Sorting system

Abstract

The sorting processing system according to the present disclosure includes a first detection unit configured to acquire first raw material information, a second detection unit configured to acquire second raw material information, a calculation unit configured to have an analysis model that outputs a set value related to a sorting condition, and a control unit configured to change the sorting condition of a sorting device, wherein the calculation unit processes the first raw material information at a first processing cycle, processes the second raw material information at a second processing cycle longer than the first processing cycle, and switches between a first analysis method in which the first raw material information is input to the analysis model to output the set value and a second analysis method in which at least the second raw material information is input to the analysis model to output the set value.

Description

Technical Field

[0001] This disclosure relates to a sorting and processing system. Background Technology

[0002] Patent Document 1 discloses a technique for sorting mixtures of plastic sheets and the like. In such sorting, the raw material composition ratio or specific charge and other raw material states are detected, and sorting conditions are determined based on the results.

[0003] Patent Document 1: International Publication No. 2012 / 101874 Summary of the Invention

[0004] The problem the invention aims to solve

[0005] The state of raw materials can change over time. To account for such changes, the state of the raw materials is acquired at regular time intervals. In structures that detect the state of multiple types of raw materials, the period for acquiring the data needed to determine sorting conditions sometimes varies depending on the state of the raw materials. In this case, how to use the states of multiple types of raw materials acquired at different periods to determine the sorting conditions will affect the sorting accuracy.

[0006] In view of the above, the purpose of this disclosure is to provide a sorting system that can ensure sorting accuracy in a structure that acquires the states of multiple types of raw materials at different cycles.

[0007] Solution for solving the problem

[0008] One aspect of the sorting system disclosed herein includes: a sorting device for sorting a mixture containing multiple types of objects according to the types of objects; a first detection unit for acquiring first raw material information related to the mixture fed into the sorting device; a second detection unit for acquiring second raw material information related to the mixture fed into the sorting device and of a different type from the first raw material information; a calculation unit for outputting an analytical model that outputs a set value related to the sorting conditions of the sorting device; and a control unit for changing the sorting conditions of the sorting device based on the set value output by the calculation unit. The calculation unit processes the first raw material information for a first processing cycle and processes the second raw material information for a second processing cycle longer than the first processing cycle. The calculation unit switches between a first analytical method and a second analytical method. In the first analytical method, the first raw material information is input into the analytical model to output the set value. In the second analytical method, at least the second raw material information is input into the analytical model to output the set value.

[0009] The effects of the invention

[0010] According to the sorting and processing system disclosed herein, sorting accuracy can be ensured in a structure that acquires the state of multiple types of raw materials at different cycles. Attached Figure Description

[0011] Figure 1 This is a diagram illustrating a structural example of the sorting processing system in Implementation Method 1.

[0012] Figure 2 It means Figure 1 The diagram shows an example of the structure of the first and second detection units.

[0013] Figure 3 This is a diagram illustrating the method of obtaining the raw material composition ratio using HSI data from a hyperspectral camera.

[0014] Figure 4 This is a diagram illustrating the first and second analytical methods. Detailed Implementation

[0015] Implementation method 1.

[0016] Hereinafter, embodiments of the present disclosure will be described with reference to the figures. Furthermore, the scope of the present disclosure is not limited to the following embodiments, and modifications can be made arbitrarily within the scope of the technical concept of the present disclosure. Figure 1 This is a structural diagram illustrating the sorting processing system 1 in Embodiment 1. The sorting processing system 1 includes a first detection unit 11, a sorting device 12, a calculation unit 13, a control unit 14, and a second detection unit 21.

[0017] The sorting system 1 is configured to sort a mixture containing multiple types of objects according to the type of object. In this embodiment, a group P of plastic sheets will be used as an example to illustrate "a mixture containing multiple types of objects". Figure 1 In the example, the plastic sheet group P contains two types of plastic sheets p1 and p2 with different materials. In this specification, the materials of plastic sheets p1 and p2 are sometimes not distinguished and they are referred to as "sheets". The plastic sheet group P may also contain more than three types of plastic sheets.

[0018] The following explanation uses the case where plastic sheet p1 is ABS and plastic sheet p2 is PS as an example. Plastic sheets p1 and p2 are obtained, for example, by crushing the casing of a household appliance using a shredder and then drying it. Plastic sheets p1 and p2 are, for example, formed to a size of approximately 10mm square.

[0019] The sorting device 12 sorts the plastic sheets p1 and p2 according to their type using electrostatic sorting. Figure 1In the example, the sorting device 12 includes an input section 121, a flashlight 122, a vibrating feeder 123, a first electrode 124, a second electrode 125, a DC power supply 126, a recycling bin 127, and separator plates 128 and 129. However, Figure 1 The structure of the sorting device 12 is just one example and can be changed.

[0020] The sorting device 12 can electrostatically separate a group of plastic sheets P, which consists of multiple types of plastic sheets p1 and p2 with different electrical properties, into plastic sheets p1 and plastic sheets p2.

[0021] The feeding unit 121 includes a hopper 121a and a feeding feeder 121b. Dried plastic sheets P are supplied to the hopper 121a. The hopper 121a supplies a predetermined amount of plastic sheets P to the feeding feeder 121b per unit time. The feeding feeder 121b supplies the plastic sheets P fed from the hopper 121a into the flashlight 122.

[0022] The charged cylinder 122 and the vibrating feeder 123 constitute the charged section. The charged section charges the plastic sheets p1 and p2 respectively and causes them to fall. Specifically, the charged cylinder 122 agitates the group of plastic sheets P by rotating. Inside the charged cylinder 122, the various types of plastic sheets p1 and p2 mixed in the group of plastic sheets P become charged through mutual friction. The charged plastic sheets p1 and p2 each have a charge amount of polarity (positive or negative) corresponding to the triboelectric charging sequence. In this example, the plastic sheet p1, which is ABS, is positively charged, and the plastic sheet p2, which is PS, is negatively charged.

[0023] Charged plastic sheets p1 and p2 are supplied to the rear end of the upper surface of the vibrating feeder 123. The positively charged plastic sheet p1 and the negatively charged plastic sheet p2 attract each other due to electrostatic force and pair up. The vibrating feeder 123 pushes the plastic sheets p1 and p2 forward while vibrating them up and down. As a result, the pairing of plastic sheets p1 and p2 is released, and they travel along the X direction in the figure. Additionally, the plastic sheets p1 and p2 fall from the vibrating feeder 123.

[0024] Electrodes 124 and 125 and a DC power supply 126 constitute an electric field generating unit. The electric field generating unit applies an electrostatic field to each charged plastic sheet, causing each plastic sheet to fall to a position corresponding to its charged state. Specifically, electrodes 124 and 125 are formed in a plate shape. Electrodes 124 and 125 are arranged in the X direction in the figure, facing each other so as to sandwich the paths of the falling plastic sheets p1 and p2. A ground voltage GND is applied to the first electrode 124. The DC power supply 126 applies a predetermined DC voltage between the first electrode 124 and the second electrode 125, generating an electrostatic field between them.

[0025] When the vibrating feeder 123 releases the paired plastic sheets p1 and p2 and they fall between electrodes 124 and 125, each sheet is drawn towards either electrode 124 or electrode 125 due to electrostatic forces corresponding to its charged state (polarity, charge). In other words, each sheet p1 and p2 traces a parabolic trajectory corresponding to its charged state and falls at different positions. In this example, sheet p1 is positively charged and therefore falls on the side of the first electrode 124. On the other hand, sheet p2 is negatively charged and therefore falls on the side of the second electrode 125.

[0026] A recycling bin 127 is positioned below electrodes 124 and 125 to collect plastic sheets p1 and p2 that fall from the vibrating feeder 123 between electrodes 124 and 125. The recycling bin 127 is rectangular in shape with an opening at the top. The opening of the recycling bin 127 is rectangular in shape, with its long side facing the X direction in the figure.

[0027] The partition plates 128 and 129 are also referred to as partition members. The partition plates 128 and 129 are arranged parallel to the YZ plane in the figure within the recycling bin 127, and are configured to be movable along the X direction in the figure. The X-direction position of each of the partition plates 128 and 129 is controlled by the control unit 14. The partition plate 128 is located on the side of the first electrode 124, and the partition plate 129 is located on the side of the second electrode 125. The recycling bin 127 is divided by the partition plates 128 and 129 into a recycling chamber 127a on the side of the first electrode 124, a recycling chamber 127b on the side of the second electrode 125, and an intermediate recycling chamber 127c.

[0028] The plastic sheets p1 and p2 that fall from the vibrating feeder 123 between electrodes 124 and 125 are recycled to any one of the three recycling chambers 127a to 127c according to their charged state. In this example, plastic sheet p1 is positively charged and is therefore recycled to recycling chamber 127a. On the other hand, plastic sheet p2 is negatively charged and is therefore recycled to recycling chamber 127b. Plastic sheets p1 and p2 that are not sufficiently charged are recycled to recycling chamber 127c.

[0029] Plastic sheet p1, which is recycled to recycling chamber 127a, plastic sheet p2, which is recycled to recycling chamber 127b, and plastic sheets p1 and p2, which are recycled to recycling chamber 127c, are transported by a conveyor (not shown) and housed in their respective containers.

[0030] The first detection unit 11 acquires information about a first raw material. This first raw material information may be, for example, the raw material composition ratio. When acquiring the raw material composition ratio, the first detection unit 11 may include, for example, [missing information - likely a specific feature or function]. Figure 2The hyperspectral camera 11a and processing unit 11b are shown. The hyperspectral camera 11a captures images of the plastic sheet group P flowing on the vibrating feeder 123 in a line scan manner. The hyperspectral camera 11a performs a line scan of the plastic sheet group P, which is conveyed by the vibrating feeder 123 at a constant speed, for example, at about 500 fps.

[0031] The hyperspectral camera 11a disperses light emitted from various points of the plastic sheet group P, which is the subject, and captures it on a sensor surface. Multiple pixels are arranged on the sensor surface, each capturing light of a different wavelength. The hyperspectral camera 11a outputs HSI data based on the intensity of light at each wavelength. HSI is short for hyperspectral imaging. The HSI data contains spectral information in the near-infrared region for each pixel.

[0032] Figure 3 An example is shown of obtaining the raw material composition ratio using HSI data from a hyperspectral camera 11a. For example... Figure 3 As shown in (A), the HSI data contains spectral information for each pixel associated with the shape of the sheet on the vibrating feeder 123. Points (i) and (ii) are a portion of the sheet, and point (iii) is a portion of the vibrating feeder 123. Figure 3 (A1) shows the spectrum of each pixel at points (i) to (iii). Figure 3 In the various curves of (A1), for example, the horizontal axis represents wavelength and the vertical axis represents the intensity of each wavelength.

[0033] The processing unit 11b of the first detection unit 11 processes the HSI data generated by the hyperspectral camera 11a. The processing unit 11b analyzes the HSI data and generates an image that distinguishes the thin sheets contained in the plastic sheet group P by color according to the material of the plastic. Figure 3 (B) is a Figure 3 An example of an image generated by parsing the HSI data of (A). Figure 3 In image (B), the slice containing point (i) is shown in red, and the slice containing point (ii) is shown in blue. Figure 3 In image (B), for example, the red sheet is plastic sheet p1, and the blue sheet is plastic sheet p2. Further, the processing unit 11b performs image analysis, calculates the area ratio of each color, and converts it into a raw material composition ratio. Figure 3 In example (B), the ratio of the area of ​​the red region to the area of ​​the blue region is 60:40. Therefore, it can be determined that the raw material composition ratio of plastic sheet p1 is 60% and that of plastic sheet p2 is 40%. In this way, the first detection unit 11 sequentially measures the raw material composition ratio of the group of plastic sheets P conveyed by the vibrating feeder 123 in a line scanning manner.

[0034] The second detection unit 21 acquires information about a second material that is different from the information about the first material. This second material information may be, for example, specific charge. When acquiring specific charge, the second detection unit 21 may include, for example, [details omitted]. Figure 2 The charge sensor 21a and weight sensor 21b are shown. Specifically, each sheet conveyed on the vibrating feeder 123 is picked up individually, and the charge and weight are measured using the charge sensor 21a and weight sensor 21b. By dividing the charge by the weight, the specific charge of the sheet can be determined.

[0035] The first detection unit 11 inputs the acquired first raw material information to the calculation unit 13. The second detection unit 21 inputs the acquired second raw material information to the calculation unit 13. The calculation unit 13 has an analytical model that outputs set values ​​related to the sorting conditions of the sorting device 12. This analytical model analyzes the set values ​​of the sorting conditions in a way that achieves optimal sorting accuracy, based on at least one of the first and second raw material information. The analytical model of the calculation unit 13 may, for example, use multiple regression analysis. Alternatively, the analytical model of the calculation unit 13 may use machine learning. These analytical models analyze based on a combination of past raw material information, set values ​​of sorting conditions, and sorting accuracy, and output set values ​​of sorting conditions suitable for the current raw material information.

[0036] The setting values ​​for the sorting conditions, which are the analysis results of the calculation unit 13, are input to the control unit 14. The control unit 14 controls the sorting conditions of the sorting device 12 based on the setting values ​​input from the calculation unit 13. For example, the control unit 14 may also control the position of the separators 128 and 129 in the X direction. Alternatively, the control unit 14 may also control the rotational speed or tilt of the flashlight 122, the voltage applied by the DC power supply 126 to the second electrode 125, etc. In other words, the "setting values" refer to the position of the separators 128 and 129 in the X direction, the rotational speed or tilt of the flashlight 122, the voltage of the DC power supply 126, etc. The "setting values" may also include multiple parameters.

[0037] Here, the arithmetic unit 13 processes the first raw material information acquired by the first detection unit 11 based on a "first processing cycle." Additionally, the arithmetic unit 13 processes the second raw material information acquired by the second detection unit 21 based on a "second processing cycle." The first and second processing cycles are determined based on the required data volume for the first and second raw material information. The "required data volume" refers to the amount of first and second raw material information data required by the arithmetic unit 13 to analyze the set values ​​of the sorting conditions. The required data volume is determined based on the deviation between the measured data of the first and second raw material information. The greater the deviation in the measured data, the greater the required data volume is needed to ensure sorting accuracy.

[0038] As an example, when the sorting conditions are set based on the raw material composition ratio, a data volume of 500 flakes is required to ensure sorting accuracy. In online scanning, for example, the raw material composition ratio of 1000 flakes can be acquired in 1 minute. In this example, the cycle for obtaining the required data volume, i.e., the "raw material composition ratio of 500 flakes," is 30 seconds. Therefore, the "first processing cycle" in this example is 30 seconds.

[0039] As an example, when the sorting conditions are set based on specific charge, a data volume of 200 flakes is required to ensure sorting accuracy. In the acquisition method, for example, the specific charge of 10 flakes can be acquired per minute. In this example, the cycle for obtaining the required data volume, i.e., the specific charge of 200 flakes, is 20 minutes. Therefore, the "second processing cycle" in this example is 20 minutes.

[0040] As described above, the first and second raw material information contain measurement data for multiple sheets. The calculation unit 13 performs statistical processing on these measurement data to obtain statistical values ​​such as average or median. The calculation unit 13 inputs such statistical values ​​into the analytical model and outputs the set values ​​of the sorting conditions. Furthermore, the specific values ​​of the first processing cycle, the second processing cycle, the required data volume, etc., described above are merely examples and can be changed. However, in this disclosure, the first processing cycle is shorter than the second processing cycle.

[0041] Here, the first raw material information has the advantage of being easily detectable even when there are fluctuations in the input mixture due to the short first processing cycle. A "fluctuation point" refers, for example, to a change in the type of household appliances that are the source of the mixture input into the sorting device 12. Imagine that the first and second raw material information change significantly before and after a fluctuation point. Because the second processing cycle is long, the second raw material information is likely to contain data from before and after the fluctuation point. It is argued that if the setting values ​​for the sorting conditions are determined based on this second raw material information containing data from before and after the fluctuation point, the sorting accuracy will decrease.

[0042] On the other hand, the raw material composition ratio, which serves as an example of first raw material information, has little correlation with sorting accuracy such as recovery rate and purity. However, the specific charge, which serves as an example of second raw material information, has a greater correlation with sorting accuracy compared to the raw material composition ratio. Therefore, by utilizing the second raw material information as much as possible to determine the setting values ​​of the sorting conditions, sorting accuracy can be further improved.

[0043] In view of the above, the arithmetic unit 13 in this embodiment is as follows: Figure 4 The parsing method when switching the output sorting condition settings as shown. Figure 4In the "first analytical method" shown in (b), the calculation unit 13 inputs the first raw material information into the analytical model without using the second raw material information, and outputs the set value of the sorting condition. Figure 4 In the "second analytical method" shown in (c), the calculation unit 13 inputs the first raw material information and the second raw material information into the analytical model and outputs the set value of the sorting condition.

[0044] Figure 4 (a) is an example of a graph that arranges the changes in the information of the first and second raw materials in a time series. Figure 4 In (a), the descriptions of the first and second raw material information represent statistical values ​​calculated according to their respective processing cycles, corresponding to the required data volume. In this example, "statistical value" refers to the average, but the median, etc., can also be used instead. Figure 4 In (a), the raw material composition ratio is exemplified as the first raw material information, and the specific charge is exemplified as the second raw material information. At time t1, the statistical value of the first raw material information corresponding to the required data amount is obtained, but the statistical value of the second raw material information corresponding to the required data amount is not obtained. Therefore, the arithmetic unit 13 outputs the set value of the sorting condition through the "first analysis method" during the period from time t1 to t2.

[0045] exist Figure 4 At time t2 (a), statistical values ​​of the second raw material information corresponding to the required data volume are obtained. Therefore, after time t2, when using both the first and second raw material information to output the set values ​​of the sorting conditions, it is highly likely to obtain more ideal sorting accuracy. Therefore, the arithmetic unit 13 outputs the set values ​​of the sorting conditions using the "second analytical method" during the period from time t2 to t3.

[0046] exist Figure 4 At time t3 (a), the value of the first raw material information changes significantly. Therefore, the calculation unit 13 can determine that time t3 is a "change point". For example, the calculation unit 13 can also compare the current statistical value of the first raw material information with the previous statistical value, and determine it as a "change point" when the difference exceeds a threshold. It is conceivable that before and after time t3, which is a change point, not only the first raw material information but also the second raw material information changes significantly. Therefore, after time t3, if statistical values ​​containing the second raw material information obtained before time t3 are used, it is highly likely that ideal sorting accuracy cannot be obtained. Therefore, the calculation unit 13 outputs the set value of the sorting conditions during the period from time t3 to t4 using the "first analysis method".

[0047] exist Figure 4At time t4 (a), statistical values ​​of the second raw material information corresponding to the required amount of data are obtained. However, the statistical values ​​of the second raw material information obtained at time t4 include the state of the mixture before the point of change. Therefore, the statistical values ​​of the second raw material information at time t4 may not accurately reflect the current state of the raw material. Therefore, the calculation unit 13 continues to use the "first analysis method" during the period from time t4 to t5.

[0048] exist Figure 4 At time t5 (a), the statistical value of the second raw material information is obtained. At least one second processing cycle has elapsed between time t5 and time t3, which is the point of change. Therefore, the statistical value of the second raw material information obtained at time t5 does not include the state of the mixture before the point of change. In other words, the reliability of the statistical value of the second raw material information at time t4 is low, while the reliability of the statistical value of the second raw material information at time t5 is high. Therefore, the calculation unit 13 outputs the set value of the sorting conditions after time t5 using the "second analysis method".

[0049] The calculation unit 13 then detects any changes based on the first raw material information. If a change is detected, the first analysis method is used until at least one second processing cycle has elapsed. After one second processing cycle following the change, the second analysis method is used. Thus, the calculation unit 13 can output the sorting condition setting value with high accuracy using both the first and second raw material information, while excluding the second raw material information where data before and after the change exists.

[0050] Furthermore, in the second analytical method, if a good and appropriate set value for the sorting conditions can be output using only the second raw material information, the first raw material information may not be used. In other words, in the second analytical method, at least the second raw material information is sufficient.

[0051] As described above, the sorting processing system 1 disclosed herein includes: a sorting device 12 for sorting a mixture containing multiple types of objects according to the type of objects; a first detection unit 11 for acquiring first raw material information related to the mixture fed into the sorting device 12; a second detection unit 21 for acquiring second raw material information related to the mixture fed into the sorting device 12 and of a different type from the first raw material information; a calculation unit 13 equipped with an analytical model that outputs a set value related to sorting conditions; and a control unit 14 for changing the sorting conditions of the sorting device 12 based on the set value output by the calculation unit 13. The calculation unit 13 processes the first raw material information according to a first processing cycle and processes the second raw material information according to a second processing cycle longer than the first processing cycle. The calculation unit 13 switches between a first analytical method and a second analytical method, in which the first analytical method inputs the first raw material information into the analytical model to output the set value, and in the second analytical method, at least the second raw material information is input into the analytical model to output the set value. According to the sorting and processing system 1, the sorting accuracy can be ensured by a structure in which statistical values ​​of the first raw material information and the second raw material information are obtained in different first and second processing cycles.

[0052] Furthermore, the arithmetic unit 13 can also detect the point of change in the state of the mixture fed into the sorting device 12 based on the first raw material information processed according to the first processing cycle, and output a set value using the first analytical method after the point of change until at least the second processing cycle has elapsed. According to this structure, it is possible to suppress the use of second raw material information containing data prior to the point of change to determine the set value of the sorting conditions. Therefore, it is possible to suppress the decrease in sorting accuracy at the point of change.

[0053] Alternatively, the first material information can be the material composition ratio of each material in the plastic sheet group P, and the first detection unit 11 can also include a hyperspectral camera 11a that captures images of the plastic sheet group P. In a structure that uses the hyperspectral camera 11a to detect the material composition ratio, for example, the material composition ratio of 1000 sheets can be acquired in 1 minute. Therefore, the material composition ratio can be preferably used as the first material information for detecting changes.

[0054] Furthermore, the scope of this disclosure is not limited to the described embodiments, and various modifications can be made without departing from the intent of this disclosure.

[0055] For example, in the described embodiment, a group of plastic sheets P is used as an example of a "mixture containing multiple types of objects" to be sorted by the sorting system 1. However, the sorting system 1 can also sort mixtures of objects other than plastic sheets. In this case, this disclosure also helps to solve the problem of ensuring sorting accuracy in a structure that acquires first material information and second material information in different first and second processing cycles.

[0056] Furthermore, in the described embodiment, it is explained that statistical values ​​(average values, etc.) of the first raw material information are input into the analytical model. However, it is not necessary to calculate the statistical values. For example, the detection data of the first detection unit 11 or the second detection unit 21 can be input into the analytical model as is, and the set values ​​of the sorting conditions can be output. In other words, "processing the first raw material information according to the first processing cycle" includes not only calculating the statistical values, but also inputting the first raw material information corresponding to the required data volume into the analytical model.

[0057] Furthermore, in the described embodiment, the raw material composition ratio is exemplified as the first raw material information, and the specific charge is exemplified as the second raw material information. Other examples include the amount of plastic sheet group P input, or the temperature and humidity of the environment in the sorting device 12. The second raw material information may be the moisture content in the sheet. Other types of first or second raw material information may also be used. The calculation unit 13 may also output setting values ​​for the sorting conditions based on three or more raw material information.

[0058] In other words, as a third type of raw material information, different from the first and second raw material information, information such as the amount of plastic sheet group P input, the temperature and humidity of the environment in the sorting device 12, and the moisture content of the sheets can also be used. In this case, Figure 4 In the first analytical method in (b), the information on the first raw material and the information on the third raw material can also be input into the analytical model. Figure 4 In the second analytical method in (c), the information of the first to third raw materials can also be input into the analytical model, or only the information of the second and third raw materials can be input into the analytical model.

[0059] Furthermore, the functions of the arithmetic unit 13, control unit 14, etc., are implemented by a processor such as a CPU (Central Processing Unit) executing programs stored in program memory. Some or all of these functions can be implemented using hardware such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), or FPGA (Field-Programmable Gate Array), or through a combination of software and hardware. The functions of the arithmetic unit 13 and the control unit 14 can also be implemented using the same hardware.

[0060] Furthermore, the above embodiments describe the sorting of plastic sheets by electrostatic separation. However, the sorting method is not limited; for example, it can be either gravity sorting or optical sorting. Gravity sorting refers to a sorting method that utilizes the phenomenon that the specific gravity of plastic sheets differs according to their type. For example, if the group of plastic sheets is vibrated or floated in a medium, the heavier plastic sheets will sink, and the lighter plastic sheets will rise.

[0061] Optical sorting is a sorting method that utilizes the reflectivity of light to differentiate between different types of plastic sheets. In optical sorting, a detection light is shone onto a group of plastic sheets, and the reflected light is detected. Various wavelengths of light, such as infrared or X-rays, can be used as the detection light. By detecting the spectrum of the reflected or Raman scattered light, the plastic sheets can be distinguished by type. Alternatively, after this initial sorting, the plastic sheets can be further sorted using methods such as blowing air.

[0062] In addition, the above-described embodiments or variations can be appropriately combined.

[0063] (Explanation of reference numerals in the attached image)

[0064] 1: Sorting and processing system; 11: First detection unit; 11a: Hyperspectral camera; 12: Sorting device; 13: Calculation unit; 14: Control unit; 21: Second detection unit; P: Plastic sheet group.

Claims

1. A sorting and processing system, comprising: The sorting device sorts a mixture containing multiple types of objects according to the type of objects. The first detection unit acquires first raw material information related to the mixture fed into the sorting device; The second detection unit acquires information about a second raw material that is different from the first raw material information and is related to the mixture fed into the sorting device. The arithmetic unit includes an analytical model that outputs set values ​​related to the sorting conditions of the sorting device; and The control unit, based on the set value output by the calculation unit, changes the sorting conditions of the sorting device. The computing unit processes the first raw material information according to a first processing cycle, and processes the second raw material information according to a second processing cycle that is longer than the first processing cycle. The calculation unit switches between a first analysis method and a second analysis method. In the first analysis method, the first raw material information is input into the analysis model to output the set value. In the second analysis method, at least the second raw material information is input into the analysis model to output the set value.

2. The sorting and processing system according to claim 1, wherein, The calculation unit detects the point of change in the state of the mixture fed into the sorting device based on the first raw material information processed according to the first processing cycle, and outputs the set value using the first analysis method after the point of change until at least the second processing cycle has elapsed.

3. The sorting and processing system according to claim 1 or 2, wherein, The sorting device sorts the mixture by electrostatic separation.

4. The sorting and processing system according to any one of claims 1 to 3, wherein, The mixture is a group of plastic sheets, and the object is made of plastic.

5. The sorting and processing system according to claim 4, wherein, The first raw material information is the raw material composition ratio of each material in the group of plastic sheets. The first detection unit has a hyperspectral camera that captures images of the plastic sheet group.

Images