibration plate 11 is not correctly positioned in the imaging area of ​​the mid-infrared camera 4 due to some malfunction in the operation of the calibration plate 11, the temperature of the portion of the conveyor 2 on the transport path 3 irradiated with the infrared rays from the lighting 10 will rise, which may cause burning or fire. For this reason, if the calibration plate 11 is not fixed within the field of view of the mid-infrared camera 4, it is preferable to provide an interlock so that the lighting 10 does not irradiate infrared rays.

[0065] As shown in FIG. 7, the lighting 10 has a lamp 10A (sheath heater, carbon lamp, Kanthal lamp, etc.) which is a light source of infrared rays, and a reflector 10B which collects heat from the lamp 10A. The lamp 10A is formed so as to extend along the width direction (y direction) of the conveyor 2, and is arranged so as to radiate infrared rays in all directions around the axis along the y axis. The reflector 10B is arranged on the opposite side of the conveyor 2 from the conveying path 3 with respect to the lamp 10A, and is formed so as to be curved along the circumferential direction around the axis of the lamp 10A, so that it can collect infrared rays radiated from the lamp 10A to the opposite side of the conveyor 2, and reflect and send them to the conveyor 2 side. The reflector 10B is made of, for example, aluminum, stainless steel, or aluminum-plated material.

[0066] Returning to FIG. 6, in step S03, the preprocessing unit 51 generates a corrected spectrum S cor A characteristic wavelength region is extracted from (n, w). FIG. 8 is a diagram showing an example of a process for extracting a characteristic wavelength region from a reflected wave spectrum obtained when infrared rays are irradiated onto black waste plastic pieces. The horizontal axis of FIG. 8 indicates the wavelength (nm) of the spectrum, and the vertical axis indicates the intensity of the spectrum at each wavelength. FIG. 8 shows an example of the spectrum of each material, acrylonitrile-butadiene-styrene (ABS), high impact polystyrene (HIPS), polypropylene (PP), and polyethylene (PE). In the example of FIG. 8, the spectrum of the wavelength region of 3250 to 3750 (nm) and 4400 to 4600 (nm) is extracted. In the example of FIG. 8, the range of the wavelength region to be extracted is shown by a hatched pattern. Therefore, when sorting black plastics by material, the spectrum of at least one of the wavelength regions in the above ranges can be used.

[0067] 6, in step S04, the first determination unit 52 uses the spectrum corrected in step S02 and from which a characteristic wavelength region has been extracted in step S03 to determine whether each spectrum is the belt (conveyance path 3) of the conveyor 2 or an object (waste plastic) on the conveyance path 3. In this embodiment, the first determination unit 52 makes the determination by using a trained One Class SVM.

[0068] In step S05, the second judgment unit 53 extracts two types of feature data Score1 and Score2 from the spectrum judged to be an object (waste plastic) in step S04 using the trained PLS. FIG. 9 is a diagram showing an example of extracted feature data. The horizontal axis of FIG. 9 indicates the first feature data (Score1), and the vertical axis indicates the second feature data (Score2). FIG. 9 shows an example of extraction of four types of materials, ABS, HIPS, PP, and PE, as exemplified in FIG. 8. As shown in FIG. 9, it can be seen that the areas plotted for each material can be divided in a two-dimensional space using the two types of feature data Score1 and Score2. The number of types of feature data may be other than two.

[0069] Returning to FIG. 6, in step S06, the third judgment unit 54 discriminates the material using a trained decision tree based on the two types of feature data Score1 and Score2 extracted in step S5. FIG. 10 is a diagram showing an example of material discrimination using a decision tree. In this embodiment, in order to ultimately discriminate four types of materials (PE, PP, ABS, HIPS), the decision tree has two levels of conditional branching as shown in FIG. 10. In the first level, a set of feature data Score1 and Score2 is divided into two groups G1 and G2 using a conditional branching function f1 (Score1, Score2). In the second level, one group G1 is further divided into two groups G11 and G12 using a conditional branching function f2 (Score1, Score2). In the second level, the other group G2 is further divided into two groups G21 and G22 using a conditional branching function f3 (Score1, Score2). As a result, the pairs of feature data Score1 and Score2 are classified into four groups G11, G12, G21, and G22, and the materials of each group are determined to be PE, PP, ABS, and HIPS, respectively.

[0070] As such, the discrimination device 5 of the waste plastic material discrimination and sorting apparatus 1 in this embodiment is equipped with a first judgment unit 52 that judges whether the spectrum of reflected light of light irradiated by the lighting 10 onto the conveying path 3 of the conveyor 2, detected by the mid-infrared camera 4, is from either the waste plastic piece S or the conveying path 3, a second judgment unit 53 that extracts two types of feature data Score1 and Score2 from the spectrum judged to be the waste plastic piece S by the first judgment unit 52, and a third judgment unit 54 that discriminates the materials S1 and S2 of the waste plastic piece S based on the feature data Score1 and Score2 extracted by the second judgment unit 53.

[0071] With this configuration, output information on the material of waste plastic can be obtained from the input information of the reflection spectrum through three stages of judgment processing and data narrowing: narrowing down to the spectrum of black waste plastic pieces S by object discrimination in the first judgment unit 52, dimensional compression from the spectrum information to feature data by feature amount extraction in the second judgment unit 53, and classification processing in the third judgment unit 54. Therefore, the waste plastic sorting device 1 of this embodiment can judge the material of waste plastic taking into account various conditions, and can perform detailed judgment over multiple stages, improving the accuracy of judging the material of waste plastic.

[0072] In addition, the discrimination device 5 of the waste plastic sorting device 1 according to this embodiment detects the reflection spectrum S org (n, w) is the first correction spectrum W measured under bright reflected light conditions. ref (n,w) and the second correction spectrum D measured under relatively darker conditions. ref A pre-processing unit 51 is provided for performing correction using (n, w).

[0073] Thus, the reflectance spectrum S org (n, w) is, for example, calculated using equation (1) as the correction spectrum W ref (n,w), D ref By correcting using (n, w), it is possible to suppress differences in the characteristics of the spectral intensity due to the influence of the temperature of the black waste plastic pieces S1 and S2 to be measured, the aging of the mid-infrared camera 4, the position on the conveyor 2, etc. cor By using (n, w) to perform learning and judgment in the first judgment unit 52, the second judgment unit 53, and the third judgment unit 54, it is possible to further improve the accuracy of judgment of the material of the waste plastic.

[0074] The preprocessing unit 51 further outputs the corrected spectrum S cor A predetermined frequency range is cut out from (n, w) and the processed spectrum is output to the first determination unit 52.

[0075] With this configuration, parts of the spectrum that are closely related to the material of the waste plastic can be extracted and used for learning and judgment by the first judgment unit 52, the second judgment unit 53, and the third judgment unit 54, thereby reducing the inclusion of noise that hinders learning and judgment, and further improving the accuracy of determining the material of the waste plastic.

[0076] In this embodiment, the pre-processing unit 51 detects the reflection spectrum S org Two processes are performed: a correction process for (n, w) and a process for extracting a predetermined frequency range. However, a configuration may be adopted in which only one of the two processes is performed.

[0077] <Waste plastic piece sorting system> FIG. 11 is a side view showing a schematic configuration of a waste plastic sorting system 1A according to the first embodiment.

[0078] 11, the sorting system 1A of the first embodiment includes two sorting devices, a first sorting device 1A1 and a second sorting device 1A2. The surface treatment device 20 performs surface treatment only on the waste plastic pieces transported by the transport device 13 from the first sorting device 1A1 to the second sorting device 1A2.

[0079] The configurations of the first sorting device 1A1 and the second sorting device 1A2 are the same as those of the sorting device 1 described above. That is, the first sorting device 1A1 has a conveyor 2A, a conveying path 3A, a mid-infrared camera 4A, a discrimination device 5A (first discrimination unit), a jetting control unit 6A, a jetting nozzle row 7A, a vibrating feeder 8A, a partition plate 9A, a lighting 10A1, and a sorting unit 12A (first sorting unit). Similarly, the second sorting device 1A2 has a conveyor 2B, a conveying path 3B, a mid-infrared camera 4B, a discrimination device 5B (second discrimination unit), a jetting control unit 6B, a jetting nozzle row 7B, a vibrating feeder 8B, a partition plate 9B, a lighting 10B1, and a sorting unit 12B (second sorting unit). Each component of the first sorting device 1A1 and the second sorting device 1A2 has the same configuration and function as the conveyor 2, the conveying path 3, the mid-infrared camera 4, the discrimination device 5, the injection control unit 6, the injection nozzle row 7, the vibrating feeder 8, the partition plate 9, the lighting 10, and the sorting unit 12 of the above-mentioned sorting device 1.

[0080] On the transport path of the waste plastic pieces, the first sorting device 1A1 is disposed on the upstream side, and the second sorting device 1A2 is disposed on the downstream side. A transport device 13 (transport section) is disposed between the first sorting device 1A1 and the second sorting device 1A2. In the example of FIG. 11, the surface treatment device 20 is illustrated as being disposed immediately before the second sorting device 1A2 on the upstream side, but it may be disposed between the first sorting device 1A1 and the second sorting device 1A2.

[0081] The sorting system 1A of the first embodiment performs two-stage sorting, a first sorting by a first sorting device 1A1 and a second sorting by a second sorting device 1A2. In Fig. 11, as an example of this two-stage sorting, a device is shown that judges and sorts waste plastic pieces S1 of one material from a waste plastic piece group in which waste plastic pieces S1 made of one material and waste plastic pieces S2 made of a different material from the waste plastic pieces S1, similar to the above-mentioned sorting device 1. However, in the example of Fig. 11, the waste plastic piece group also includes waste plastic pieces S1A that are made of the same material as the waste plastic pieces S1 but have different surface properties.

[0082] The waste plastic piece S1 has surface properties to such an extent that, when light is irradiated onto it, a reflection spectrum effective for identifying the material can be obtained. On the other hand, the waste plastic piece S1A has surface properties to such an extent that, when light is irradiated onto it, a reflection spectrum effective for identifying the material cannot be obtained. In other words, in the example of FIG. 11, the surface of the waste plastic piece S1 is included in the effective range of various conditions such as SMD and glossiness after surface treatment by the surface treatment device 20 in the above-mentioned sorting device 1. On the other hand, the surface of the waste plastic piece S1A is not included in these effective ranges.

[0083] In FIG. 11, the waste plastic pieces S1 are shown as triangles, the waste plastic pieces S2 are shown as squares, and the waste plastic pieces S1A are shown as circles.

[0084] In the first sorting by the first sorting device 1A1, the waste plastic pieces S1, S2, and S1A are sorted by type without undergoing surface treatment. In the first sorting, the discrimination device 5A and the sorting section 12A can select the waste plastic pieces S1 that have sufficient surface properties for sorting. However, the waste plastic pieces S1A that have insufficient surface properties for sorting are not sorted as the waste plastic pieces S1, even though they are made of the same material as the waste plastic pieces S1, but are sorted together with other waste plastic pieces S2 as the remaining plastic pieces S2 and S1A other than the specific waste plastic pieces S1.

[0085] The conveying device 13 conveys the remaining plastic pieces S2 and S1A selected by the first sorting device 1A1 to the second sorting device 1A2. These plastic pieces S2 and S1A are surface treated by the surface treatment device 20 before being fed into the second sorting device 1A2. Similar to the above-mentioned sorting device 1, the surface treatment device 20 performs surface treatment on the plastic pieces so that when light is irradiated, the surface has a degree of surface quality that allows a reflection spectrum effective for identifying the material to be obtained.

[0086] In the second sorting by the second sorting device 1A2, the types of waste plastic pieces S2 and S1A are sorted after the surface treatment is applied to the waste plastic pieces S2 and S1A by the surface treatment device 20. In the second sorting, the discrimination device 5B and the sorting section 12B can sort the surface-treated waste plastic pieces S1A as being of the same material as the waste plastic pieces S1. On the other hand, the waste plastic pieces S2 are sorted as the remaining plastic pieces other than the specific waste plastic pieces S1.

[0087] Thus, the sorting system 1A of the first embodiment comprises a discrimination device 5A that irradiates light onto the waste plastic pieces S1, S2, and S1A and determines the material based on the spectrum of the reflected light, a sorting unit 12A that sorts the waste plastic piece S1 based on the judgment result of the discrimination device 5A, a surface treatment device 20 that processes the surfaces of the remaining waste plastic pieces S2 and S1A of the waste plastic pieces sorted by the sorting unit 12A, a discrimination device 5B that irradiates light onto the waste plastic pieces S2 and S1A that have been surface treated by the surface treatment device 20 and determines the material based on the spectrum of the reflected light, and a sorting unit 12B that sorts the waste plastic piece S1A that has been surface treated based on the judgment result of the discrimination device 5B.

[0088] With these configurations, similar to the sorting device 1 described above, by performing surface treatment on the plastic pieces to be sorted, it becomes possible to obtain a reflection spectrum that is effective for identifying the material when light is irradiated onto them, thereby improving the accuracy of determining the type of waste plastic piece.As a result, the waste plastic can be sorted by material with high precision.

[0089] Furthermore, in the sorting system 1A of the first embodiment, before the second sorting by the discriminator 5B and the sorting unit 12B after the surface treatment of the waste plastic pieces, the first sorting by the discriminator 5A and the sorting unit 12A is performed without performing the surface treatment, so that the waste plastic pieces S1 that can be sorted without performing the surface treatment can be sorted in advance in the first sorting and can be excluded from the second sorting. Therefore, the number of plastic pieces S2 and S1A to be surface-treated by the surface treatment device 20 can be reduced, making it possible to suppress unnecessary surface treatment and to improve the efficiency of the sorting process of the waste plastic pieces. As a result, the recovery rate of the waste plastic pieces can be increased overall while suppressing the targets of the surface treatment. In addition, by narrowing down the targets of the surface treatment, it is possible to suppress the consumption of materials (e.g., abrasives) for the surface treatment of the surface treatment device 20, and the cost of the sorting process can be reduced.

[0090] Furthermore, since the first sorting device 1A1 and the second sorting device 1A2 use judgment methods and sorting methods similar to those of the sorting device 1 described above, the sorting methods of each device themselves require few changes from the sorting device 1, and high-precision sorting can be achieved at low cost.

[0091] In addition, a configuration in which three or more stages of sorting are performed may be configured by providing another sorting device downstream of the two sorting devices 1A1 and 1A2 shown in Fig. 11. With this configuration, for example, when the plastic pieces S2 sorted by the second sorting device 1A2 as the remaining plastic pieces other than the specific waste plastic pieces S1 include multiple types, it becomes possible to further sort another specific type of waste plastic pieces, thereby increasing the number of types that can be sorted and improving the versatility of the sorting system.

[0092] [Second embodiment] The second embodiment will be described with reference to Fig. 12. Fig. 12 is a side view showing a schematic configuration of a waste plastic sorting system 1B according to the second embodiment.

[0093] The sorting system 1B of the second embodiment includes a single sorting device 1B1, a transport device 13, and a surface treatment device 20.

[0094] The configuration of the single sorting device 1B1 is similar to that of the above-described sorting device 1, and therefore a description of each element will be omitted.

[0095] The conveying device 13 re-inputs the waste plastic pieces output from the single sorting device 1B1 into this sorting device 1B1.

[0096] The surface treatment device 20 performs surface treatment on the waste plastic pieces re-input by the conveying device 13. The surface treatment device 20 is disposed on the path of the conveying device 13, for example.

[0097] The sorting system 1B of the second embodiment includes such a conveying device 13, and the surface treatment device 20 performs surface treatment only on the waste plastic pieces re-input by the conveying device 13. Moreover, the sorting system 1B of the second embodiment performs two-stage sorting using only a single sorting device 1B1.

[0098] The sorting system 1B of the second embodiment performs two-stage sorting, a first sorting and a second sorting, using a single sorting device 1B1. As an example of this two-stage sorting, Fig. 12 shows an apparatus that determines and sorts the waste plastic pieces S1 of a material from a group of waste plastic pieces including the waste plastic pieces S1, S2, and S1A, similar to the example of the first embodiment in Fig. 11.

[0099] In the first sorting, the waste plastic pieces S1, S2, and S1A are sorted by type without undergoing any surface treatment. In the first sorting, the discrimination device 5 and the sorting section 12 can select the waste plastic pieces S1 that have sufficient surface properties for sorting. However, the waste plastic pieces S1A that have insufficient surface properties for sorting are not sorted as the waste plastic pieces S1, even though they are made of the same material as the waste plastic pieces S1, but are sorted together with other waste plastic pieces S2 as the remaining plastic pieces S2 and S1A other than the specific waste plastic pieces S1.

[0100] The conveying device 13 conveys the remaining plastic pieces S2 and S1A that have been selected by the sorting device 1B1 to be re-input into the sorting device 1B1. These plastic pieces S2 and S1A are surface-treated by the surface treatment device 20 before being re-introduced into the sorting device 1B1. As a result, as shown in FIG. 12, the waste plastic pieces S1A are processed in the surface treatment device 20 so that they have the same surface properties as the waste plastic pieces S1.

[0101] In the second sorting, the waste plastic pieces S2 and S1A are sorted by type after being surface-treated by the surface treatment device 20. In the second sorting, the discrimination device 5 and the sorting section 12 can sort the surface-treated waste plastic pieces S1A as being of the same material as the waste plastic pieces S1.

[0102] In this way, in the sorting system 1B of the second embodiment, the discrimination device 5 functions as a first discrimination unit that irradiates light onto the waste plastic pieces S1, S2, and S1A before surface treatment and determines the material based on the spectrum of the reflected light in the first sorting before the surface treatment by the surface treatment device 20. The discrimination device 5 functions as a second discrimination unit that irradiates light onto the waste plastic pieces S2 and S1A that have been subjected to surface treatment and determines the material based on the spectrum of the reflected light in the second sorting after the surface treatment by the surface treatment device 20.

[0103] In addition, the sorting unit 12 functions as a first sorting unit that sorts the waste plastic pieces S1 based on the judgment result of the first discrimination device 5 in the first sorting before the surface treatment by the surface treatment device 20. The sorting unit 12 functions as a second sorting unit that sorts the waste plastic pieces S1A that have been subjected to surface treatment based on the judgment result of the second discrimination device 5 in the second sorting after the surface treatment by the surface treatment device 20.

[0104] With these configurations, it is possible to suppress unnecessary surface treatment of waste plastic pieces, and to improve the efficiency of the sorting process of waste plastic pieces, as in the first embodiment. Furthermore, since two-stage sorting can be performed with only a single sorting device 1B1, there is no need to increase the number of sorting devices to improve the accuracy of sorting, and the high accuracy of sorting can be achieved at a lower cost.

[0105] It is also possible to configure the system so that when re-feeding the surface-treated plastic pieces S2 and S1A from the conveying device 13, new waste plastic pieces that have not been surface-treated (including S1, S2, and S1A in the example of FIG. 12) are mixed in and fed. With this configuration, the second sorting of any group of plastic pieces and the first sorting of the next group can be performed simultaneously, shortening the time required to complete the sorting process for all plastic pieces.

[0106] [Third embodiment] The third embodiment will be described with reference to Fig. 13. Fig. 13 is a plan view showing a schematic configuration of a waste plastic sorting system 1C according to the third embodiment. Fig. 13 shows a simplified diagram corresponding to the plan view of the sorting device 1 shown in Fig. 3. In the example of Fig. 13, as an example of a sorting method, a plastic mix containing waste plastic pieces of five types of materials (1), (2), (3), (4), and (5) is treated as a sorting target, and an example of sorting waste plastic pieces of a specific material (1) from this plastic mix is ​​described.

[0107] The sorting system 1C of the third embodiment includes a single sorting device 1C1, a conveying device 13, and a surface treatment device 20. The schematic configuration of the single sorting device 1C1 is similar to that of the above-described sorting device 1, so that the description of the elements with the same reference numerals will be omitted.

[0108] In the example of Fig. 13, the transport path 3 of the conveyor 2 is divided into two systems, a first system and a second system, in the width direction (y direction). More specifically, the inlet (vibration feeder 8), the conveyor 2, and the sorting unit 12 are each divided into two systems in the width direction. Note that the inlet 8 and the conveyor 2 are not divided into two components, but rather a partition or the like is attached to a single element to prevent mixing between the systems. For example, the transport path 3 of the conveyor 2 can be divided into two systems by providing a partition wall along the transport direction at approximately the center position in the width direction.

[0109] In the following description, the first system is denoted by the subscript A, and the second system is denoted by the subscript B.

[0110] In the sorting section 12, the waste plastics are separated into two main types by starting and stopping the spraying of each spray nozzle in the spray nozzle row 7, using the partition plate 9 shown in Fig. 2 etc. as a boundary. For this reason, in the following explanation, the elements sorted into two types in the first-system sorting section 12 will be referred to as "sorting section A1" and "sorting section B1", and the elements sorted into two types in the first-system sorting section 12 will be referred to as "sorting section A2" and "sorting section B2".

[0111] Further, the discriminator 5 is functionally divided into a "discriminator A" applied to the first system and a "discriminator B" applied to the second system.

[0112] The sorting system 1C of the third embodiment includes a conveying device 13 that re-inputs waste plastic pieces output from a single sorting device 1C1 into the sorting device 1C1, and the surface treatment device 20 performs surface treatment only on the waste plastic pieces re-input by the conveying device 13. The sorting system 1C of the third embodiment also performs two-stage sorting using only the single sorting device 1C1. Furthermore, the sorting system 1C of the third embodiment simultaneously performs two-stage sorting by providing two systems, the first and second systems, in parallel on the conveying path 3.

[0113] The sorting system 1C of the third embodiment performs two-stage sorting: a first sorting by a first system A of the sorting device 1C1, and a second sorting by a second system B of the sorting device 1C1. Figure 13 shows, as an example of this two-stage sorting, an apparatus that determines and sorts waste plastic pieces (1) of a specific material from a plastic mix containing waste plastic pieces (1) to (5) of five different materials.

[0114] In the first sorting, in the first system A, the waste plastic pieces (1) to (5) are sorted by type without undergoing any surface treatment. In the first sorting, the discrimination device A (first discrimination section) and the sorting section A1 (first sorting section) can select the waste plastic pieces (1) that have surface properties sufficient for sorting. However, the waste plastic pieces with surface properties insufficient for sorting ("a small amount of (1)" in the figure) are not sorted as the waste plastic pieces (1) even though they are made of the same material as the waste plastic pieces (1), and are sorted by the sorting section A2 together with the other waste plastic pieces (2) to (5) as a remaining group of plastic pieces that includes a mixture of waste plastic pieces other than the specific waste plastic pieces (1).

[0115] The conveying device 13 conveys the remaining plastic pieces selected by the sorting section A2 ((2), (3), (4), (5) and a small amount of (1) in the figure) to be input into the second system B. These plastic pieces are surface treated by the surface treatment device 20 before being input into the input port B of the second system B. As a result, in the surface treatment device 20, the small amount of waste plastic pieces (1) that were not sorted in the first sorting are processed so that they have the same surface properties as the waste plastic pieces (1) selected in the first sorting.

[0116] In the second sorting, in the second system B, the waste plastic pieces are sorted by type after being surface-treated by the surface treatment device 20. In the second sorting, the discrimination device B (second discrimination unit) and the sorting unit B1 (second sorting unit) can sort the waste plastic pieces (1) after the surface treatment as being of the same material as the waste plastic pieces (1) sorted in the first sorting. The sorting unit B2 sorts the group of plastic pieces in which other types of waste plastic pieces (2) to (5) are mixed.

[0117] In this way, the sorting system 1C of the third embodiment, like the first embodiment, can suppress unnecessary surface treatment of waste plastic pieces, and can make the sorting process of waste plastic pieces more efficient. Also, like the second embodiment, two-stage sorting can be performed with only a single sorting device 1C1, so there is no need to increase the number of sorting devices to improve the accuracy of sorting, and high accuracy of sorting can be achieved at even lower cost. Furthermore, by providing the first and second systems A and B in parallel on the conveying path 3, two-stage sorting can be performed simultaneously, so the time required to complete the sorting process of all plastic pieces can be shortened. EXAMPLES

[0118] (Example 1) In this embodiment, a group of black waste plastic pieces (plastic mix) was used as the target of sorting. The size of each plastic piece was about 5 to 30 mm in average diameter in plan view. The group of black waste plastic pieces used was a group of plastic pieces containing at least seven types of plastic pieces, namely polyethylene (PE), polypropylene (PP), polycarbonate / acrylonitrile-butadiene-styrene (PCABS), acrylonitrile-butadiene-styrene (ABS), polystyrene (PS), polyphenylene ether / polystyrene (PPEPS), and polyamide (PA), but also contained plastics other than the above seven types of plastics. Such a group of black waste plastic pieces was sorted by material using a sorting device similar to the sorting device 1 shown in Figures 1 to 3. The weight of the group of black waste plastic pieces used in one trial was 2.35 kg. The conveyor speed of the sorting device was 120 to 150 m / min.

[0119] In the sorting device, infrared rays of 3 to 5 μm were irradiated and the reflected light spectrum was detected. From the reflected light spectrum obtained, spectra in the wavelength ranges of 3250 to 3750 nm and 4400 to 4600 nm were extracted, and characteristic quantities were calculated. Based on the characteristic quantities, the plastic material was determined.

[0120] In the sorting device used in this embodiment, a nozzle row in which 318 nozzles are arranged in a direction perpendicular to the conveying direction is provided. The discrimination device in the sorting device was capable of registering seven types of plastics: polyethylene (PE), polypropylene (PP), polycarbonate / acrylonitrile-butadiene-styrene (PCABS), acrylonitrile-butadiene-styrene (ABS), polystyrene (PS), polyphenylene ether / polystyrene (PPEPS), and polyamide (PA). In addition, for each trial, one or more types of plastics could be selected to be blown off by injecting air from the nozzle (selectively blown).

[0121] Waste plastics were sorted by selective spraying in Trials 1-A and 1-1 to 1-7 shown below.

[0122] Trial 1-A: Selective spraying of all seven types of plastic Trial 1-1: Selective spraying of PE only Trial 1-2: Selective spraying of PP only Trial 1-3: Selective spraying of only PCABS Trial 1-4: Selective spraying of ABS only Trial 1-5: PS only sprayed Trial 1-6: Selective spraying of PPEPS only Trial 1-7: Selective spraying of PA only

[0123] <Measurement and Evaluation> To evaluate the accuracy of sorting, the recovery rate R of all seven types of plastics in the collected material obtained in Trial 1-A was A (%), recovery rate R of various plastics in the collected materials obtained in trials 1-1 to 1-7 PE , R PP , ...(%), and the purity R of various plastics in the recovered materials obtained in Trials 1-1 to 1-7. PE , R PP The results are shown in Table 1.

[0124] (Recovery rate R A (Calculation of Recovery rate R of all seven types of plastics in Trial 1-A A (%) was calculated as follows:

[0125] R A (%)=W A / W L ×100 ·W L (kg): Amount of waste plastic pieces (plastic mix) input ·W A (kg): Amount of all 7 types of waste plastic pieces collected (amount of plastic pieces blown away by selective spraying)

[0126] (Recovery rate R PE , RPP , ...) Recovery rate R of various plastics in trials 1-1 to 1-7 PE , R PP , ... (%) was calculated as follows: First, a group of waste plastic pieces with the content ratio and amount of each material shown in Table 2 was prepared and each trial was carried out, and the recovery rate for each type of plastic was calculated based on the actually recovered amount.

[0127] For example, R in trial 1-1 PE was calculated from the following formula: R PE (%)=W1 PE / sWA PE ×100 W1 PE (kg): Actual recovery amount of PE from Trial 1-1 ·sWA PE (kg): PE content (Table 2) The recovery rates of the other plastics in Trials 1-2 to 1-7 were similarly determined.

[0128] (Purity R PE , R PP , …) Purity of the recovered material from Trials 1-1 to 1-7 P PE , P PP , ...(%) are the content ratios of various plastics in each collected material in each trial. These purities were obtained by feeding the plastic pieces collected in each trial of the sorting device back into the sorting device and using the plastic ratio determination function of the sorting device. For example, the purity P in Trial 1-1 was PE was the PE content measured by the plastic ratio determination function. The same was true for the other plastics in Trials 1-2 to 1-7.

[0129] (Measurement of surface properties) As a surface characteristic of the plastic pieces after surface treatment, the glossiness (specular glossiness (%)) was measured according to JIS Z 8741. A glossmeter "VG 7000" manufactured by Nippon Denshoku Industries Co., Ltd. was used for the measurement, and the glossiness (specular glossiness (%)) was measured at an incidence angle of 60° and an incidence angle of 75°. In addition, the mean deviation of the surface roughness (SMD) of the plastic pieces after surface treatment was measured using an automated surface tester "KES-FB4-A" manufactured by Kato Tech Co., Ltd. Table 3 shows the measurement results of the surface characteristics of PCABS and PS as representative examples.

[0130] (Example 2) Except for not carrying out surface treatment, the plastic pieces were sorted by material in the same manner as in Example 1. As in Example 1, selective spraying was carried out in Trials 2-A and 2-1 to 2-7 shown below.

[0131] Trial 2-A: Selective spraying of all seven types of plastic Trial 2-1: Selective spraying of PE only Trial 2-2: Selective spraying of PP only Trial 2-3: Selective spraying of only PCABS Trial 2-4: Selective spraying of ABS only Trial 2-5: PS only sprayed Trial 2-6: Selective spraying of PPEPS only Trial 2-7: Selective spraying of PA only

[0132] The content ratio, content, recovery rate, and purity were determined in the same manner as in Example 1. The results are shown in Tables 1 and 2. In addition, the surface properties of the plastic pieces before sorting were determined in the same manner as in Example 1. The results are shown in Table 3.

[0133] [Table 1]

[0134] [Table 2]

[0135] [Table 3]

[0136] Table 1 shows the results of the selective spraying trials of all seven types of plastics (Trial 1-A in Example 1 and Trial 2-A in Example 2) and the selective spraying trials of various representative plastics (Trials 1-3 to 1-6 in Example 1 and Trials 2-3 to 2-6 in Example 2), comparing Example 1 (with surface treatment) with Example 2 (without surface treatment). From these results, it was found that the recovery rate and purity of the plastic pieces were improved by performing surface treatment before sorting the waste plastic pieces. In particular, it was found that the recovery rate and purity of the plastic pieces were improved by performing surface treatment so that the gloss (specular gloss (%)) at an incident angle of 60° measured in accordance with JIS Z 8741 was 10 or less, the gloss (specular gloss (%)) at an incident angle of 75° measured in accordance with JIS Z 8741 was 25 or less, or the surface roughness mean deviation (SMD) was 1 μm or more.

[0137] (Example 3) A group of plastic pieces having surface properties sufficient for sorting even without surface treatment were prepared, mixed with the group of plastic pieces used in Example 2 above, and sorted by material using an apparatus similar to the sorting system 1A shown in Figure 10. The trial conditions for each element of the first sorting device 1A1 and the second sorting device 1A2 were similar to those for the sorting device 1 shown in Example 1.

[0138] Table 4 shows the measurement results of the surface properties of PCABS and PS, which are representative examples of the plastic pieces used in the trial.

[0139] [Table 4]

[0140] As shown in Table 4, the surface properties of the plastic pieces having sufficient surface properties for sorting even without surface treatment were shown to be in a range between those of the plastic pieces having sufficient surface properties for sorting after surface treatment (Example 1) shown in Table 3 and those of the plastic pieces not having sufficient surface properties for sorting before surface treatment (Example 2).

[0141] When the plastic pieces of PCABS Example 2 and Example 3 were mixed and fed into the first sorting device 1A1, the percentage of the plastic pieces that were sorted and recovered as PCABS was about 65% of the amount fed into the first sorting device 1A1. On the other hand, the percentage of the plastic pieces that were not determined to be PCABS and were not sorted out was about 35% of the amount fed into the first sorting device 1A1.

[0142] Next, the plastic pieces that were not determined to be PCABS and sorted out by the first sorting device 1A1 were surface treated by the surface treatment device 20 to give them the same surface properties as in Example 1, and then fed into the second sorting device 1A2. The proportion of pieces sorted out and recovered as PCABS was about 70% of the amount fed into the second sorting device 1A2. In other words, the total recovery rate for the first and second sorting was about 90% of the amount initially fed into the first sorting device 1A1.

[0143] On the other hand, the proportion of plastic pieces that were not determined to be PCABS and were not sorted out in the second sorting device 1A2 was about 30% of the amount fed into the second sorting device 1A2. In other words, about 10% of the total amount fed into the first sorting device 1A1 was left as residue.

[0144] In this way, by using a two-stage sorting method such as in the present embodiment Achi, in which a first sorting is performed using a first sorting device 1A1, surface treatment is applied to only the plastic pieces that escape the sorting, and then a second sorting is performed using a second sorting device 1A2, it has been shown that the recovery rate can be improved compared to that shown in Example 1, and that it is possible to sort waste plastic by material with greater precision.

[0145] The present embodiment has been described above with reference to specific examples. However, the present disclosure is not limited to these specific examples. Any design modifications made by a person skilled in the art to these specific examples are also included within the scope of the present disclosure as long as they have the features of the present disclosure. The elements of each of the above-mentioned specific examples and their arrangements, conditions, shapes, etc. are not limited to those exemplified and can be changed as appropriate. The combination of each of the elements of each of the above-mentioned specific examples can be changed as appropriate as long as no technical contradiction occurs. [Explanation of symbols]

[0146] 1A, 1B, 1C Waste plastic sorting system 1A1 First sorting device 1A2 Second sorting device 1, 1B1, 1C1 Sorting device 2, 2A, 2B Conveyor 3, 3A, 3B conveyance path 4, 4A, 4B Mid-infrared camera (reflection spectrum detection section) 5 Discrimination device (discrimination unit, first discrimination unit, second discrimination unit) 5A Discrimination device (1st discrimination section) 5B Discrimination device (second discrimination section) 6, 6A, 6B Injection control section 7, 7A, 7B Injection nozzle row 8, 8A, 8B Vibration feeder 12 Sorting Section (First Sorting Section, Second Sorting Section) 12A Sorting Section (First Sorting Section) 12B Sorting Section (Second Sorting Section) 13 Conveying device (conveying section) 20 Surface treatment equipment (surface treatment unit) 21, 22 Large Lola 23, 25 Rough surface roller 28 Supply section 51 Pretreatment section 52 First judgment unit (first judgment means) 53 Second judgment unit (second judgment means) 54 Third judgment unit (third judgment means) S, S1, S2, S1A Waste plastic pieces S' Waste plastic pieces before surface treatment

Claims

1. a first discrimination unit that irradiates light onto the waste plastic pieces transported on the transport path and discriminates the material based on the spectrum of the reflected light; A first sorting unit that sorts the waste plastic pieces based on the judgment result of the first discrimination unit; A surface treatment section which treats the surfaces of the remaining waste plastic pieces of the waste plastic pieces sorted by the first sorting section; A second discrimination unit that irradiates light onto the waste plastic pieces that have been surface-treated by the surface treatment unit and determines the material based on the spectrum of reflected light; A second sorting unit that sorts the waste plastic pieces that have been subjected to the surface treatment based on the judgment result of the second discrimination unit; A waste plastic sorting system equipped with

2. a first sorting device having the first discrimination unit and the first sorting unit; a second sorting device having the second discrimination unit and the second sorting unit; Equipped with The waste plastic sorting system according to claim 1.

3. A single sorting device having a discrimination unit that irradiates light onto waste plastic pieces and determines the material based on the spectrum of reflected light, and a sorting unit that sorts the waste plastic pieces based on the judgment result of the discrimination unit; A conveying unit that re-inputs the waste plastic pieces output from the single sorting device into the single sorting device; Equipped with The surface treatment unit performs a surface treatment on the waste plastic pieces re-input by the conveying unit, The discrimination unit is The surface treatment part functions as the first discrimination part before the surface treatment by the surface treatment part, and functions as the second discrimination part after the surface treatment by the surface treatment part, The sorting unit includes: Before the surface treatment by the surface treatment section, the sorting section functions as the first sorting section, and after the surface treatment by the surface treatment section, the sorting section functions as the second sorting section. The waste plastic sorting system according to claim 1.

4. A single sorting device; A conveying unit that re-inputs the waste plastic pieces output from the single sorting device into the single sorting device; Equipped with The surface treatment unit performs a surface treatment on the waste plastic pieces re-input by the conveying unit, The conveying path is divided into two systems, a first system and a second system, in the width direction, The first system has the first discrimination unit and the first sorting unit, and collects waste plastic pieces of a desired material and supplies the remaining waste plastic pieces to the second system via the conveying unit; The second system has the second discrimination unit and the second sorting unit, and further collects the waste plastic pieces of the desired material after surface treatment from the remaining waste plastic pieces that have been surface-treated by the surface treatment unit. The waste plastic sorting system according to claim 1.

5. In the surface treatment section, the surface of the waste plastic pieces is (a) A specular gloss at an incident angle of 60° measured in accordance with JIS Z 8741 is 10% or less; (b) A specular gloss at an incident angle of 75° measured in accordance with JIS Z 8741 is 25% or less; and (c) Surface roughness mean deviation (SMD) is 1 μm or more The processing is performed so as to satisfy one or more of the following conditions: The waste plastic sorting system according to any one of claims 1 to 4.

6. The irradiated light includes mid-infrared light having a wavelength of more than 3 μm. The waste plastic sorting system according to any one of claims 1 to 5.

7. The first discrimination unit and the second discrimination unit A first determination means for determining whether the spectrum of the reflected light is the spectrum of the waste plastic pieces or the spectrum of the transport path; A second determination means for extracting a feature amount from the spectrum determined to be the spectrum of the waste plastic pieces; A third determination means for determining the material of the waste plastic pieces based on the feature amount; Equipped with The first sorting unit and the second sorting unit sort the waste plastic pieces by material based on the result obtained by the third determination means. The waste plastic sorting system according to any one of claims 1 to 6.

8. a pre-processing unit that corrects the spectrum of the reflected light using a first correction spectrum obtained by measuring the reflected light under bright conditions and a second correction spectrum obtained by measuring the reflected light under dark conditions that are darker than the bright conditions; The first determination means performs the determination using the spectrum corrected by the pre-processing unit. The waste plastic sorting system according to claim 7.

9. The pre-processing unit performs processing to extract a predetermined frequency range from the corrected spectrum, The first determination means determines the material of the waste plastic pieces using the extracted spectrum. The waste plastic sorting system according to claim 8.

10. a first discrimination step of irradiating light onto the waste plastic pieces conveyed on the conveying path and discriminating the material based on the spectrum of the reflected light; A first sorting step of sorting the waste plastic pieces based on the judgment result of the first discrimination step; A surface treatment step of treating the surfaces of the remaining waste plastic pieces of the waste plastic pieces sorted in the first sorting step; A second determination step of irradiating light onto the waste plastic pieces that have been surface-treated in the surface treatment step and determining the material based on the spectrum of reflected light; A second sorting step of sorting the waste plastic pieces that have been subjected to the surface treatment based on the judgment result of the second discrimination step; A method for sorting waste plastics, comprising:

Citation Information

Patent Citations

  • Heattpumping means of twoostaged compressor type

    JP1978067145A

  • Method and apparatus for recycling part to be judged of plastic

    JP2001334572A

  • Apparatus and method for identifying resin

    JP2011102760A

  • Resin determination method and apparatus

    JP2018100903A

  • Optoelectronic device for multi-spectral spectroscopic identification of the polymer composition of an unknown plastic object and related methods

    US20170336264A1