WO2021161779A1 - Waste plastic material determination device, material determination method, and material determination program - Google Patents

Waste plastic material determination device, material determination method, and material determination program Download PDF

Info

Publication number
WO2021161779A1
WO2021161779A1 PCT/JP2021/002624 JP2021002624W WO2021161779A1 WO 2021161779 A1 WO2021161779 A1 WO 2021161779A1 JP 2021002624 W JP2021002624 W JP 2021002624W WO 2021161779 A1 WO2021161779 A1 WO 2021161779A1
Authority
WO
WIPO (PCT)
Prior art keywords
waste plastic
determination
spectrum
unit
determination unit
Prior art date
Application number
PCT/JP2021/002624
Other languages
French (fr)
Japanese (ja)
Inventor
大石　昇治
孝伸 村上
Original Assignee
大王製紙株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 大王製紙株式会社 filed Critical 大王製紙株式会社
Priority to KR1020227023966A priority Critical patent/KR20220137627A/en
Priority to CN202180011546.5A priority patent/CN115003425A/en
Publication of WO2021161779A1 publication Critical patent/WO2021161779A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/34—Sorting according to other particular properties
    • B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
    • C—CHEMISTRY; METALLURGY
    • C08—ORGANIC MACROMOLECULAR COMPOUNDS; THEIR PREPARATION OR CHEMICAL WORKING-UP; COMPOSITIONS BASED THEREON
    • C08J—WORKING-UP; GENERAL PROCESSES OF COMPOUNDING; AFTER-TREATMENT NOT COVERED BY SUBCLASSES C08B, C08C, C08F, C08G or C08H
    • C08J11/00—Recovery or working-up of waste materials
    • C08J11/04—Recovery or working-up of waste materials of polymers
    • C08J11/06—Recovery or working-up of waste materials of polymers without chemical reactions
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/27—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection ; circuits for computing concentration
    • G01N21/274—Calibration, base line adjustment, drift correction
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/85—Investigating moving fluids or granular solids
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N2021/845—Objects on a conveyor
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
    • Y02W30/00—Technologies for solid waste management
    • Y02W30/50—Reuse, recycling or recovery technologies
    • Y02W30/62—Plastics recycling; Rubber recycling

Definitions

  • This disclosure relates to a waste plastic material determination device, a material determination method, and a material determination program.
  • the object to be sorted is irradiated with infrared light to receive the reflected light from the object to be sorted, and the resin type of the object to be sorted is determined by a pattern matching method using a spectrum based on the reflected light. It is stated that.
  • An object of the present disclosure is to provide a material determination device, a material determination method, and a material determination program that can improve the determination accuracy of the material of waste plastic.
  • the waste plastic material determination device receives the irradiation unit that irradiates the waste plastic piece conveyed on the transport path with light and the reflected light of the light emitted by the irradiation unit.
  • a reflection spectrum detection unit that detects the spectrum of the reflected light
  • a first determination unit that determines whether the spectrum detected by the reflection spectrum detection unit is either the waste plastic piece or the transport path.
  • the material of the waste plastic piece is discriminated based on the second determination unit that extracts the feature amount from the spectrum determined by the first determination unit as the waste plastic piece and the feature amount extracted by the second determination unit. It includes a third determination unit.
  • Side view of the waste plastic material determination device shown in FIG. Top view of the waste plastic material determination device shown in FIG.
  • Functional block diagram of the discriminator Flowchart of material discrimination process of waste plastic according to the embodiment
  • the figure which shows the extraction method of the spectrum for correction The figure which shows an example of the process which cuts out a characteristic wavelength region from a reflected wave spectrum.
  • the figure which shows the extraction example of the feature data The figure which shows the example of the material discrimination using a decision tree
  • Top view showing the first material selection method by the material determination apparatus of this embodiment
  • Top view showing the second material selection method by the material determination apparatus of this embodiment.
  • the x direction, the y direction, and the z direction are perpendicular to each other.
  • the x-direction and the y-direction are horizontal directions, and the z-direction is a vertical direction.
  • the x direction is the transport direction of the transport path 3 of the conveyor 2.
  • the y direction is the width direction of the transport path 3 of the conveyor 2.
  • the z positive direction side may be expressed as the upper side and the z negative direction side may be expressed as the lower side.
  • FIG. 1 is a perspective view showing a schematic configuration of a waste plastic material determination device 1 according to an embodiment.
  • FIG. 2 is a side view of the waste plastic material determination device 1 shown in FIG.
  • FIG. 3 is a plan view of the waste plastic material determination device 1 shown in FIG.
  • the waste plastic to be determined as a material is a black waste plastic
  • two types of materials S1 and S2 (indicated by quadrangular and triangular marks in FIGS. 1 to 3) are mixed.
  • the black waste plastic pieces of the two types of materials S1 and S2 may be collectively represented by the reference numeral S.
  • the black waste plastic material determination device 1 conveys a vibration feeder 8 as an example of a supply unit that sequentially supplies black waste plastic pieces S1 and S2, and black waste plastic pieces S1 and S2 supplied by the vibration feeder 8.
  • a conveyor 2 as an example of a transport unit is provided as a main unit.
  • the crushed black waste plastic pieces S1 and S2 are supplied to the vibration feeder 8 via, for example, a charging hopper.
  • the vibration feeder 8 supplies the black waste plastic pieces S1 and S2 to the conveyor 2 while preventing the black waste plastic pieces S1 and S2 from being overlapped with each other by vibrating the mounting surface on which the black waste plastic pieces S1 and S2 are placed.
  • the conveyor 2 has a transport path 3 on its upper surface, and transports the black waste plastic pieces S1 and S2 on the transport path 3 in a direction away from the vibration feeder 8.
  • the material determination device 1 is an example of an illumination 10 as an example of an irradiation unit that irradiates the black waste plastic pieces S1 and S2 with infrared rays, and an example of a reflection spectrum detection unit that detects the reflection spectrum from the black waste plastic pieces S1 and S2.
  • the main part is a mid-infrared camera 4 as a main part, and a discriminating device 5 for identifying the materials of the black waste plastic pieces S1 and S2 based on the reflection spectrum detected by the mid-infrared camera 4.
  • the illumination 10 has a lamp 10A (see FIG.
  • the illumination 10 is installed on the mid-infrared camera 4 so that the reflected light from the black waste plastic pieces S1 and S2 enters the mid-infrared camera 4, and the lighting 10 is installed on both upper sides (or one side of the upper side) of the conveyor 2 in the flow direction with respect to the mid-infrared camera 4. ) Is installed.
  • one mid-infrared camera 4 can measure the entire width direction of the conveyor 2, and is divided into a plurality of (for example, 318) regions along the width direction and is black.
  • the reflected light of near infrared rays from the waste plastic pieces S1 and S2 can be received, and the spectrum of the reflected light can be measured for each region.
  • the mid-infrared camera 4 is composed of, for example, a camera with a spectroscope having a wavelength region of mid-infrared of 3 ⁇ m or more.
  • the mid-infrared camera 4 measures at a scan frequency of, for example, 230 Hz, and transmits 318 spectral data to the discriminating device 5 for each scan.
  • the discrimination device 5 outputs the material determination results of the 318 regions to the injection control unit 6, which will be described later, based on the 318 spectral data received from the mid-infrared camera 4.
  • the material determination device 1 is provided with an injection nozzle 7 that injects air laterally or diagonally in a direction intersecting the transport direction on the downstream side of the conveyor 2 in the transport direction.
  • a plurality of injection nozzles 7 (for example, 318) are arranged side by side in the width direction of the conveyor 2, and the operation of each nozzle is controlled by the injection control unit 6.
  • the injection control unit 6 injects or does not inject air from the injection nozzle 7 according to the material determination result received from the determination device 5, so that, for example, a plurality of regions (for example, a recovery hopper) classified by the partition plate 9 are formed. Black waste plastic pieces S1 and S2 are sorted and dropped to collect waste plastic of a desired material.
  • the injection control unit 6, the injection nozzle 7, and the partition plate 9 are made of a desired material from the waste plastic piece flowing through the transport path 3 of the conveyor 2 based on the material determination result by the discrimination device 5. It functions as a collecting device 12 for collecting things.
  • the vibration feeder 8 gives weight to the supplied black waste plastic pieces S1 and S2 while applying vibration. It is conveyed downstream so as not to become a conveyor 2 and supplied to the conveyor 2.
  • the black waste plastic pieces S1 and S2 supplied to the transport path 3 on the upper surface of the conveyor 2 are transported in the transport direction on the x positive direction side, and are infrared from the illumination 10 at a position where the mid-infrared camera 4 can take an image. Light is emitted.
  • the mid-infrared camera 4 receives the light reflected by the black waste plastic pieces S1 and S2 of the infrared rays emitted from the illumination 10, and outputs the light receiving result (data of the light receiving spectrum) to the discriminating device 5.
  • the discrimination device 5 identifies the materials of the black waste plastic pieces S1 and S2 based on the light receiving result input from the mid-infrared camera 4. The details of the material determination method by the determination device 5 will be described later with reference to FIGS. 4 to 9.
  • the discrimination device 5 outputs the material identification result to the injection control unit 6.
  • the injection control unit 6 selects the injection nozzle 7 according to the material from the plurality of the injection nozzles 7 arranged, measures the timing, and transmits the control signal.
  • the injection nozzle 7 that has received the control signal opens the nozzle opening and injects air. By injecting air from the injection nozzle 7 at an appropriate timing according to the discrimination result of the discrimination device 5, the material to be sorted and the material not to be sorted can be separated and collected.
  • the black waste plastic piece S1 on the conveyor 2 receives air from the air injection nozzle 7 that has received the control signal, is blown off by the collecting device 12 provided for each material, and falls. Will be recovered. Further, since the black waste plastic piece S2 on the conveyor 2 does not receive air from the injection nozzle 7, it is collected by a collecting device 12 different from the black waste plastic piece S1. By injecting and stopping the injection nozzle 7 in this way, black waste plastic pieces made of a plurality of materials can be sorted and collected for each material.
  • FIG. 4 is a functional block diagram of the discrimination device 5.
  • the discrimination device 5 includes a preprocessing unit 51, a first determination unit 52, a second determination unit 53, and a third determination unit 54.
  • the pretreatment unit 51 performs pretreatment such as correction and processing of the reflection spectra of the black waste plastic pieces S1 and S2 detected by the mid-infrared camera 4.
  • the preprocessing unit 51 corrects the detected reflection spectrum by using, for example, a spectrum measured under a bright condition and a spectrum measured under a dark condition.
  • the "dark condition” means a condition that is relatively darker than the above-mentioned "bright condition”.
  • the preprocessing unit 51 performs processing to cut out a predetermined frequency range from the corrected reflection spectrum.
  • the first determination unit 52 determines whether the spectrum detected by the mid-infrared camera 4 is that of the waste plastic pieces S1 and S2 or the conveyor 2 transport path 3. The first determination unit 52 makes a determination using the learned One Class SVM (Support Vector Machine).
  • One Class SVM Small Vector Machine
  • One Class SVM is a kind of SVM which is a kind of classification algorithm of machine learning.
  • SVM the identification boundary is set so as to maximize the Euclidean distance of each class based on the support vector of each class (the position closest to the other classes in the training data). If the features are non-linear, the kernel is used to map the data into the feature space. With proper kernel selection, it is possible to draw identification boundaries even in complex data arrangements.
  • One Class SVM maps data to a feature space in a high-dimensional space using a technique called a kernel trick for one type of training data. At this time, since the training data is mapped so as to be arranged far from the origin, data that is not similar to the original training data gathers near the origin. Using this property, normal data (conveyor 2) and abnormal data (objects (waste plastic pieces S1, S2)) are distinguished.
  • One Class SVM which has excellent pattern identification ability, it is possible to accurately determine whether the reflection spectrum is reflected by the waste plastic pieces S1 and S2 or by the transport path 3 of the conveyor 2. Can be identified.
  • a classification method for supervised learning of machine learning other than One Class SVM may be applied to the first determination unit 52.
  • the second determination unit 53 extracts feature data Score1 and Score2 (feature amounts) from the spectrum determined to be waste plastic pieces by the first determination unit 52.
  • the second determination unit 53 makes a determination using the learned PLS (Partial Last Squares).
  • 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 and the objective variable among the principal components calculated from the explanatory variables.
  • the principal component is calculated so that the covariance with the objective variable is large.
  • two types of feature data Score1 and Score2 are calculated using PLS based on the explanatory variables of the reflection spectrum determined to be reflected by the waste plastic pieces S1 and S2.
  • PLS for the second determination unit 53, it is possible to reduce the number of features from the multidimensional explanatory variables of the reflection spectrum to a small number of features, so that appropriate feature data Score1 and Score2 that are easier to distinguish can be extracted. ..
  • a machine learning multivariate analysis method other than PLS may be applied to the second determination unit 53.
  • the third determination unit 54 determines the materials of the waste plastic pieces S1 and S2 corresponding to this spectrum based on the two feature quantities Score1 and Score2 of the reflection spectrum extracted by the second determination unit 53.
  • the third determination unit 54 makes a determination using the learned decision tree.
  • Decision trees are a type of classification algorithm for supervised learning.
  • a decision tree is a tree-structured representation of the rules for classifying objective variables and is often used in classification problems.
  • the materials of the waste plastic pieces S1 and S2 can be accurately discriminated from the two feature quantities Score1 and Score2 of the reflection spectrum.
  • a classification method for supervised learning of machine learning other than the decision tree may be applied to the third determination unit 54.
  • the discrimination device 5 is physically configured as a computer system including a CPU (Central Processing Unit), a main storage device such as a RAM (Random Access Memory) and a ROM (Read Only Memory), a communication module, and an auxiliary storage device. can do.
  • a CPU Central Processing Unit
  • main storage device such as a RAM (Random Access Memory) and a ROM (Read Only Memory)
  • ROM Read Only Memory
  • Each function of the discrimination device 5 shown in FIG. 4 operates various hardware under the control of the CPU by loading predetermined computer software (material determination program) into the CPU, RAM, or the like, and also in the RAM. It is realized by reading and writing data. That is, by executing the material determination program according to the present embodiment on the computer, the determination device 5 can be used as the preprocessing unit 51, the first determination unit 52, the second determination unit 53, and the third determination unit 54 in FIG. Function.
  • predetermined computer software material determination program
  • the material determination program of this embodiment is stored in, for example, a storage device provided in a computer.
  • a part or all of the material determination program may be transmitted via a transmission medium such as a communication line, and may be received and recorded (including installation) by a communication module or the like provided in the computer.
  • the material determination program has a configuration in which a part or all of the material determination program is recorded (including installation) in the computer from a state in which a part or all of the program is stored in a portable storage medium such as a CD-ROM, a DVD-ROM, or a flash memory. May be.
  • the discrimination device 5 may be a circuit composed of an analog circuit, a digital circuit, or an analog / digital mixed circuit. Further, a control circuit for controlling each function of the discriminating device 5 may be provided. The implementation of each circuit may be by ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), or the like.
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • 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, and the like, and loads predetermined computer software into the CPU, RAM, and the like. The function is realized by making it.
  • FIG. 5 is a flowchart of the material discrimination process of the waste plastic according to the embodiment. Each process of the flowchart shown in FIG. 5 is executed by the discriminating device 5.
  • step S01 the preprocessing unit 51 acquires the spectrum S org (n, w) taken by the mid-infrared camera 4.
  • n is the number of sensors (the number of spectrum detection regions divided in the width direction of the conveyor 2 by the mid-infrared camera 4), and when the number of sensors is 318, 0 to 317 corresponding to each detection region.
  • An integer is used.
  • w is the wavelength of the spectrum, and in the present embodiment, a total of 131 wavelengths are set between 2700 (nm) and 5300 (nm) in increments of 20 (nm), and an integer of 0 to 130 corresponding to each wavelength is set. Is used. That is, S org (n, w) represents a numerical value of the intensity of the spectrum of the wavelength w in the nth spectrum detection region along the width direction of the conveyor 2.
  • step S02 the preprocessing unit 51 corrects the spectrum S org (n, w) acquired in step S01, and calculates the corrected spectrum S cor (n, w). Due to this correction, the spectrum due to the influence of changes in the concentration 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 aged deterioration of the illumination 10 and the mid-infrared camera 4, the position on the conveyor 2, and the like. It can absorb the difference in strength characteristics.
  • the corrected spectrum S cor (n, w) can be calculated by, for example, the following equation (1).
  • W ref (n, w) is the first correction spectrum measured under the condition that the reflected light is bright.
  • D ref (n, w) is a second correction spectrum measured under a condition in which the reflected light is darker than the above-mentioned bright condition.
  • FIG. 6 is a diagram showing an extraction method of spectra W ref (n, w) and D ref (n, w) for correction.
  • a calibration plate 11 for acquiring a correction spectrum is installed in the imaging region of the mid-infrared camera 4 on the transport path 3 of the conveyor 2, and the spectrum of the reflected light by the mid-infrared camera 4 is provided.
  • the spectra W ref (n, w) and D ref (n, w) for correction can be obtained.
  • the calibration plate 11 is arranged when acquiring the correction spectra W ref (n, w) and D ref (n, w), as shown by the dotted arrows in FIG. 6, for example, the transport path of the conveyor 2. It is preferable that the camera is movably installed between the position of the imaging region of the mid-infrared camera 4 and the standby position outside the imaging region of the mid-infrared camera 4 and the irradiation range of the illumination 10. In other words, the calibration plate 11 can be fixed at a predetermined position in the field of view of the mid-infrared camera 4 and a predetermined position outside the field of view, and is preferably movable between both predetermined positions.
  • the calibration plate 11 is preferably processed so that the surface roughness of the main surface that receives the light from the illumination 10 is large and rough. As a result, it is possible to suppress the occurrence of halation of the reflected light.
  • the conveyor 2 may be stopped when the correction spectrum is acquired.
  • the infrared rays of the illumination 10 irradiate the infrared rays on the conveyor 2 with the conveyor 2.
  • the temperature of the part rises, and there is a risk of burning or ignition. Therefore, when the calibration plate 11 is not fixed in the field of view of the mid-infrared camera 4, it is preferable to provide an interlock so as not to irradiate infrared rays from the illumination 10.
  • the illumination 10 has a lamp 10A (sheath heater, carbon lamp, cantal lamp, etc.) which is an infrared light source, and a reflector 10B which collects the heat of 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 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 conveyor 2 with respect to the lamp 10A, and is formed to be curved along the circumferential direction around the axis of the lamp 10A, whereby the lamp 10A to the conveyor 2 Can collect infrared rays radiated on the opposite side, reflect them on the conveyor 2 side, and send them.
  • the reflector 10B is made of, for example, a member plated with aluminum, stainless steel, or aluminum.
  • FIG. 7 is a diagram showing an example of processing for cutting out a characteristic wavelength region from the reflected wave spectrum.
  • the horizontal axis of FIG. 7 indicates the wavelength (nm) of the spectrum, and the vertical axis indicates the intensity of the spectrum at each wavelength.
  • FIG. 7 shows an example of the spectrum of each material of ABS, HIPS, PP, and PE. Then, in the example of FIG. 7, spectra in the wavelength regions of 3250 to 3750 (nm) and 4400 to 4600 (nm) are cut out. In the example of FIG. 7, the range of the wavelength region to be cut out is shown by a shaded pattern.
  • each spectrum is a belt of the conveyor 2 using the spectrum corrected in step S02 by the first determination unit 52 and the characteristic wavelength region cut out in step S03. It is determined whether it is (conveyor path 3) or an object (waste plastic) on the conveyor path 3.
  • the first determination unit 52 makes a determination using the learned One Class SVM.
  • the second determination unit 53 extracts two types of feature data Score1 and Score2 from the spectrum determined to be an object (waste plastic) in step S4 using the learned PLS.
  • FIG. 8 is a diagram showing an example of extracting feature data. The horizontal axis of FIG. 8 shows the first feature data (Score1), and the vertical axis shows the second feature data (Score2).
  • FIG. 8 shows an extraction example of four types of materials, ABS, HIPS, PP, and PE illustrated in FIG. 7. As shown in FIG. 8, it can be seen that the area plotted for each material can be divided on the two-dimensional space by the two feature data Score1 and Score2. The number of feature data may be other than two.
  • FIG. 9 is a diagram showing an example of material discrimination using a decision tree.
  • the decision tree has two layers of conditional branching as shown in FIG. 9 in order to finally identify four types of materials (PE, PP, ABS, HIPS).
  • the set of feature data Score1 and Score2 is divided into two groups G1 and G2 by using the conditional branching function f1 (Score1 and Score2).
  • One group G1 is further divided into two groups G11 and G12 in the second layer by using the conditional branching function f2 (Score1 and Score2).
  • the other group G2 is further divided into two groups G21 and G22 in the second layer by using the conditional branching function f3 (Score1 and Score2).
  • the set of feature data Score1 and Score2 is 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.
  • the discrimination device 5 of the waste plastic material determination device 1 is a spectrum of the reflected light of the light detected by the mid-infrared camera 4 and irradiated to the transport path 3 of the conveyor 2 by the illumination 10.
  • feature data There are two types of feature data, Score1 and Score2, from the spectrum determined to be the waste plastic piece S by the first determination unit 52, which determines whether the waste plastic piece S or the transport path 3 is used.
  • the second determination unit 53 is provided, and the third determination unit 54 that determines the materials S1 and S2 of the waste plastic piece S based on the feature data Scope1 and Spectra2 extracted by the second determination unit 53 is provided.
  • the input information of the reflection spectrum is narrowed down to the spectrum of the black waste plastic piece S by the object discrimination of the first judgment unit 52, and the dimension from the spectrum information to the feature data by the feature amount extraction of the second judgment unit 53.
  • the output information of the material of the waste plastic can be obtained through the three-step determination process of the compression and the classification process of the third determination unit 54 and the narrowing down of the data. Therefore, the waste plastic material determination device 1 of the present embodiment can determine the material of the waste plastic in consideration of various conditions, and can perform detailed determination in multiple stages. The accuracy of determining the material of plastic can be improved.
  • the discrimination device 5 of the waste plastic material determination device 1 is the first measurement of the reflection spectrum S org (n, w) detected by the mid-infrared camera 4 under the condition that the reflected light is bright.
  • a preprocessing unit 51 for correction using a correction spectrum W ref (n, w) and a second correction spectrum D ref (n, w) measured under a condition relatively darker than this bright condition is provided. ..
  • the reflection spectrum S org (n, w) is corrected by using, for example, the equation (1) and the correction spectra W ref (n, w) and D ref (n, w). Differences in spectral intensity characteristics due to the effects of the temperatures of the black waste plastic pieces S1 and S2 to be measured, the aged deterioration of the mid-infrared camera 4, the position on the conveyor 2, and the like can be suppressed. Therefore, the material of the waste plastic is made of waste plastic by learning and determining the first determination unit 52, the second determination unit 53, and the third determination unit 54 using the corrected spectrum S cor (n, w). Judgment accuracy can be further improved.
  • the preprocessing unit 51 further performs processing to cut out a predetermined frequency range from the corrected spectrum S cor (n, w), and outputs the processed spectrum to the first determination unit 52.
  • the preprocessing unit 51 performs two processes, that is, a correction process for the reflection spectrum S org (n, w) and a process for cutting out a predetermined frequency range, but only one of the two processes is performed. It may be configured to be performed.
  • waste plastic to be material-determined is the black waste plastic S
  • waste plastics of other colors such as red and blue
  • waste plastics having different colors may be mixed and used.
  • FIG. 10 is a plan view showing a first material selection method by the material determination device 1 of the present embodiment.
  • FIG. 10 shows a simplified view corresponding to the plan view of the material determination device 1 shown in FIG. From FIG. 10 onward, as an example of the sorting method, an example in which a plastic mix in which five kinds of materials (1), (2), (3), (4), and (5) are mixed is targeted for sorting will be described.
  • the configuration in which the conveyor 2 and the collecting device 12 are not divided in the width direction (y direction) of the conveyor 2 is formed as a system of transport paths is illustrated.
  • the collecting device 12 waste plastic is sorted by the injection and stop of the injection nozzle 7 with the partition plate 9 shown in FIG. 2 or the like as a boundary, so that the selection target is roughly classified into two types. Therefore, in order to sort the plastic mix in which the five types of materials to be sorted are mixed for each single material, one of the collecting devices 12 is the collecting device 12-1 (for example, air is injected from the injection nozzle 7). It is necessary to repeat the process of separating each type of waste plastic into a device for collecting the waste plastic. That is, as shown in FIG.
  • the remaining plastic mix collected in the other collecting device 12-2 is a mixture of the other four types of materials (2) to (5).
  • the remaining plastic mix in which the four types are mixed is put into the material determination device 1 again, and any one of (2) to (5) is classified. By repeating this procedure four times, it is possible to separate each of the five types of materials (1) to (5).
  • FIG. 11 is a plan view showing a second material selection method by the material determination device 1A of the present embodiment.
  • the conveyor 2 transport path 3 is divided into two systems, a first system and a second system, in the width direction. More specifically, each of the input port (vibration feeder 8), the conveyor 2, and the collecting device 12 is divided into two in the width direction.
  • the input port 8 and the conveyor 2 do not have two components, but a single element is provided with a partition or the like so that the components do not mix with each other.
  • the transport path 3 of the conveyor 2 can be divided into two systems by providing a partition wall along the transport direction at a position substantially at the center in the width direction.
  • the first system is represented by the subscript A
  • the second system is represented by the subscript B.
  • the elements corresponding to the collecting device 12-1 in FIG. 10 are referred to as “collecting device A1” and “collecting device B1”
  • the elements corresponding to the collecting device 12-2 in FIG. 10 are referred to as “collecting device A2” and “collecting device A2”. Notated as “collector B2”.
  • waste plastic pieces of the same material are collected in the first system and the second system.
  • a plastic mix in which five types of materials (1) to (5) are mixed is supplied to the inlets A and B of the first and second systems, respectively, and the material can be determined in each system.
  • waste plastic pieces of the same material (1) are collected by the collecting devices A1 and B1 respectively.
  • the collecting devices A2 and B2 collect waste plastic in which the remaining materials (2) to (5) are mixed.
  • FIG. 12 is a plan view showing a third material selection method by the material determination device 1B of the present embodiment.
  • waste plastic pieces of the first material are collected and the remaining waste plastic pieces are supplied to the second system, and in the second system, the remaining waste plastic pieces. Collect the waste plastic pieces of the second material from the inside.
  • a plurality of types of mixed materials can be classified into three types: a first material, a second material, and other materials.
  • a plastic mix in which five kinds of materials (1) to (5) are mixed is supplied to the input port A of the first system, and the material is determined by the conveyor A of the first system.
  • the waste plastic piece of the material (1) is collected by the collecting device A1. Further, the collecting device A2 collects waste plastic in which the remaining materials (2) to (5) are mixed.
  • the waste plastic in which the remaining materials (2) to (5) collected by the collection device A2 are mixed is conveyed to the input port B of the second system by the transfer device 13 and supplied to the input port B. NS.
  • the material is determined by the conveyor B of the second system, and the waste plastic piece of the material (2) is collected by the collecting device B1.
  • waste plastic in which the remaining materials (3) to (5) are mixed is collected.
  • FIG. 13 is a plan view showing a fourth material selection method by the material determination device 1C of the present embodiment.
  • waste plastic pieces of the first material and a trace amount of other materials are collected, and the collected waste plastic pieces are supplied to the second system. , Collect the waste plastic pieces of the first material from the waste plastic pieces of the first material and a trace amount of other materials.
  • a plastic piece made of a predetermined type of material can be sorted with high purity.
  • a plastic mix in which five kinds of materials (1) to (5) are mixed is supplied to the input port A of the first system, and the material is determined by the conveyor A of the first system.
  • Material (1) and a small amount of waste plastic pieces (2) to (5) are collected by the collecting device A1. Further, the collecting device A2 collects waste plastic in which the remaining materials (2) to (5) and a trace amount (1) are mixed.
  • the waste plastic in which the material (1) collected by the collecting device A1 and a small amount of (2) to (5) are mixed is transported to the input port B of the second system by the transport device 13, and is transported to the input port B. It is supplied to B.
  • the material is determined by the conveyor B of the second system, the material (1) is sorted again by the collecting device B1, and the waste plastic pieces of the material (1) are collected.
  • the material (1) collected by the collecting device B1 has a higher purity than the material collected by the collecting device A1.
  • waste plastic in which the remaining materials (1) to (5) are mixed is collected.
  • FIG. 14 is a plan view showing a fifth material selection method by the material determination device 1D of the present embodiment.
  • the first system waste plastic pieces of the first material and a trace amount of other materials are excluded, and the remaining excluded waste plastic pieces are supplied to the second system, and the second system is used.
  • the first material and a trace amount of waste plastic pieces of other materials are further excluded from the other waste plastic pieces, and the waste plastic pieces not containing the first material are collected.
  • a plastic piece of a predetermined type of material can be more reliably selected from the mixed materials.
  • a plastic mix in which five kinds of materials (1) to (5) are mixed is supplied to the input port A of the first system, and the material is determined by the conveyor A of the first system.
  • Material (1) and a small amount of waste plastic pieces (2) to (5) are collected by the collecting device A1. Further, the collecting device A2 collects waste plastic in which the remaining materials (2) to (5) and a small amount (1) are mixed.
  • the waste plastic in which the materials (2) to (5) collected by the collecting device A2 and a small amount (1) are mixed is conveyed to the input port B of the second system by the transfer device 13, and is conveyed to the input port B. It is supplied to B.
  • the material is determined by the conveyor B of the second system, the material (1) is sorted again by the collecting device B1, and waste plastic pieces in which the material (1) and a trace amount of the materials (2) to (5) are mixed are produced. Collected.
  • waste plastic in which the remaining materials (2) to (5) and a trace amount (1) are mixed is collected.
  • FIG. 15 is a diagram showing an example of an operation screen of the material determination device 1.
  • the operation screen shown in FIG. 15 is displayed on, for example, a display device installed in the main body of the material determination device 1.
  • the material names of the plastics to be sorted are listed on the operation screen, and the first system (“primary” in FIG. 15 and the second system (“secondary” in FIG. 15”) are listed. ),
  • the material to be jetted and sorted can be individually selected.
  • the display device on which the operation screen is displayed is, for example, a touch panel, and by an operation such as pressing the "OFF" display in the "spray selection" column.
  • Waste plastic material determination device 1 Conveyor 3 Conveyor path 4 Mid-infrared camera (reflection spectrum detector) 5 Discrimination device 51 Pretreatment unit 52 1st judgment unit 53 2nd judgment unit 54 3rd judgment unit 12, 12-1, 12-2, A1, A2, B1, B2 Collection device S1, S2 Black waste plastic piece

Landscapes

  • Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Analytical Chemistry (AREA)
  • Polymers & Plastics (AREA)
  • Sustainable Development (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Medicinal Chemistry (AREA)
  • Organic Chemistry (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Engineering & Computer Science (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)
  • Sorting Of Articles (AREA)
  • Separation, Recovery Or Treatment Of Waste Materials Containing Plastics (AREA)

Abstract

A waste plastic material determination device comprising: a first determination unit that determines whether a reflected light spectrum of light radiated by illumination onto the transport path of a conveyor as detected by a mid-infrared camera indicates a waste plastic fragment or the transport path; a second determination unit that extracts two types of feature data from a spectrum determined by the first determination unit as indicating a waste plastic fragment; and a third determination unit that identifies the material of the waste plastic fragment on the basis of the feature data extracted by the second determination unit.

Description

廃プラスチックの材質判定装置、材質判定方法、及び材質判定プログラムWaste plastic material judgment device, material judgment method, and material judgment program
　本開示は、廃プラスチックの材質判定装置、材質判定方法、及び材質判定プログラムに関する。 This disclosure relates to a waste plastic material determination device, a material determination method, and a material determination program.
　廃プラスチックの再処理においてマテリアルリサイクルのためには、選別後の製品への非対象物混入が少なく純度が高いことが求められる。また、素材に高価なものが含まれる場合には、高価な素材を取りこぼしなく選別できることが求められる。また、従来は分別できないためサーマルリサイクルをせざるを得なかった黒色プラスチックを、マテリアルリサイクルするために材質判別、選別を効率良く行うことが求められている。 In the reprocessing of waste plastics, in order to recycle materials, it is required that the products after sorting are less mixed with non-objects and have high purity. Further, when the material contains an expensive material, it is required to be able to sort the expensive material without missing it. In addition, it is required to efficiently discriminate and sort black plastics, which have had to be thermally recycled because they cannot be separated in the past, in order to recycle the materials.
　特許文献１には、選別対象物に赤外光を照射して選別対象物からの反射光を受光し、反射光に基づくスペクトルを用いてパターンマッチングの手法によって選別対象物の樹脂種を判定することが記載されている。 In Patent Document 1, the object to be sorted is irradiated with infrared light to receive the reflected light from the object to be sorted, and the resin type of the object to be sorted is determined by a pattern matching method using a spectrum based on the reflected light. It is stated that.
特開２０１８－１００９０３号公報JP-A-2018-100903
　しかしながら、特許文献１等に記載の従来手法では、材質の判定精度に改善の余地がある。 However, in the conventional method described in Patent Document 1 and the like, there is room for improvement in the determination accuracy of the material.
　本開示は、廃プラスチックの材質の判定精度を向上できる材質判定装置、材質判定方法、及び材質判定プログラムを提供することを目的とする。 An object of the present disclosure is to provide a material determination device, a material determination method, and a material determination program that can improve the determination accuracy of the material of waste plastic.
　本発明の実施形態の一観点に係る廃プラスチックの材質判定装置は、搬送路上で搬送される廃プラスチック片に光を照射する照射部と、前記照射部により照射された光の反射光を受光して前記反射光のスペクトルを検出する反射スペクトル検出部と、前記反射スペクトル検出部により検出された前記スペクトルが前記廃プラスチック片及び前記搬送路のどちらかのものかを判定する第１判定部と、前記第１判定部により前記廃プラスチック片と判定されたスペクトルから特徴量を抽出する第２判定部と、前記第２判定部により抽出された前記特徴量に基づき前記廃プラスチック片の材質を判別する第３判定部と、を備える。 The waste plastic material determination device according to one aspect of the embodiment of the present invention receives the irradiation unit that irradiates the waste plastic piece conveyed on the transport path with light and the reflected light of the light emitted by the irradiation unit. A reflection spectrum detection unit that detects the spectrum of the reflected light, and a first determination unit that determines whether the spectrum detected by the reflection spectrum detection unit is either the waste plastic piece or the transport path. The material of the waste plastic piece is discriminated based on the second determination unit that extracts the feature amount from the spectrum determined by the first determination unit as the waste plastic piece and the feature amount extracted by the second determination unit. It includes a third determination unit.
　本開示によれば、廃プラスチックの材質の判定精度を向上できる材質判定装置、材質判定方法、及び材質判定プログラムを提供することができる。 According to the present disclosure, it is possible to provide a material determination device, a material determination method, and a material determination program that can improve the determination accuracy of the material of waste plastic.
実施形態に係る廃プラスチックの材質判定装置の概略構成を示す斜視図A perspective view showing a schematic configuration of a waste plastic material determination device according to an embodiment. 図１に示す廃プラスチックの材質判定装置の側面図Side view of the waste plastic material determination device shown in FIG. 図１に示す廃プラスチックの材質判定装置の平面図Top view of the waste plastic material determination device shown in FIG. 判別装置の機能ブロック図Functional block diagram of the discriminator 実施形態に係る廃ブラスチックの材質判別処理のフローチャートFlowchart of material discrimination process of waste plastic according to the embodiment 補正用のスペクトルの抽出手法を示す図The figure which shows the extraction method of the spectrum for correction 反射波スペクトルから特徴のある波長領域を切り出す処理の一例を示す図The figure which shows an example of the process which cuts out a characteristic wavelength region from a reflected wave spectrum. 特徴データの抽出例を示す図The figure which shows the extraction example of the feature data 決定木を用いた材質判別の例を示す図The figure which shows the example of the material discrimination using a decision tree 本実施形態の材質判定装置による第１の材質選別手法を示す平面図Top view showing the first material selection method by the material determination apparatus of this embodiment 本実施形態の材質判定装置による第２の材質選別手法を示す平面図Top view showing the second material selection method by the material determination apparatus of this embodiment. 本実施形態の材質判定装置による第３の材質選別手法を示す平面図A plan view showing a third material selection method by the material determination device of the present embodiment. 本実施形態の材質判定装置による第４の材質選別手法を示す平面図A plan view showing a fourth material selection method by the material determination device of the present embodiment. 本実施形態の材質判定装置による第５の材質選別手法を示す平面図A plan view showing a fifth material selection method by the material determination device of the present embodiment. 材質判定装置の操作画面の一例を示す図The figure which shows an example of the operation screen of the material judgment apparatus
　以下、添付図面を参照しながら実施形態について説明する。説明の理解を容易にするため、各図面において同一の構成要素に対しては可能な限り同一の符号を付して、重複する説明は省略する。 Hereinafter, embodiments will be described with reference to the attached drawings. In order to facilitate understanding of the description, the same components are designated by the same reference numerals as much as possible in each drawing, and duplicate description is omitted.
　なお、以下の説明において、ｘ方向、ｙ方向、ｚ方向は互いに垂直な方向である。ｘ方向及びｙ方向は水平方向であり、ｚ方向は鉛直方向である。ｘ方向はコンベア２の搬送路３の搬送方向である。ｙ方向は、コンベア２の搬送路３の幅方向である。また、以下では説明の便宜上、ｚ正方向側を上側、ｚ負方向側を下側とも表現する場合がある。 In the following description, the x direction, the y direction, and the z direction are perpendicular to each other. The x-direction and the y-direction are horizontal directions, and the z-direction is a vertical direction. The x direction is the transport direction of the transport path 3 of the conveyor 2. The y direction is the width direction of the transport path 3 of the conveyor 2. Further, in the following, for convenience of explanation, the z positive direction side may be expressed as the upper side and the z negative direction side may be expressed as the lower side.
　図１～図３を参照して、実施形態に係る廃プラスチックの材質判定装置１の概略構成を説明する。図１は、実施形態に係る廃プラスチックの材質判定装置１の概略構成を示す斜視図である。図２は、図１に示す廃プラスチックの材質判定装置１の側面図である。図３は、図１に示す廃プラスチックの材質判定装置１の平面図である。ここでは、材質判定対象の廃プラスチックが黒色廃プラスチックの場合であり、かつ、二種類の材質Ｓ１、Ｓ２（図１～図３では四角形と三角形のマークで示す）を混合する構成を例示して説明する。以下では、二種類の材質Ｓ１、Ｓ２の黒色廃プラスチック片を纏めて符号Ｓで表す場合がある。 The schematic configuration of the waste plastic material determination device 1 according to the embodiment will be described with reference to FIGS. 1 to 3. FIG. 1 is a perspective view showing a schematic configuration of a waste plastic material determination device 1 according to an embodiment. FIG. 2 is a side view of the waste plastic material determination device 1 shown in FIG. FIG. 3 is a plan view of the waste plastic material determination device 1 shown in FIG. Here, a configuration is illustrated in which the waste plastic to be determined as a material is a black waste plastic, and two types of materials S1 and S2 (indicated by quadrangular and triangular marks in FIGS. 1 to 3) are mixed. explain. In the following, the black waste plastic pieces of the two types of materials S1 and S2 may be collectively represented by the reference numeral S.
　この黒色廃プラスチックの材質判定装置１は、黒色廃プラスチック片Ｓ１、Ｓ２を順次供給する供給部の一例としての振動フィーダー８と、振動フィーダー８により供給された黒色廃プラスチック片Ｓ１、Ｓ２を搬送する搬送部の一例としてのコンベア２とを主要部として備えている。振動フィーダー８には、例えば投入用ホッパなどを介して、破砕された黒色廃プラスチック片Ｓ１、Ｓ２が供給される。振動フィーダー８は、黒色廃プラスチック片Ｓ１、Ｓ２が載置される載置面が振動することによって、黒色廃プラスチック片Ｓ１、Ｓ２同士の重畳を防止しながらコンベア２に供給する。コンベア２は、その上面に搬送路３を有し、振動フィーダー８から遠ざかる向きに搬送路３上の黒色廃プラスチック片Ｓ１、Ｓ２を搬送する。 The black waste plastic material determination device 1 conveys a vibration feeder 8 as an example of a supply unit that sequentially supplies black waste plastic pieces S1 and S2, and black waste plastic pieces S1 and S2 supplied by the vibration feeder 8. A conveyor 2 as an example of a transport unit is provided as a main unit. The crushed black waste plastic pieces S1 and S2 are supplied to the vibration feeder 8 via, for example, a charging hopper. The vibration feeder 8 supplies the black waste plastic pieces S1 and S2 to the conveyor 2 while preventing the black waste plastic pieces S1 and S2 from being overlapped with each other by vibrating the mounting surface on which the black waste plastic pieces S1 and S2 are placed. The conveyor 2 has a transport path 3 on its upper surface, and transports the black waste plastic pieces S1 and S2 on the transport path 3 in a direction away from the vibration feeder 8.
　また、材質判定装置１は、黒色廃プラスチック片Ｓ１、Ｓ２に赤外線を照射する照射部の一例としての照明１０と、黒色廃プラスチック片Ｓ１、Ｓ２からの反射スペクトルを検出する反射スペクトル検出部の一例としての中赤外線カメラ４と、中赤外線カメラ４で検出した反射スペクトルに基づき黒色廃プラスチック片Ｓ１、Ｓ２の材質を同定する判別装置５と、を主要部として備えている。照明１０は、例えばハロゲンタングステンランプ等の赤外線光源であるランプ１０Ａ（図６参照）を有し、ランプ１０Ａから黒色廃プラスチック片Ｓ１、Ｓ２に向かって赤外線を照射する。また、照明１０は、中赤外線カメラ４に黒色廃プラスチック片Ｓ１、Ｓ２からの反射光が入光するように設置され、中赤外線カメラ４に対してコンベア２の流れ方向の上部両側（又は上部片側）に設置されている。 Further, the material determination device 1 is an example of an illumination 10 as an example of an irradiation unit that irradiates the black waste plastic pieces S1 and S2 with infrared rays, and an example of a reflection spectrum detection unit that detects the reflection spectrum from the black waste plastic pieces S1 and S2. The main part is a mid-infrared camera 4 as a main part, and a discriminating device 5 for identifying the materials of the black waste plastic pieces S1 and S2 based on the reflection spectrum detected by the mid-infrared camera 4. The illumination 10 has a lamp 10A (see FIG. 6) which is an infrared light source such as a halogen tungsten lamp, and irradiates infrared rays from the lamp 10A toward the black waste plastic pieces S1 and S2. Further, the illumination 10 is installed on the mid-infrared camera 4 so that the reflected light from the black waste plastic pieces S1 and S2 enters the mid-infrared camera 4, and the lighting 10 is installed on both upper sides (or one side of the upper side) of the conveyor 2 in the flow direction with respect to the mid-infrared camera 4. ) Is installed.
　中赤外線カメラ４は、例えば図１に示すように１台でコンベア２の幅方向の全域に亘って計測可能であり、幅方向に沿って複数個（例えば３１８個）の領域に区分して黒色廃プラスチック片Ｓ１、Ｓ２からの近赤外線の反射光を受光し、各領域ごとに反射光のスペクトルを計測できる。中赤外線カメラ４は、例えば、中赤外線の波長領域３μｍ以上の分光器付カメラで構成されている。中赤外線カメラ４は、例えば２３０Ｈｚのスキャン周波数で計測を行い、１回のスキャンごとに３１８個のスペクトルデータを判別装置５に送信する。判別装置５は、中赤外線カメラ４から受信した３１８個のスペクトルデータに基づき、３１８個の各領域の材質判定結果を後述の噴射制御部６に出力する。 As shown in FIG. 1, for example, one mid-infrared camera 4 can measure the entire width direction of the conveyor 2, and is divided into a plurality of (for example, 318) regions along the width direction and is black. The reflected light of near infrared rays from the waste plastic pieces S1 and S2 can be received, and the spectrum of the reflected light can be measured for each region. The mid-infrared camera 4 is composed of, for example, a camera with a spectroscope having a wavelength region of mid-infrared of 3 μm or more. The mid-infrared camera 4 measures at a scan frequency of, for example, 230 Hz, and transmits 318 spectral data to the discriminating device 5 for each scan. The discrimination device 5 outputs the material determination results of the 318 regions to the injection control unit 6, which will be described later, based on the 318 spectral data received from the mid-infrared camera 4.
　さらに、材質判定装置１は、コンベア２の搬送方向の下流側にて、搬送方向と交差する方向に横又は斜めからエアーを噴射する噴射ノズル７が設けられている。噴射ノズル７は、コンベア２の幅方向に複数個（例えば３１８個）が並設されており、噴射制御部６によって個々のノズルの動作が制御される。噴射制御部６は、判別装置５から受信した材質判定結果に応じて、噴射ノズル７からエアーを噴射させ、または噴射させないことにより、例えば仕切り板９により区分される複数の領域（例えば回収用ホッパなど）に黒色廃プラスチック片Ｓ１、Ｓ２を仕分けて落下させて、所望の材質の廃プラスチックを収集する。つまり、本実施形態では、噴射制御部６と、噴射ノズル７と、仕切り板９とが、判別装置５による材質判定結果に基づき、コンベア２の搬送路３を流れる廃プラスチック片から所望の材質のものを収集する収集装置１２として機能する。 Further, the material determination device 1 is provided with an injection nozzle 7 that injects air laterally or diagonally in a direction intersecting the transport direction on the downstream side of the conveyor 2 in the transport direction. A plurality of injection nozzles 7 (for example, 318) are arranged side by side in the width direction of the conveyor 2, and the operation of each nozzle is controlled by the injection control unit 6. The injection control unit 6 injects or does not inject air from the injection nozzle 7 according to the material determination result received from the determination device 5, so that, for example, a plurality of regions (for example, a recovery hopper) classified by the partition plate 9 are formed. Black waste plastic pieces S1 and S2 are sorted and dropped to collect waste plastic of a desired material. That is, in the present embodiment, the injection control unit 6, the injection nozzle 7, and the partition plate 9 are made of a desired material from the waste plastic piece flowing through the transport path 3 of the conveyor 2 based on the material determination result by the discrimination device 5. It functions as a collecting device 12 for collecting things.
　材質判定装置１の動作について説明する。例えば投入用ホッパなどを介して、破砕された黒色廃プラスチック片Ｓ１、Ｓ２が振動フィーダー８に供給されると、振動フィーダー８は、供給された黒色廃プラスチック片Ｓ１、Ｓ２に振動を与えながら重ならないようにして下流に搬送して、コンベア２に供給する。 The operation of the material determination device 1 will be described. For example, when the crushed black waste plastic pieces S1 and S2 are supplied to the vibration feeder 8 via a charging hopper or the like, the vibration feeder 8 gives weight to the supplied black waste plastic pieces S1 and S2 while applying vibration. It is conveyed downstream so as not to become a conveyor 2 and supplied to the conveyor 2.
　コンベア２の上面の搬送路３に供給された黒色廃プラスチック片Ｓ１、Ｓ２は、ｘ正方向側の搬送方向に搬送されながら、中赤外線カメラ４の撮像可能な位置にて、照明１０から赤外光が照射される。中赤外線カメラ４は、照明１０から発せられた赤外線の黒色廃プラスチック片Ｓ１、Ｓ２による反射光を受光し、受光結果（受光スペクトルのデータ）を判別装置５に出力する。 The black waste plastic pieces S1 and S2 supplied to the transport path 3 on the upper surface of the conveyor 2 are transported in the transport direction on the x positive direction side, and are infrared from the illumination 10 at a position where the mid-infrared camera 4 can take an image. Light is emitted. The mid-infrared camera 4 receives the light reflected by the black waste plastic pieces S1 and S2 of the infrared rays emitted from the illumination 10, and outputs the light receiving result (data of the light receiving spectrum) to the discriminating device 5.
　判別装置５は、中赤外線カメラ４から入力された受光結果に基づき、黒色廃プラスチック片Ｓ１、Ｓ２の材質を同定する。なお、判別装置５による材質判定手法の詳細は図４～図９を参照して後述する。判別装置５は、材質同定結果を噴射制御部６に出力する。 The discrimination device 5 identifies the materials of the black waste plastic pieces S1 and S2 based on the light receiving result input from the mid-infrared camera 4. The details of the material determination method by the determination device 5 will be described later with reference to FIGS. 4 to 9. The discrimination device 5 outputs the material identification result to the injection control unit 6.
　噴射制御部６は、複数配置されている噴射ノズル７のうち、材質に応じた噴射ノズル７を選択して、タイミングを計って制御信号を送信する。制御信号を受信した噴射ノズル７は、ノズル口を開口して、エアーを噴射する。判別装置５の判別結果により適切なタイミングで噴射ノズル７からエアーを噴射することにより、選別対象の材質とそうでないものとを分離して回収することができる。 The injection control unit 6 selects the injection nozzle 7 according to the material from the plurality of the injection nozzles 7 arranged, measures the timing, and transmits the control signal. The injection nozzle 7 that has received the control signal opens the nozzle opening and injects air. By injecting air from the injection nozzle 7 at an appropriate timing according to the discrimination result of the discrimination device 5, the material to be sorted and the material not to be sorted can be separated and collected.
　図２、図３の例では、コンベア２上の黒色廃プラスチック片Ｓ１は、制御信号を受信したエアー噴射ノズル７からエアーを受けて、材質毎に設けられた収集装置１２に吹き飛ばされ落下して回収される。また、コンベア２上の黒色廃プラスチック片Ｓ２は、噴射ノズル７からエアーを受けないので、黒色廃プラスチック片Ｓ１とは異なる収集装置１２に回収される。このように噴射ノズル７の噴射及び停止によって、複数の材質の黒色廃プラスチック片を材質ごとに仕分けて回収することができる。 In the examples of FIGS. 2 and 3, the black waste plastic piece S1 on the conveyor 2 receives air from the air injection nozzle 7 that has received the control signal, is blown off by the collecting device 12 provided for each material, and falls. Will be recovered. Further, since the black waste plastic piece S2 on the conveyor 2 does not receive air from the injection nozzle 7, it is collected by a collecting device 12 different from the black waste plastic piece S1. By injecting and stopping the injection nozzle 7 in this way, black waste plastic pieces made of a plurality of materials can be sorted and collected for each material.
　図４～図９を参照して、判別装置５による廃プラスチックの材質判別手法について説明する。図４は、判別装置５の機能ブロック図である。 A method for discriminating the material of waste plastic by the discriminating device 5 will be described with reference to FIGS. 4 to 9. FIG. 4 is a functional block diagram of the discrimination device 5.
　図４に示すように、判別装置５は、前処理部５１と、第１判定部５２と、第２判定部５３と、第３判定部５４とを有する。 As shown in FIG. 4, the discrimination device 5 includes a preprocessing unit 51, a first determination unit 52, a second determination unit 53, and a third determination unit 54.
　前処理部５１は、中赤外線カメラ４により検出された黒色廃プラスチック片Ｓ１、Ｓ２の反射スペクトルの補正や加工などの前処理を行う。前処理部５１は、例えば、反射光が明るい条件で計測したスペクトルと、暗い条件で計測したスペクトルとを用いて、検出された反射スペクトルを補正する。「暗い条件」とは、上記の「明るい条件」よりも相対的に暗い条件を意味する。また、前処理部５１は、補正された反射スペクトルから所定の周波数の範囲を切り出す加工を行う。 The pretreatment unit 51 performs pretreatment such as correction and processing of the reflection spectra of the black waste plastic pieces S1 and S2 detected by the mid-infrared camera 4. The preprocessing unit 51 corrects the detected reflection spectrum by using, for example, a spectrum measured under a bright condition and a spectrum measured under a dark condition. The "dark condition" means a condition that is relatively darker than the above-mentioned "bright condition". In addition, the preprocessing unit 51 performs processing to cut out a predetermined frequency range from the corrected reflection spectrum.
　第１判定部５２は、中赤外線カメラ４により検出されたスペクトルが廃プラスチック片Ｓ１，Ｓ２及びコンベア２の搬送路３のどちらのものかを判定する。第１判定部５２は、学習済みのＯｎｅ　Ｃｌａｓｓ　ＳＶＭ（Ｓｕｐｐｏｒｔ　Ｖｅｃｔｏｒ　Ｍａｃｈｉｎｅ）を用いて判定を行う。 The first determination unit 52 determines whether the spectrum detected by the mid-infrared camera 4 is that of the waste plastic pieces S1 and S2 or the conveyor 2 transport path 3. The first determination unit 52 makes a determination using the learned One Class SVM (Support Vector Machine).
　Ｏｎｅ　Ｃｌａｓｓ　ＳＶＭは、機械学習の分類アルゴリズムの一種であるＳＶＭの一種である。ＳＶＭでは、各クラスのサポートベクター(学習データの中で最も他のクラスと近い位置にある)を基準として、それらのユークリッド距離が最大になるように識別境界を設定する。また、特徴が非線形の場合には、カーネルを用いてデータを特徴空間に写像する。カーネルを適切に選択することで、複雑なデータ配置でも識別境界を引くことが可能となる。 One Class SVM is a kind of SVM which is a kind of classification algorithm of machine learning. In SVM, the identification boundary is set so as to maximize the Euclidean distance of each class based on the support vector of each class (the position closest to the other classes in the training data). If the features are non-linear, the kernel is used to map the data into the feature space. With proper kernel selection, it is possible to draw identification boundaries even in complex data arrangements.
　Ｏｎｅ　Ｃｌａｓｓ　ＳＶＭでは、１種類の学習データに対してカーネルトリックと呼ばれる手法を用いて、高次元空間の特徴空間へデータを写像する。このとき、学習データは原点から遠くに配置されるように写像されるため、元の学習データと類似していないデータは原点の近くに集まる。この性質を用いて正常データ（コンベア２）と異常データ（物体（廃プラスチック片Ｓ１，Ｓ２））の区別を行う。 One Class SVM maps data to a feature space in a high-dimensional space using a technique called a kernel trick for one type of training data. At this time, since the training data is mapped so as to be arranged far from the origin, data that is not similar to the original training data gathers near the origin. Using this property, normal data (conveyor 2) and abnormal data (objects (waste plastic pieces S1, S2)) are distinguished.
　第１判定部５２にパターン識別能力に優れるＯｎｅ　Ｃｌａｓｓ　ＳＶＭを用いることにより、反射スペクトルが廃プラスチック片Ｓ１，Ｓ２で反射されたものか、コンベア２の搬送路３で反射されたものかを高精度に識別できる。なお、第１判定部５２には、Ｏｎｅ　Ｃｌａｓｓ　ＳＶＭ以外の機械学習の教師有り学習の分類手法を適用してもよい。 By using One Class SVM, which has excellent pattern identification ability, for the first determination unit 52, it is possible to accurately determine whether the reflection spectrum is reflected by the waste plastic pieces S1 and S2 or by the transport path 3 of the conveyor 2. Can be identified. A classification method for supervised learning of machine learning other than One Class SVM may be applied to the first determination unit 52.
　第２判定部５３は、第１判定部５２により廃プラスチック片と判定されたスペクトルから特徴データＳｃｏｒｅ１、Ｓｃｏｒｅ２（特徴量）を抽出する。第２判定部５３は、学習済みのＰＬＳ（Ｐａｒｔｉａｌ　Ｌｅａｓｔ　Ｓｑｕａｒｅｓ：部分的最小二乗法）を用いて判定を行う。 The second determination unit 53 extracts feature data Score1 and Score2 (feature amounts) from the spectrum determined to be waste plastic pieces by the first determination unit 52. The second determination unit 53 makes a determination using the learned PLS (Partial Last Squares).
　ＰＬＳは、機械学習の教師あり学習の回帰アルゴリズムの一種であり、説明変数から計算された主成分のうち、少数の主成分のみと目的変数との間で回帰分析を行う。ＰＬＳでは、主成分は目的変数との共分散が大きくなるように計算される。本実施形態では、廃プラスチック片Ｓ１，Ｓ２で反射されたと判定された反射スペクトルの説明変数に基づき、ＰＬＳを用いて二種類の特徴データＳｃｏｒｅ１、Ｓｃｏｒｅ２を算出する。 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 and the objective variable among the principal components calculated from the explanatory variables. In PLS, the principal component is calculated so that the covariance with the objective variable is large. In the present embodiment, two types of feature data Score1 and Score2 are calculated using PLS based on the explanatory variables of the reflection spectrum determined to be reflected by the waste plastic pieces S1 and S2.
　第２判定部５３に、ＰＬＳを用いることにより、反射スペクトルの多次元の説明変数から、少数の特徴量に縮約することができるので、より区別しやすい適切な特徴データＳｃｏｒｅ１、Ｓｃｏｒｅ２を抽出できる。なお、第２判定部５３には、ＰＬＳ以外の機械学習の多変量解析手法を適用してもよい。 By using PLS for the second determination unit 53, it is possible to reduce the number of features from the multidimensional explanatory variables of the reflection spectrum to a small number of features, so that appropriate feature data Score1 and Score2 that are easier to distinguish can be extracted. .. A machine learning multivariate analysis method other than PLS may be applied to the second determination unit 53.
　第３判定部５４は、第２判定部５３により抽出された反射スペクトルの２つの特徴量Ｓｃｏｒｅ１、Ｓｃｏｒｅ２に基づき、このスペクトルに対応する廃プラスチック片Ｓ１、Ｓ２の材質を判別する。第３判定部５４は、学習済みの決定木を用いて判定を行う。決定木は、教師あり学習の分類アルゴリズムの一種である。決定木は、目的変数を分類するルールを木構造で表したものであり、分類問題で頻繁に利用される。 The third determination unit 54 determines the materials of the waste plastic pieces S1 and S2 corresponding to this spectrum based on the two feature quantities Score1 and Score2 of the reflection spectrum extracted by the second determination unit 53. The third determination unit 54 makes a determination using the learned decision tree. Decision trees are a type of classification algorithm for supervised learning. A decision tree is a tree-structured representation of the rules for classifying objective variables and is often used in classification problems.
　第３判定部５４に、決定木を用いることにより、反射スペクトルの２つの特徴量Ｓｃｏｒｅ１、Ｓｃｏｒｅ２から、廃プラスチック片Ｓ１、Ｓ２の材質を精度良く判別できる。なお、第３判定部５４には、決定木以外の機械学習の教師有り学習の分類手法を適用してもよい。 By using a decision tree in the third determination unit 54, the materials of the waste plastic pieces S1 and S2 can be accurately discriminated from the two feature quantities Score1 and Score2 of the reflection spectrum. A classification method for supervised learning of machine learning other than the decision tree may be applied to the third determination unit 54.
　判別装置５は、物理的には、ＣＰＵ（Ｃｅｎｔｒａｌ　Ｐｒｏｃｅｓｓｉｎｇ　Ｕｎｉｔ）、主記憶装置であるＲＡＭ（Ｒａｎｄｏｍ　Ａｃｃｅｓｓ　Ｍｅｍｏｒｙ）およびＲＯＭ（Ｒｅａｄ　Ｏｎｌｙ　Ｍｅｍｏｒｙ）、通信モジュール、補助記憶装置、などを含むコンピュータシステムとして構成することができる。図４に示した判別装置５の各機能は、ＣＰＵやＲＡＭなどに所定のコンピュータソフトウェア（材質判定プログラム）を読み込ませることにより、ＣＰＵの制御のもとで各種ハードウェアを動作させると共に、ＲＡＭにおけるデータの読み出し及び書き込みを行うことで実現される。すなわち、本実施形態に係る材質判定プログラムをコンピュータ上で実行させることで、判別装置５は、図４の前処理部５１、第１判定部５２、第２判定部５３、第３判定部５４として機能する。 The discrimination device 5 is physically configured as a computer system including a CPU (Central Processing Unit), a main storage device such as a RAM (Random Access Memory) and a ROM (Read Only Memory), a communication module, and an auxiliary storage device. can do. Each function of the discrimination device 5 shown in FIG. 4 operates various hardware under the control of the CPU by loading predetermined computer software (material determination program) into the CPU, RAM, or the like, and also in the RAM. It is realized by reading and writing data. That is, by executing the material determination program according to the present embodiment on the computer, the determination device 5 can be used as the preprocessing unit 51, the first determination unit 52, the second determination unit 53, and the third determination unit 54 in FIG. Function.
　本実施形態の材質判別プログラムは、例えばコンピュータが備える記憶装置内に格納される。なお、材質判別プログラムは、その一部又は全部が、通信回線等の伝送媒体を介して伝送され、コンピュータが備える通信モジュール等により受信されて記録（インストールを含む）される構成としてもよい。また、材質判別プログラムは、その一部又は全部が、ＣＤ－ＲＯＭ、ＤＶＤ－ＲＯＭ、フラッシュメモリなどの持ち運び可能な記憶媒体に格納された状態から、コンピュータ内に記録（インストールを含む）される構成としてもよい。 The material determination program of this embodiment is stored in, for example, a storage device provided in a computer. A part or all of the material determination program may be transmitted via a transmission medium such as a communication line, and may be received and recorded (including installation) by a communication module or the like provided in the computer. Further, the material determination program has a configuration in which a part or all of the material determination program is recorded (including installation) in the computer from a state in which a part or all of the program is stored in a portable storage medium such as a CD-ROM, a DVD-ROM, or a flash memory. May be.
　判別装置５は、アナログ回路、デジタル回路又はアナログ・デジタル混合回路で構成された回路であってもよい。また、判別装置５の各機能の制御を行う制御回路を備えていてもよい。各回路の実装は、ＡＳＩＣ（Ａｐｐｌｉｃａｔｉｏｎ　Ｓｐｅｃｉｆｉｃ　Ｉｎｔｅｇｒａｔｅｄ　Ｃｉｒｃｕｉｔ）、ＦＰＧＡ（Ｆｉｅｌｄ　Ｐｒｏｇｒａｍｍａｂｌｅ　Ｇａｔｅ　Ａｒｒａｙ）等によるものであってもよい。 The discrimination device 5 may be a circuit composed of an analog circuit, a digital circuit, or an analog / digital mixed circuit. Further, a control circuit for controlling each function of the discriminating device 5 may be provided. The implementation of each circuit may be by ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), or the like.
　同様に、噴射制御部６も、物理的には、ＣＰＵ、ＲＡＭおよびＲＯＭ、通信モジュール、補助記憶装置、などを含むコンピュータシステムとして構成することができ、ＣＰＵやＲＡＭなどに所定のコンピュータソフトウェアを読み込ませることによりその機能が実現される。 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, and the like, and loads predetermined computer software into the CPU, RAM, and the like. The function is realized by making it.
　図５は、実施形態に係る廃ブラスチックの材質判別処理のフローチャートである。図５に示すフローチャートの各処理は判別装置５により実行される。 FIG. 5 is a flowchart of the material discrimination process of the waste plastic according to the embodiment. Each process of the flowchart shown in FIG. 5 is executed by the discriminating device 5.
　ステップＳ０１では、前処理部５１により、中赤外線カメラ４によるスペクトルＳorg（ｎ，ｗ）が取得される。ここで、ｎはセンサ数（中赤外線カメラ４によりコンベア２の幅方向で区分されるスペクトル検出領域の数）であり、センサ数が３１８個の場合には各検出領域に対応する０～３１７の整数が用いられる。ｗはスペクトルの波長であり、本実施形態では、２７００（nm）～５３００（nm）の間で２０（nm）刻みで合計１３１個の波長が設定され、各波長に対応する０～１３０の整数が用いられる。つまり、Ｓorg（ｎ，ｗ）は、コンベア２の幅方向に沿ったｎ番目のスペクトル検出領域における、波長ｗのスペクトルの強度の数値を表す。 In step S01, the preprocessing unit 51 acquires the spectrum S org (n, w) taken by the mid-infrared camera 4. Here, n is the number of sensors (the number of spectrum detection regions divided in the width direction of the conveyor 2 by the mid-infrared camera 4), and when the number of sensors is 318, 0 to 317 corresponding to each detection region. An integer is used. w is the wavelength of the spectrum, and in the present embodiment, a total of 131 wavelengths are set between 2700 (nm) and 5300 (nm) in increments of 20 (nm), and an integer of 0 to 130 corresponding to each wavelength is set. Is used. That is, S org (n, w) represents a numerical value of the intensity of the spectrum of the wavelength w in the nth spectrum detection region along the width direction of the conveyor 2.
　ステップＳ０２では、前処理部５１により、ステップＳ０１で取得されたスペクトルＳorg（ｎ，ｗ）が補正されて、補正済みのスペクトルＳcor（ｎ，ｗ）が算出される。この補正により、測定空間の水蒸気及び二酸化炭素の濃度変化、計測対象の黒色廃プラスチック片Ｓ１、Ｓ２の温度、照明１０および中赤外線カメラ４の経年劣化、コンベア２上の位置、などの影響によるスペクトル強度の特性の差異を吸収できる。補正済みのスペクトルＳcor（ｎ，ｗ）は、例えば下記の（１）式により算出できる。 In step S02, the preprocessing unit 51 corrects the spectrum S org (n, w) acquired in step S01, and calculates the corrected spectrum S cor (n, w). Due to this correction, the spectrum due to the influence of changes in the concentration 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 aged deterioration of the illumination 10 and the mid-infrared camera 4, the position on the conveyor 2, and the like. It can absorb the difference in strength characteristics. The corrected spectrum S cor (n, w) can be calculated by, for example, the following equation (1).
Figure JPOXMLDOC01-appb-M000001
 ここで、Wref（ｎ，ｗ）は、反射光が明るい条件で計測した第１の補正用スペクトルである。Dref（ｎ，ｗ）は、反射光が上記の明るい条件よりも暗い条件で計測した第２の補正用スペクトルである。これらの補正用スペクトルWref（ｎ，ｗ）、Dref（ｎ，ｗ）は、例えば、材質判別処理を実行する前に中赤外線カメラ４の校正を行うときに抽出できる。
Figure JPOXMLDOC01-appb-M000001
 Here, W ref (n, w) is the first correction spectrum measured under the condition that the reflected light is bright. D ref (n, w) is a second correction spectrum measured under a condition in which the reflected light is darker than the above-mentioned bright condition. These correction spectra W ref (n, w) and D ref (n, w) can be extracted, for example, when the mid-infrared camera 4 is calibrated before the material discrimination process is executed.
　図６は、補正用のスペクトルWref（ｎ，ｗ）、Dref（ｎ，ｗ）の抽出手法を示す図である。図６に示すように、コンベア２の搬送路３上の、中赤外線カメラ４の撮像領域に、補正用スペクトルを取得するための校正板１１を設置して、中赤外線カメラ４による反射光のスペクトルの検出を行うことで、補正用のスペクトルWref（ｎ，ｗ）、Dref（ｎ，ｗ）を取得できる。 FIG. 6 is a diagram showing an extraction method of spectra W ref (n, w) and D ref (n, w) for correction. As shown in FIG. 6, a calibration plate 11 for acquiring a correction spectrum is installed in the imaging region of the mid-infrared camera 4 on the transport path 3 of the conveyor 2, and the spectrum of the reflected light by the mid-infrared camera 4 is provided. By detecting, the spectra W ref (n, w) and D ref (n, w) for correction can be obtained.
　反射光が明るい条件で計測した第１の補正用スペクトルWref（ｎ，ｗ）の場合、中赤外線領域の波長をすべて反射する校正板１１（アルミ、ステンレス等）を置き、照明１０を点灯した状態で、すべてのセンサ（ｎ＝０、１，２、・・・、３１７）について、全波長（ｗ＝０（２７００）、１（２７２０）、２（２７４０）、・・・、１３０（５３００））のデータを取得する。 In the case of the first correction spectrum W ref (n, w) measured under conditions where the reflected light is bright, a calibration plate 11 (aluminum, stainless steel, etc.) that reflects all wavelengths in the mid-infrared region is placed and the illumination 10 is turned on. In the state, for all sensors (n = 0, 1, 2, ..., 317), all wavelengths (w = 0 (2700), 1 (2720), 2 (2740), ..., 130 (5300) )) Get the data.
　反射光が暗い条件で計測した第２の補正用スペクトルDref（ｎ，ｗ）の場合、中赤外線領域の波長をすべて反射する校正板１１（アルミ、ステンレス等）を置き、照明１０を消灯した状態（もしくはカメラのシャッターを閉じた状態）で、すべてのセンサ（ｎ＝０、１，２、・・・、３１７）について、全波長（ｗ＝０（２７００）、１（２７２０）、２（２７４０）、・・・、１３０（５３００））のデータを取得する。 In the case of the second correction spectrum D ref (n, w) measured under the condition that the reflected light is dark, a calibration plate 11 (aluminum, stainless steel, etc.) that reflects all wavelengths in the mid-infrared region is placed and the illumination 10 is turned off. In the state (or with the camera shutter closed), all wavelengths (w = 0 (2700), 1 (2720), 2 ( 2740), ..., 130 (5300)) data are acquired.
　校正板１１は、例えば図６に点線の矢印で示すように、補正用のスペクトルWref（ｎ，ｗ）、Dref（ｎ，ｗ）を取得する際に配置される、コンベア２の搬送路３上の、中赤外線カメラ４の撮像領域の位置と、中赤外線カメラ４の撮像領域や照明１０の照射範囲から外れる待機位置との間で移動可能に設置されるのが好ましい。言い換えると、校正板１１は、中赤外線カメラ４の視野内の所定位置と、視野外の所定位置とに固定可能であり、両方の所定位置の間を移動可能であるのが好ましい。校正板１１は、照明１０からの光を受ける主面の表面粗さが大きくざらざらした面となるように加工するのが好ましい。これにより、反射光のハレーションの発生を抑制できる。 The calibration plate 11 is arranged when acquiring the correction spectra W ref (n, w) and D ref (n, w), as shown by the dotted arrows in FIG. 6, for example, the transport path of the conveyor 2. It is preferable that the camera is movably installed between the position of the imaging region of the mid-infrared camera 4 and the standby position outside the imaging region of the mid-infrared camera 4 and the irradiation range of the illumination 10. In other words, the calibration plate 11 can be fixed at a predetermined position in the field of view of the mid-infrared camera 4 and a predetermined position outside the field of view, and is preferably movable between both predetermined positions. The calibration plate 11 is preferably processed so that the surface roughness of the main surface that receives the light from the illumination 10 is large and rough. As a result, it is possible to suppress the occurrence of halation of the reflected light.
　また、補正用スペクトルの取得時には、コンベア２は停止していてもよい。この場合、校正板１１の動作の何らかの不具合により、校正板１１が中赤外線カメラ４の撮像領域の位置に正しく配置されないと、照明１０の赤外線によりコンベア２の搬送路３上の赤外線が照射される部分の温度が上昇し、焼損や発火の虞がある。このため、校正板１１が中赤外線カメラ４の視野内に固定されていない場合には、照明１０から赤外線を照射しないようにインターロックを設けるのが好ましい。 Further, the conveyor 2 may be stopped when the correction spectrum is acquired. In this case, if the calibration plate 11 is not correctly arranged at the position of the imaging region of the mid-infrared camera 4 due to some trouble in the operation of the calibration plate 11, the infrared rays of the illumination 10 irradiate the infrared rays on the conveyor 2 with the conveyor 2. The temperature of the part rises, and there is a risk of burning or ignition. Therefore, when the calibration plate 11 is not fixed in the field of view of the mid-infrared camera 4, it is preferable to provide an interlock so as not to irradiate infrared rays from the illumination 10.
　なお、図６に示すように、照明１０は、赤外線の光源であるランプ１０Ａ（シースヒーター、カーボンランプ、カンタルランプなど）と、ランプ１０Ａの熱を集める反射板１０Ｂとを有する。ランプ１０Ａは、コンベア２の幅方向（ｙ方向）に沿って延在するよう形成され、ｙ軸に沿った軸心まわりの全方向に赤外線を放射するよう配置される。反射板１０Ｂは、ランプ１０Ａを基準としてコンベア２の搬送路３とは反対側に配置され、ランプ１０Ａの軸心まわりの周方向に沿って湾曲して形成され、これによりランプ１０Ａからコンベア２とは反対側に放射された赤外線を集めてコンベア２側に反射して送ることができる。反射板１０Ｂは、例えば、アルミニウム、ステンレス、またはアルミニウムメッキなどされた部材からなる。 As shown in FIG. 6, the illumination 10 has a lamp 10A (sheath heater, carbon lamp, cantal lamp, etc.) which is an infrared light source, and a reflector 10B which collects the heat of 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 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 conveyor 2 with respect to the lamp 10A, and is formed to be curved along the circumferential direction around the axis of the lamp 10A, whereby the lamp 10A to the conveyor 2 Can collect infrared rays radiated on the opposite side, reflect them on the conveyor 2 side, and send them. The reflector 10B is made of, for example, a member plated with aluminum, stainless steel, or aluminum.
　図５に戻り、ステップＳ０３では、前処理部５１により、補正済みのスペクトルＳcor（ｎ，ｗ）の中から、特徴のある波長領域が切り出される。図７は、反射波スペクトルから特徴のある波長領域を切り出す処理の一例を示す図である。図７の横軸はスペクトルの波長（ｎｍ）を示し、縦軸は各波長におけるスペクトルの強度を示す。図７には、ＡＢＳ、ＨＩＰＳ，ＰＰ、ＰＥの各材質のスペクトルの一例が示されている。そして、図７の例では、３２５０～３７５０（ｎｍ）及び４４００～４６００（ｎｍ）の波長領域のスペクトルが切り出されている。図７の例では、切り出される波長領域の範囲が網掛け模様で示されている。 Returning to FIG. 5, in step S03, the preprocessing unit 51 cuts out a characteristic wavelength region from the corrected spectrum S cor (n, w). FIG. 7 is a diagram showing an example of processing for cutting out a characteristic wavelength region from the reflected wave spectrum. The horizontal axis of FIG. 7 indicates the wavelength (nm) of the spectrum, and the vertical axis indicates the intensity of the spectrum at each wavelength. FIG. 7 shows an example of the spectrum of each material of ABS, HIPS, PP, and PE. Then, in the example of FIG. 7, spectra in the wavelength regions of 3250 to 3750 (nm) and 4400 to 4600 (nm) are cut out. In the example of FIG. 7, the range of the wavelength region to be cut out is shown by a shaded pattern.
　図５に戻り、ステップＳ０４では、第１判定部５２により、ステップＳ０２にて補正され、かつ、ステップＳ０３にて特徴のある波長領域が切り出されたスペクトルを用いて、各スペクトルがコンベア２のベルト（搬送路３）か、搬送路３上の物体（廃プラスチック）かが判定される。第１判定部５２は、本実施形態では学習済みのＯｎｅ　Ｃｌａｓｓ　ＳＶＭを利用して判定を行う。 Returning to FIG. 5, in step S04, each spectrum is a belt of the conveyor 2 using the spectrum corrected in step S02 by the first determination unit 52 and the characteristic wavelength region cut out in step S03. It is determined whether it is (conveyor path 3) or an object (waste plastic) on the conveyor path 3. In the present embodiment, the first determination unit 52 makes a determination using the learned One Class SVM.
　ステップＳ０５では、第２判定部５３により、ステップＳ４にて物体（廃プラスチック）と判定されたスペクトルから、学習済みのＰＬＳを使用して２種類の特徴データＳｃｏｒｅ１、Ｓｃｏｒｅ２が抽出される。図８は、特徴データの抽出例を示す図である。図８の横軸は第１の特徴データ（Ｓｃｏｒｅ１）を示し、縦軸は第２の特徴データ（Ｓｃｏｒｅ２）を示す。図８には、図７に例示したＡＢＳ、ＨＩＰＳ，ＰＰ、ＰＥの４種類の材質の抽出例が示されている。図８に示すように、２つの特徴データＳｃｏｒｅ１、Ｓｃｏｒｅ２による二次元空間上では、各材質ごとにプロットされる領域が区分可能であることがわかる。なお、特徴データの数は、２種類以外でもよい。 In step S05, the second determination unit 53 extracts two types of feature data Score1 and Score2 from the spectrum determined to be an object (waste plastic) in step S4 using the learned PLS. FIG. 8 is a diagram showing an example of extracting feature data. The horizontal axis of FIG. 8 shows the first feature data (Score1), and the vertical axis shows the second feature data (Score2). FIG. 8 shows an extraction example of four types of materials, ABS, HIPS, PP, and PE illustrated in FIG. 7. As shown in FIG. 8, it can be seen that the area plotted for each material can be divided on the two-dimensional space by the two feature data Score1 and Score2. The number of feature data may be other than two.
　図５に戻り、ステップＳ０６では、第３判定部５４により、ステップＳ５にて抽出された２種類の特徴データＳｃｏｒｅ１、Ｓｃｏｒｅ２に基づき、学習済みの決定木を使用して材質の判別が行われる。図９は、決定木を用いた材質判別の例を示す図である。本実施形態では、最終的に４種類の材質（ＰＥ、ＰＰ，ＡＢＳ、ＨＩＰＳ）を識別するため、図９に示すように決定木は２階層の条件分岐を有する。第１階層では、条件分岐の関数ｆ１（Ｓｃｏｒｅ１、Ｓｃｏｒｅ２）を用いて、特徴データＳｃｏｒｅ１、Ｓｃｏｒｅ２の組が２つのグループＧ１、Ｇ２に分けられる。一方のグループＧ１は、第２階層では、条件分岐の関数ｆ２（Ｓｃｏｒｅ１、Ｓｃｏｒｅ２）を用いて、さらに２つのグループＧ１１、Ｇ１２に分けられる。他方のグループＧ２は、第２階層では、条件分岐の関数ｆ３（Ｓｃｏｒｅ１、Ｓｃｏｒｅ２）を用いて、さらに２つのグループＧ２１、Ｇ２２に分けられる。この結果、特徴データＳｃｏｒｅ１、Ｓｃｏｒｅ２の組は、４つのグループＧ１１、Ｇ１２、Ｇ２１、Ｇ２２に分類され、各グループの材質がそれぞれＰＥ，ＰＰ，ＡＢＳ、ＨＩＰＳと判定される。 Returning to FIG. 5, in step S06, the third determination unit 54 determines the material using the learned decision tree based on the two types of feature data Score1 and Score2 extracted in step S5. FIG. 9 is a diagram showing an example of material discrimination using a decision tree. In the present embodiment, the decision tree has two layers of conditional branching as shown in FIG. 9 in order to finally identify four types of materials (PE, PP, ABS, HIPS). In the first layer, the set of feature data Score1 and Score2 is divided into two groups G1 and G2 by using the conditional branching function f1 (Score1 and Score2). One group G1 is further divided into two groups G11 and G12 in the second layer by using the conditional branching function f2 (Score1 and Score2). The other group G2 is further divided into two groups G21 and G22 in the second layer by using the conditional branching function f3 (Score1 and Score2). As a result, the set of feature data Score1 and Score2 is 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.
　このように、本実施形態に係る廃プラスチックの材質判定装置１の判別装置５は、中赤外線カメラ４により検出された、照明１０によりコンベア２の搬送路３に照射された光の反射光のスペクトルが、廃プラスチック片Ｓ及び搬送路３のどちらかのものかを判定する第１判定部５２と、第１判定部５２により廃プラスチック片Ｓと判定されたスペクトルから２種類の特徴データＳｃｏｒｅ１、Ｓｃｏｒｅ２を抽出する第２判定部５３と、第２判定部５３により抽出された特徴データＳｃｏｒｅ１、Ｓｃｏｒｅ２に基づき廃プラスチック片Ｓの材質Ｓ１、Ｓ２を判別する第３判定部５４と、を備える。 As described above, the discrimination device 5 of the waste plastic material determination device 1 according to the present embodiment is a spectrum of the reflected light of the light detected by the mid-infrared camera 4 and irradiated to the transport path 3 of the conveyor 2 by the illumination 10. There are two types of feature data, Score1 and Score2, from the spectrum determined to be the waste plastic piece S by the first determination unit 52, which determines whether the waste plastic piece S or the transport path 3 is used. The second determination unit 53 is provided, and the third determination unit 54 that determines the materials S1 and S2 of the waste plastic piece S based on the feature data Scope1 and Spectra2 extracted by the second determination unit 53 is provided.
　この構成により、反射スペクトルの入力情報から、第１判定部５２の物体判別による黒色廃プラスチック片Ｓのスペクトルへの絞り込みと、第２判定部５３の特徴量抽出によるスペクトル情報から特徴データへの次元圧縮と、第３判定部５４の分類処理との三段階の判定処理とデータの絞り込みを経て、廃プラスチックの材質の出力情報を得ることができる。このため、本実施形態の廃プラスチックの材質判定装置１は、廃プラスチックの材質の判定を多種の条件を考慮して行うことができ、かつ、多段階に亘ってきめ細かく行うことが可能となり、廃プラスチックの材質の判定精度を向上できる。 With this configuration, the input information of the reflection spectrum is narrowed down to the spectrum of the black waste plastic piece S by the object discrimination of the first judgment unit 52, and the dimension from the spectrum information to the feature data by the feature amount extraction of the second judgment unit 53. The output information of the material of the waste plastic can be obtained through the three-step determination process of the compression and the classification process of the third determination unit 54 and the narrowing down of the data. Therefore, the waste plastic material determination device 1 of the present embodiment can determine the material of the waste plastic in consideration of various conditions, and can perform detailed determination in multiple stages. The accuracy of determining the material of plastic can be improved.
　また、本実施形態に係る廃プラスチックの材質判定装置１の判別装置５は、中赤外線カメラ４により検出された反射スペクトルＳorg（ｎ，ｗ）を、反射光が明るい条件で計測した第１の補正用スペクトルWref（ｎ，ｗ）と、この明るい条件よりも相対的に暗い条件で計測した第２の補正用スペクトルDref（ｎ，ｗ）とを用いて補正する前処理部５１を備える。 Further, the discrimination device 5 of the waste plastic material determination device 1 according to the present embodiment is the first measurement of the reflection spectrum S org (n, w) detected by the mid-infrared camera 4 under the condition that the reflected light is bright. A preprocessing unit 51 for correction using a correction spectrum W ref (n, w) and a second correction spectrum D ref (n, w) measured under a condition relatively darker than this bright condition is provided. ..
　このように反射スペクトルＳorg（ｎ，ｗ）を、例えば（１）式を用いて、補正用のスペクトルWref（ｎ，ｗ）、Dref（ｎ，ｗ）を用いて補正することにより、計測対象の黒色廃プラスチック片Ｓ１、Ｓ２の温度、中赤外線カメラ４の経年劣化、コンベア２上の位置、などの影響によるスペクトル強度の特性の差異を抑制できる。このため、補正済みのスペクトルＳcor（ｎ，ｗ）を用いて、第１判定部５２、第２判定部５３、第３判定部５４の学習と判定とを行うことによって、廃プラスチックの材質の判定精度をさらに向上できる。 In this way, the reflection spectrum S org (n, w) is corrected by using, for example, the equation (1) and the correction spectra W ref (n, w) and D ref (n, w). Differences in spectral intensity characteristics due to the effects of the temperatures of the black waste plastic pieces S1 and S2 to be measured, the aged deterioration of the mid-infrared camera 4, the position on the conveyor 2, and the like can be suppressed. Therefore, the material of the waste plastic is made of waste plastic by learning and determining the first determination unit 52, the second determination unit 53, and the third determination unit 54 using the corrected spectrum S cor (n, w). Judgment accuracy can be further improved.
　また、前処理部５１は、さらに、補正されたスペクトルＳcor（ｎ，ｗ）から所定の周波数の範囲を切り出す加工を行い、加工後のスペクトルを第１判定部５２に出力する。 Further, the preprocessing unit 51 further performs processing to cut out a predetermined frequency range from the corrected spectrum S cor (n, w), and outputs the processed spectrum to the first determination unit 52.
　この構成により、スペクトルから廃プラスチックの材質と関連が強い部分を抽出して第１判定部５２、第２判定部５３、第３判定部５４の学習と判定とに利用することができるので、学習や判定を阻害するノイズの混入を低減でき、廃プラスチックの材質の判定精度をさらに向上できる。 With this configuration, a portion strongly related to the material of the waste plastic can be extracted from the spectrum and used for learning and determination of the first determination unit 52, the second determination unit 53, and the third determination unit 54. It is possible to reduce the mixing of noise that hinders the determination and further improve the determination accuracy of the waste plastic material.
　なお、本実施形態では、前処理部５１は、反射スペクトルＳorg（ｎ，ｗ）の補正処理と、所定の周波数の範囲を切り出す処理の２つの処理を行うが、２つの処理の一方のみを行う構成でもよい。 In the present embodiment, the preprocessing unit 51 performs two processes, that is, a correction process for the reflection spectrum S org (n, w) and a process for cutting out a predetermined frequency range, but only one of the two processes is performed. It may be configured to be performed.
　また、本実施形態では、材質判定対象の廃プラスチックが黒色廃プラスチックＳの場合を例示して説明したが、例えば赤色や青色等の他の色の廃プラスチックでもよい。また、色が異なる廃プラスチックを混在して用いてもよい。 Further, in the present embodiment, the case where the waste plastic to be material-determined is the black waste plastic S has been described as an example, but waste plastics of other colors such as red and blue may be used. Further, waste plastics having different colors may be mixed and used.
　図１０～図１４を参照して、本実施形態の材質判定装置１による所望の材質の廃プラスチックの選別手法について説明する。図１０は、本実施形態の材質判定装置１による第１の材質選別手法を示す平面図である。図１０には、図３に示した材質判定装置１の平面図に対応し、簡略化した図が示されている。図１０以降では、選別手法の一例として、５種類の材質（１）、（２）、（３）、（４）、（５）が混合されたプラスチックミックスを選別対象とする例を説明する。 A method for sorting waste plastic of a desired material by the material determination device 1 of the present embodiment will be described with reference to FIGS. 10 to 14. FIG. 10 is a plan view showing a first material selection method by the material determination device 1 of the present embodiment. FIG. 10 shows a simplified view corresponding to the plan view of the material determination device 1 shown in FIG. From FIG. 10 onward, as an example of the sorting method, an example in which a plastic mix in which five kinds of materials (1), (2), (3), (4), and (5) are mixed is targeted for sorting will be described.
　図１０の例では、コンベア２や収集装置１２がコンベア２の幅方向（ｙ方向）に区分されない一系統の搬送路が形成される構成を例示する。収集装置１２では、噴射ノズル７の噴射と停止によって、廃プラスチックを図２などに示した仕切り板９を境界として分別するため、選別対象を大きく２種類に分類する。このため、選別対象の５種類の材質が混在するプラスチックミックスを単一材質ごとにそれぞれ選別するためには、収集装置１２のうち一方の収集装置１２－１（例えば、噴射ノズル７からエアーを噴射された廃プラスチックが回収される装置）に一種類ずつ分別する処理を繰り返す必要がある。つまり、図１０に示すように、まずプラスチックミックスから材質（１）のみを分類して、収集装置１２－１で回収する。このとき、他方の収集装置１２－２に収集されている残りのプラスチックミックスは他の４種類の材質（２）～（５）が混在している。次に、４種類が混在する残りのプラスチックミックスを再度材質判定装置１に投入し、（２）～（５）のいずれか１つを分類する。この手順を４回繰り返すことで、５種類の材質（１）～（５）のそれぞれに分別することができる。 In the example of FIG. 10, the configuration in which the conveyor 2 and the collecting device 12 are not divided in the width direction (y direction) of the conveyor 2 is formed as a system of transport paths is illustrated. In the collecting device 12, waste plastic is sorted by the injection and stop of the injection nozzle 7 with the partition plate 9 shown in FIG. 2 or the like as a boundary, so that the selection target is roughly classified into two types. Therefore, in order to sort the plastic mix in which the five types of materials to be sorted are mixed for each single material, one of the collecting devices 12 is the collecting device 12-1 (for example, air is injected from the injection nozzle 7). It is necessary to repeat the process of separating each type of waste plastic into a device for collecting the waste plastic. That is, as shown in FIG. 10, first, only the material (1) is classified from the plastic mix and collected by the collecting device 12-1. At this time, the remaining plastic mix collected in the other collecting device 12-2 is a mixture of the other four types of materials (2) to (5). Next, the remaining plastic mix in which the four types are mixed is put into the material determination device 1 again, and any one of (2) to (5) is classified. By repeating this procedure four times, it is possible to separate each of the five types of materials (1) to (5).
　図１１は、本実施形態の材質判定装置１Ａによる第２の材質選別手法を示す平面図である。図１１以降では、コンベア２の搬送路３は、幅方向において第１の系統と第２の系統の二系統に区分される。より詳細には、投入口（振動フィーダー８）、コンベア２、収集装置１２のそれぞれが幅方向で２分される。なお、投入口８とコンベア２は、構成要素を２つにするのではなく、単一の要素に仕切り等をつけて系統間で混在しないようにする。例えば、コンベア２の搬送路３は、幅方向のほぼ中央の位置に搬送方向に沿って仕切り壁を設けることで２系統に区分できる。 FIG. 11 is a plan view showing a second material selection method by the material determination device 1A of the present embodiment. From FIG. 11 onward, the conveyor 2 transport path 3 is divided into two systems, a first system and a second system, in the width direction. More specifically, each of the input port (vibration feeder 8), the conveyor 2, and the collecting device 12 is divided into two in the width direction. The input port 8 and the conveyor 2 do not have two components, but a single element is provided with a partition or the like so that the components do not mix with each other. 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 a position substantially at the center in the width direction.
　以下の説明では、第１の系統を添え字Ａで表し、第２の系統を添え字Ｂで表す。また、図１０の収集装置１２－１に相当する要素を「収集装置Ａ１」及び「収集装置Ｂ１」と表記し、図１０の収集装置１２－２に相当する要素を「収集装置Ａ２」及び「収集装置Ｂ２」と表記する。 In the following description, the first system is represented by the subscript A, and the second system is represented by the subscript B. Further, the elements corresponding to the collecting device 12-1 in FIG. 10 are referred to as "collecting device A1" and "collecting device B1", and the elements corresponding to the collecting device 12-2 in FIG. 10 are referred to as "collecting device A2" and "collecting device A2". Notated as "collector B2".
　図１１の例では、第１の系統と第２の系統で、同一の材質の廃プラスチック片が収集される。例えば図１１に示すように、第１、第２の系統のそれぞれの投入口Ａ、Ｂに５種類の材質（１）～（５）が混在するプラスチックミックスが供給され、各系統で材質判定が行われて、収集装置Ａ１、Ｂ１でそれぞれ同一の材質（１）の廃プラスチック片が収集される。また、収集装置Ａ２、Ｂ２では、残りの材質（２）～（５）が混在する廃プラスチックが収集される。 In the example of FIG. 11, waste plastic pieces of the same material are collected in the first system and the second system. For example, as shown in FIG. 11, a plastic mix in which five types of materials (1) to (5) are mixed is supplied to the inlets A and B of the first and second systems, respectively, and the material can be determined in each system. Then, waste plastic pieces of the same material (1) are collected by the collecting devices A1 and B1 respectively. Further, the collecting devices A2 and B2 collect waste plastic in which the remaining materials (2) to (5) are mixed.
　図１２は、本実施形態の材質判定装置１Ｂによる第３の材質選別手法を示す平面図である。図１２の例では、第１の系統では、第１の材質の廃プラスチック片を収集すると共に、残りの廃プラスチック片を第２の系統へ供給し、第２の系統では、残りの廃プラスチック片の中から第２の材質の廃プラスチック片を収集する。図１２の例では、複数種の混合素材を、第１の材質と、第２の材質と、その他の材質の３種類に分別できる。 FIG. 12 is a plan view showing a third material selection method by the material determination device 1B of the present embodiment. In the example of FIG. 12, in the first system, waste plastic pieces of the first material are collected and the remaining waste plastic pieces are supplied to the second system, and in the second system, the remaining waste plastic pieces. Collect the waste plastic pieces of the second material from the inside. In the example of FIG. 12, a plurality of types of mixed materials can be classified into three types: a first material, a second material, and other materials.
　図１２の例では、第１の系統の投入口Ａに、５種類の材質（１）～（５）が混在するプラスチックミックスが供給され、第１の系統のコンベアＡで材質判定が行われて、収集装置Ａ１で材質（１）の廃プラスチック片が収集される。また、収集装置Ａ２では、残りの材質（２）～（５）が混在する廃プラスチックが収集される。 In the example of FIG. 12, a plastic mix in which five kinds of materials (1) to (5) are mixed is supplied to the input port A of the first system, and the material is determined by the conveyor A of the first system. , The waste plastic piece of the material (1) is collected by the collecting device A1. Further, the collecting device A2 collects waste plastic in which the remaining materials (2) to (5) are mixed.
　次に、収集装置Ａ２で収集された残りの材質（２）～（５）が混在する廃プラスチックは、搬送装置１３により第２の系統の投入口Ｂまで搬送されて、投入口Ｂに供給される。第２の系統のコンベアＢで材質判定が行われて、収集装置Ｂ１で材質（２）の廃プラスチック片が収集される。収集装置Ｂ２では、残りの材質（３）～（５）が混在する廃プラスチックが収集される。 Next, the waste plastic in which the remaining materials (2) to (5) collected by the collection device A2 are mixed is conveyed to the input port B of the second system by the transfer device 13 and supplied to the input port B. NS. The material is determined by the conveyor B of the second system, and the waste plastic piece of the material (2) is collected by the collecting device B1. In the collecting device B2, waste plastic in which the remaining materials (3) to (5) are mixed is collected.
　図１３は、本実施形態の材質判定装置１Ｃによる第４の材質選別手法を示す平面図である。図１３の例では、第１の系統では、第１の材質と微量の他の材質の廃プラスチック片を収集すると共に、収集した廃プラスチック片を第２の系統へ供給し、第２の系統では、第１の材質と微量の他の材質の廃プラスチック片の中から第１の材質の廃プラスチック片を収集する。図１３の例では、所定の一種の材質のプラスチック片を高純度に選別できる。 FIG. 13 is a plan view showing a fourth material selection method by the material determination device 1C of the present embodiment. In the example of FIG. 13, in the first system, waste plastic pieces of the first material and a trace amount of other materials are collected, and the collected waste plastic pieces are supplied to the second system. , Collect the waste plastic pieces of the first material from the waste plastic pieces of the first material and a trace amount of other materials. In the example of FIG. 13, a plastic piece made of a predetermined type of material can be sorted with high purity.
　図１３の例では、第１の系統の投入口Ａに、５種類の材質（１）～（５）が混在するプラスチックミックスが供給され、第１の系統のコンベアＡで材質判定が行われて、収集装置Ａ１で材質（１）と微量の（２）～（５）の廃プラスチック片が収集される。また、収集装置Ａ２では、残りの材質（２）～（５）と微量の（１）が混在する廃プラスチックが収集される。 In the example of FIG. 13, a plastic mix in which five kinds of materials (1) to (5) are mixed is supplied to the input port A of the first system, and the material is determined by the conveyor A of the first system. , Material (1) and a small amount of waste plastic pieces (2) to (5) are collected by the collecting device A1. Further, the collecting device A2 collects waste plastic in which the remaining materials (2) to (5) and a trace amount (1) are mixed.
　次に、収集装置Ａ１で収集された材質（１）と微量の（２）～（５）が混在する廃プラスチックは、搬送装置１３により第２の系統の投入口Ｂまで搬送されて、投入口Ｂに供給される。第２の系統のコンベアＢで材質判定が行われて、収集装置Ｂ１で再度材質（１）が選別されて材質（１）の廃プラスチック片が収集される。この収集装置Ｂ１で収集された材質（１）は、収集装置Ａ１で収集された素材より材質（１）の純度が高くなっている。収集装置Ｂ２では、残りの材質（１）～（５）が混在する廃プラスチックが収集される。 Next, the waste plastic in which the material (1) collected by the collecting device A1 and a small amount of (2) to (5) are mixed is transported to the input port B of the second system by the transport device 13, and is transported to the input port B. It is supplied to B. The material is determined by the conveyor B of the second system, the material (1) is sorted again by the collecting device B1, and the waste plastic pieces of the material (1) are collected. The material (1) collected by the collecting device B1 has a higher purity than the material collected by the collecting device A1. In the collecting device B2, waste plastic in which the remaining materials (1) to (5) are mixed is collected.
　図１４は、本実施形態の材質判定装置１Ｄによる第５の材質選別手法を示す平面図である。図１４の例では、第１の系統では、第１の材質と微量の他の材質の廃プラスチック片を除外すると共に、除外した残りの廃プラスチック片を第２の系統へ供給し、第２の系統では、他の廃プラスチック片の中からさらに第１の材質と微量の他の材質の廃プラスチック片を除外して、第１の材質を含まない廃プラスチック片を収集する。図１４の例では、所定の一種の材質のプラスチック片を混在素材の中からより確実に選別できる。 FIG. 14 is a plan view showing a fifth material selection method by the material determination device 1D of the present embodiment. In the example of FIG. 14, in the first system, waste plastic pieces of the first material and a trace amount of other materials are excluded, and the remaining excluded waste plastic pieces are supplied to the second system, and the second system is used. In the system, the first material and a trace amount of waste plastic pieces of other materials are further excluded from the other waste plastic pieces, and the waste plastic pieces not containing the first material are collected. In the example of FIG. 14, a plastic piece of a predetermined type of material can be more reliably selected from the mixed materials.
　図１４の例では、第１の系統の投入口Ａに、５種類の材質（１）～（５）が混在するプラスチックミックスが供給され、第１の系統のコンベアＡで材質判定が行われて、収集装置Ａ１で材質（１）と微量の（２）～（５）の廃プラスチック片が収集される。また、収集装置Ａ２では、残りの材質（２）～（５）と少量の（１）が混在する廃プラスチックが収集される。 In the example of FIG. 14, a plastic mix in which five kinds of materials (1) to (5) are mixed is supplied to the input port A of the first system, and the material is determined by the conveyor A of the first system. , Material (1) and a small amount of waste plastic pieces (2) to (5) are collected by the collecting device A1. Further, the collecting device A2 collects waste plastic in which the remaining materials (2) to (5) and a small amount (1) are mixed.
　次に、収集装置Ａ２で収集された材質（２）～（５）と少量の（１）が混在する廃プラスチックは、搬送装置１３により第２の系統の投入口Ｂまで搬送されて、投入口Ｂに供給される。第２の系統のコンベアＢで材質判定が行われて、収集装置Ｂ１で再度材質（１）が選別されて材質（１）と微量の材質（２）～（５）が混在する廃プラスチック片が収集される。収集装置Ｂ２では、残りの材質（２）～（５）と微量の（１）が混在する廃プラスチックが収集される。 Next, the waste plastic in which the materials (2) to (5) collected by the collecting device A2 and a small amount (1) are mixed is conveyed to the input port B of the second system by the transfer device 13, and is conveyed to the input port B. It is supplied to B. The material is determined by the conveyor B of the second system, the material (1) is sorted again by the collecting device B1, and waste plastic pieces in which the material (1) and a trace amount of the materials (2) to (5) are mixed are produced. Collected. In the collecting device B2, waste plastic in which the remaining materials (2) to (5) and a trace amount (1) are mixed is collected.
　図１５は、材質判定装置１の操作画面の一例を示す図である。図１５に示す操作画面は、例えば材質判定装置１の本体に設置される表示装置に表示される。図１５に示すように、操作画面には、選別するプラスチックの材質名が列挙され、上記の第１の系統（図１５では「１次」と、第２の系統（図１５では「２次」）ごとに噴射して選別する材質を個別に選択可能となっている。操作画面が表示される表示装置は例えばタッチパネルであり、「噴射選択」欄の「ＯＦＦ」表示を押下するなどの操作によって「ＯＮ」表示に切り替えることによって、当該材質（図１５ではＡＢＳ）の場合に噴射ノズル７がエアーを噴射して収集装置で分別するように設定できる。また、操作画面では、「投入原料面積比」欄を設け、材料判定処理の判定結果に応じて、素材に混合される各材質の割合を表示することもできる。 FIG. 15 is a diagram showing an example of an operation screen of the material determination device 1. The operation screen shown in FIG. 15 is displayed on, for example, a display device installed in the main body of the material determination device 1. As shown in FIG. 15, the material names of the plastics to be sorted are listed on the operation screen, and the first system (“primary” in FIG. 15 and the second system (“secondary” in FIG. 15”) are listed. ), The material to be jetted and sorted can be individually selected. The display device on which the operation screen is displayed is, for example, a touch panel, and by an operation such as pressing the "OFF" display in the "spray selection" column. By switching to the "ON" display, it is possible to set the injection nozzle 7 to inject air and separate it by the collecting device in the case of the material (ABS in FIG. 15). In addition, on the operation screen, "input raw material area ratio". It is also possible to provide a column and display the ratio of each material mixed with the material according to the judgment result of the material judgment process.
　以上、具体例を参照しつつ本実施形態について説明した。しかし、本開示はこれらの具体例に限定されるものではない。これら具体例に、当業者が適宜設計変更を加えたものも、本開示の特徴を備えている限り、本開示の範囲に包含される。前述した各具体例が備える各要素およびその配置、条件、形状などは、例示したものに限定されるわけではなく適宜変更することができる。前述した各具体例が備える各要素は、技術的な矛盾が生じない限り、適宜組み合わせを変えることができる。 The present embodiment has been described above with reference to specific examples. However, the present disclosure is not limited to these specific examples. Those skilled in the art with appropriate design changes to these specific examples are also included in the scope of the present disclosure as long as they have the features of the present disclosure. Each element included in each of the above-mentioned specific examples, its arrangement, conditions, shape, and the like are not limited to those illustrated, and can be changed as appropriate. The combinations of the elements included in each of the above-mentioned specific examples can be appropriately changed as long as there is no technical contradiction.
　本国際出願は２０２０年２月１３日に出願された日本国特許出願２０２０－０２２８１１号に基づく優先権を主張するものであり、２０２０－０２２８１１号の全内容をここに本国際出願に援用する。 This international application claims priority based on Japanese Patent Application No. 2020-022811 filed on February 13, 2020, and the entire contents of No. 2020-022811 are incorporated herein by reference.
　１、１Ａ、１Ｂ、１Ｃ、１Ｄ　　廃プラスチックの材質判定装置
　２　　コンベア
　３　　搬送路
　４　　中赤外線カメラ（反射スペクトル検出部）
　５　　判別装置
　５１　　前処理部
　５２　　第１判定部
　５３　　第２判定部
　５４　　第３判定部
　１２、１２－１、１２－２、Ａ１、Ａ２、Ｂ１、Ｂ２　　収集装置
　Ｓ１、Ｓ２　　黒色廃プラスチック片 1, 1A, 1B, 1C, 1D Waste plastic material determination device 2 Conveyor 3 Conveyor path 4 Mid-infrared camera (reflection spectrum detector)
5 Discrimination device 51 Pretreatment unit 52 1st judgment unit 53 2nd judgment unit 54 3rd judgment unit 12, 12-1, 12-2, A1, A2, B1, B2 Collection device S1, S2 Black waste plastic piece

Claims (14)

  1. 　廃プラスチックの材質判定装置であって、
    　搬送路上で搬送される廃プラスチック片に光を照射する照射部と、
    　前記照射部により照射された光の反射光を受光して前記反射光のスペクトルを検出する反射スペクトル検出部と、
    　前記反射スペクトル検出部により検出された前記スペクトルが前記廃プラスチック片及び前記搬送路のどちらかのものかを判定する第１判定部と、
    　前記第１判定部により前記廃プラスチック片と判定されたスペクトルから特徴量を抽出する第２判定部と、
    　前記第２判定部により抽出された前記特徴量に基づき前記廃プラスチック片の材質を判別する第３判定部と、
    を備える廃プラスチックの材質判定装置。     It is a material judgment device for waste plastic.
    An irradiation unit that irradiates waste plastic pieces transported on the transport path with light,
    A reflection spectrum detection unit that receives the reflected light of the light emitted by the irradiation unit and detects the spectrum of the reflected light, and a reflection spectrum detection unit.
    A first determination unit that determines whether the spectrum detected by the reflection spectrum detection unit is either the waste plastic piece or the transport path.
    A second determination unit that extracts a feature amount from a spectrum determined to be the waste plastic piece by the first determination unit, and a second determination unit.
    A third determination unit that determines the material of the waste plastic piece based on the feature amount extracted by the second determination unit, and
    A waste plastic material determination device equipped with.
  2. 　前記反射スペクトル検出部により検出された前記スペクトルを、前記反射光が明るい条件で計測した第１の補正用スペクトルと、前記明るい条件よりも暗い条件で計測した第２の補正用スペクトルとを用いて補正する前処理部を備え、
    　前記第１判定部は、前記前処理部により補正された前記スペクトルを用いて前記判定を行う、
    請求項１に記載の廃プラスチックの材質判定装置。     The spectrum detected by the reflection spectrum detection unit is used as a first correction spectrum measured under a condition in which the reflected light is bright and a second correction spectrum measured under a condition darker than the bright condition. Equipped with a pre-processing unit for correction
    The first determination unit makes the determination using the spectrum corrected by the preprocessing unit.
    The waste plastic material determination device according to claim 1.
  3. 　前記前処理部は、補正された前記スペクトルから所定の周波数の範囲を切り出す加工を行い、
    　前記第１判定部は、前記前処理部により加工された前記スペクトルを用いて前記判定を行う、
    請求項２に記載の廃プラスチックの材質判定装置。     The pre-processing unit performs processing to cut out a predetermined frequency range from the corrected spectrum, and then performs processing.
    The first determination unit makes the determination using the spectrum processed by the pretreatment unit.
    The waste plastic material determination device according to claim 2.
  4. 　前記第１判定部は、学習済みのＯｎｅ　Ｃｌａｓｓ　ＳＶＭを用いて判定を行う、
    請求項１～３のいずれか１項に記載の廃プラスチックの材質判定装置。     The first determination unit makes a determination using the trained One Class SVM.
    The waste plastic material determination device according to any one of claims 1 to 3.
  5. 　前記第２判定部は、学習済みのＰＬＳを用いて判定を行う、
    請求項１～４のいずれか１項に記載の廃プラスチックの材質判定装置。     The second determination unit makes a determination using the learned PLS.
    The waste plastic material determination device according to any one of claims 1 to 4.
  6. 　前記第３判定部は、学習済みの決定木を用いて判定を行う、
    請求項１～５のいずれか１項に記載の廃プラスチックの材質判定装置。     The third determination unit makes a determination using a learned decision tree.
    The material determination device for waste plastic according to any one of claims 1 to 5.
  7. 　前記第３判定部の判定結果に基づき、前記搬送路を流れる前記廃プラスチック片から一の材質のものを収集する収集装置を備える、
    請求項１～６のいずれか１項に記載の廃プラスチックの材質判定装置。     A collecting device for collecting one material from the waste plastic pieces flowing through the transport path based on the determination result of the third determination unit.
    The waste plastic material determination device according to any one of claims 1 to 6.
  8. 　前記搬送路は、幅方向において第１の系統と第２の系統の二系統に区分される、
    請求項７に記載の廃プラスチックの材質判定装置。     The transport path is divided into two systems, a first system and a second system, in the width direction.
    The waste plastic material determination device according to claim 7.
  9. 　前記第１の系統と前記第２の系統で、同一の材質の廃プラスチック片を収集する、
    請求項８に記載の廃プラスチックの材質判定装置。     In the first system and the second system, waste plastic pieces of the same material are collected.
    The material determination device for waste plastic according to claim 8.
  10. 　前記第１の系統では、第１の材質の廃プラスチック片を収集すると共に、残りの廃プラスチック片を前記第２の系統へ供給し、
    　前記第２の系統では、前記残りの廃プラスチック片の中から第２の材質の廃プラスチック片を収集する、
    請求項８に記載の廃プラスチックの材質判定装置。     In the first system, waste plastic pieces of the first material are collected, and the remaining waste plastic pieces are supplied to the second system.
    In the second system, waste plastic pieces of the second material are collected from the remaining waste plastic pieces.
    The material determination device for waste plastic according to claim 8.
  11. 　前記第１の系統では、第１の材質と微量の他の材質の廃プラスチック片を収集すると共に、前記収集した廃プラスチック片を前記第２の系統へ供給し、
    　前記第２の系統では、前記第１の材質と微量の他の材質の廃プラスチック片の中から第１の材質の廃プラスチック片を収集する、
    請求項８に記載の廃プラスチックの材質判定装置。     In the first system, waste plastic pieces of the first material and a trace amount of other materials are collected, and the collected waste plastic pieces are supplied to the second system.
    In the second system, the waste plastic piece of the first material is collected from the waste plastic pieces of the first material and a trace amount of other materials.
    The material determination device for waste plastic according to claim 8.
  12. 　前記第１の系統では、第１の材質と微量の他の材質の廃プラスチック片を除外すると共に、前記除外した残りの廃プラスチック片を前記第２の系統へ供給し、
    　前記第２の系統では、前記他の廃プラスチック片の中からさらに前記第１の材質と微量の他の材質の廃プラスチック片を除外して、前記第１の材質を含まない廃プラスチック片を収集する、
    請求項８に記載の廃プラスチックの材質判定装置。     In the first system, waste plastic pieces of the first material and a trace amount of other materials are excluded, and the remaining excluded waste plastic pieces are supplied to the second system.
    In the second system, the waste plastic pieces of the first material and a trace amount of other materials are further excluded from the other waste plastic pieces, and the waste plastic pieces not containing the first material are collected. do,
    The material determination device for waste plastic according to claim 8.
  13. 　廃プラスチックの材質判定方法であって、
    　搬送路上で搬送される廃プラスチック片に光を照射する照射ステップと、
    　前記照射ステップにて照射された光の反射光を受光して前記反射光のスペクトルを検出する反射スペクトル検出ステップと、
    　前記反射スペクトル検出ステップにて検出された前記スペクトルが前記廃プラスチック片及び前記搬送路のどちらかのものかを判定する第１判定ステップと、
    　前記第１判定ステップにて前記廃プラスチック片と判定されたスペクトルから特徴量を抽出する第２判定ステップと、
    　前記第２判定ステップにて抽出された前記特徴量に基づき前記廃プラスチック片の材質を判別する第３判定ステップと、
    を含む廃プラスチックの材質判定方法。     It is a method for determining the material of waste plastic.
    An irradiation step that irradiates a piece of waste plastic transported on a transport path with light,
    A reflection spectrum detection step that receives the reflected light of the light irradiated in the irradiation step and detects the spectrum of the reflected light, and a reflection spectrum detection step.
    A first determination step for determining whether the spectrum detected in the reflection spectrum detection step is for either the waste plastic piece or the transport path, and
    A second determination step of extracting a feature amount from a spectrum determined to be the waste plastic piece in the first determination step,
    A third determination step of determining the material of the waste plastic piece based on the feature amount extracted in the second determination step, and
    Method for determining the material of waste plastic including.
  14. 　廃プラスチックの材質判定プログラムであって、
    　搬送路上で搬送される廃プラスチック片に光を照射する照射機能と、
    　前記照射機能により照射された光の反射光を受光して前記反射光のスペクトルを検出する反射スペクトル検出機能と、
    　前記反射スペクトル検出機能により検出された前記スペクトルが前記廃プラスチック片及び前記搬送路のどちらかのものかを判定する第１判定機能と、
    　前記第１判定機能により前記廃プラスチック片と判定されたスペクトルから特徴量を抽出する第２判定機能と、
    　前記第２判定機能により抽出された前記特徴量に基づき前記廃プラスチック片の材質を判別する第３判定機能と、
    をコンピュータに実現させる廃プラスチックの材質判定プログラム。     It is a material judgment program for waste plastics.
    Irradiation function that irradiates waste plastic pieces transported on the transport path with light,
    A reflection spectrum detection function that receives the reflected light of the light irradiated by the irradiation function and detects the spectrum of the reflected light, and a reflection spectrum detection function.
    A first determination function for determining whether the spectrum detected by the reflection spectrum detection function is either the waste plastic piece or the transport path, and
    A second determination function for extracting a feature amount from a spectrum determined to be the waste plastic piece by the first determination function, and
    A third determination function that determines the material of the waste plastic piece based on the feature amount extracted by the second determination function, and
    A waste plastic material judgment program that makes a computer realize.
PCT/JP2021/002624 2020-02-13 2021-01-26 Waste plastic material determination device, material determination method, and material determination program WO2021161779A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
KR1020227023966A KR20220137627A (en) 2020-02-13 2021-01-26 Waste plastic material determination device, material determination method, and material determination program
CN202180011546.5A CN115003425A (en) 2020-02-13 2021-01-26 Waste plastic material determination device, material determination method, and material determination program

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020022811A JP7419093B2 (en) 2020-02-13 2020-02-13 Waste plastic sorting equipment, sorting method, and sorting program
JP2020-022811 2020-02-13

Publications (1)

Publication Number Publication Date
WO2021161779A1 true WO2021161779A1 (en) 2021-08-19

Family

ID=77292398

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/002624 WO2021161779A1 (en) 2020-02-13 2021-01-26 Waste plastic material determination device, material determination method, and material determination program

Country Status (5)

Country Link
JP (1) JP7419093B2 (en)
KR (1) KR20220137627A (en)
CN (1) CN115003425A (en)
TW (1) TW202136744A (en)
WO (1) WO2021161779A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20230364652A1 (en) * 2022-05-12 2023-11-16 Canon Kabushiki Kaisha Sorting apparatus for sorting objects and measurementapparatus

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005249624A (en) * 2004-03-05 2005-09-15 Japan Science & Technology Agency Polymer group discriminating method by optical spectrum
JP2009191375A (en) * 2008-02-12 2009-08-27 Kaneka Corp Method for producing nonwoven fabric of synthetic fiber, and apparatus for sorting cloth-shaped and/or cottony fiber
JP2016080402A (en) * 2014-10-10 2016-05-16 キヤノン株式会社 Learning device, learning method and program
JP2016091359A (en) * 2014-11-06 2016-05-23 株式会社リコー Information processing system, information processing device, information processing method, and program
JP2019086412A (en) * 2017-11-07 2019-06-06 大日本印刷株式会社 Inspection system, inspection method and method for manufacturing inspection system
US20190218362A1 (en) * 2018-01-12 2019-07-18 Tyton Biosciences, Llc Methods for recycling cotton and polyester fibers from waste textiles
JP2019211208A (en) * 2018-05-30 2019-12-12 大王製紙株式会社 Processing method and processing system for waste paper packaging products including contraindicated items
JP2020003419A (en) * 2018-06-29 2020-01-09 株式会社リコー Spectral characteristic acquisition device, image forming apparatus, and management system for image forming apparatus

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5367145B1 (en) 2012-12-10 2013-12-11 ダイオーエンジニアリング株式会社 Black waste plastic material sorting device
JP5920236B2 (en) 2013-02-05 2016-05-18 東洋ライス株式会社 Color sorter and color sort method
JP6528665B2 (en) 2015-12-08 2019-06-12 株式会社島津製作所 Sample identification method and sample identification device
JP2018100903A (en) 2016-12-20 2018-06-28 パナソニックＩｐマネジメント株式会社 Resin determination method and apparatus
JP6880909B2 (en) 2017-03-28 2021-06-02 宇部興産株式会社 How to Sort Carbon Fiber Reinforced Composites from Waste Plastic Mixtures
JP6987698B2 (en) 2018-05-21 2022-01-05 大王製紙株式会社 Sorting equipment, sorting methods and programs, and computer-readable recording media

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005249624A (en) * 2004-03-05 2005-09-15 Japan Science & Technology Agency Polymer group discriminating method by optical spectrum
JP2009191375A (en) * 2008-02-12 2009-08-27 Kaneka Corp Method for producing nonwoven fabric of synthetic fiber, and apparatus for sorting cloth-shaped and/or cottony fiber
JP2016080402A (en) * 2014-10-10 2016-05-16 キヤノン株式会社 Learning device, learning method and program
JP2016091359A (en) * 2014-11-06 2016-05-23 株式会社リコー Information processing system, information processing device, information processing method, and program
JP2019086412A (en) * 2017-11-07 2019-06-06 大日本印刷株式会社 Inspection system, inspection method and method for manufacturing inspection system
US20190218362A1 (en) * 2018-01-12 2019-07-18 Tyton Biosciences, Llc Methods for recycling cotton and polyester fibers from waste textiles
JP2019211208A (en) * 2018-05-30 2019-12-12 大王製紙株式会社 Processing method and processing system for waste paper packaging products including contraindicated items
JP2020003419A (en) * 2018-06-29 2020-01-09 株式会社リコー Spectral characteristic acquisition device, image forming apparatus, and management system for image forming apparatus

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20230364652A1 (en) * 2022-05-12 2023-11-16 Canon Kabushiki Kaisha Sorting apparatus for sorting objects and measurementapparatus

Also Published As

Publication number Publication date
KR20220137627A (en) 2022-10-12
JP2021128062A (en) 2021-09-02
TW202136744A (en) 2021-10-01
CN115003425A (en) 2022-09-02
JP7419093B2 (en) 2024-01-22

Similar Documents

Publication Publication Date Title
Rozenstein et al. Development of a new approach based on midwave infrared spectroscopy for post-consumer black plastic waste sorting in the recycling industry
US11313869B2 (en) Methods and apparatus for determining label count during specimen characterization
US10861145B2 (en) Defect inspection device and defect inspection method
US9897560B2 (en) Screening of electronic components for detection of counterfeit articles using automated inspection system
US6879392B2 (en) Method and apparatus for inspecting defects
KR101019650B1 (en) Different-kind-of-object detector employing plane spectrometer
CN108738338A (en) Method and apparatus for detecting the chaff interferent in sample
WO2013138611A1 (en) Process and apparatus for measuring the crystal fraction of crystalline silicon casted mono wafers
EP3801934A1 (en) Process and system for in-line inspection of product stream for detection of foreign objects
WO2021161779A1 (en) Waste plastic material determination device, material determination method, and material determination program
JP6295798B2 (en) Inspection method
KR101298109B1 (en) Apparatus for color discrimination in visible light band and plastic classification system using thereof
JP2011226821A (en) Identification device and identification method
US20150371107A1 (en) Material classification using brdf feature vector
WO2021161770A1 (en) Material determination device for waste plastics
JP2015040818A (en) Method and apparatus for grain classification
Chao et al. Fast line-scan imaging system for broiler carcass inspection
KR20230099007A (en) Apparatus for sorting waste plastic and sorting maethod using the same
KR102352310B1 (en) System and method for determining a material of an object
US6624417B1 (en) Apparatus and method for judging plastic
WO2023007824A1 (en) Sorting device for waste plastic, and method for sorting waste plastic
de Lima Ribeiro et al. Multi-sensor characterization for an improved identification of polymers in WEEE recycling
KR20220077987A (en) Deep learning-based recyclables classification method
CN107192723B (en) Device and method for determining object to be inspected using X-ray
WO2023017639A1 (en) Sorting system for waste plastic and sorting method for waste plastic

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21754107

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21754107

Country of ref document: EP

Kind code of ref document: A1