Plastic sorting system based on multispectrum

Abstract

The invention discloses a multispectral-based plastic sorting system, which relates to the technical field of multispectral imaging, and comprises a light source, a to-be-detected material, a lens and a coating film sensing detector, and light intensity signals are converted into electric signals through a filter and a detector; the data acquisition and analysis module judges the components of the to-be-detected material by acquiring and analyzing the electric signal intensity of different coating film pixel areas converted by the detector; the data acquisition and analysis module comprises a reference value calibration unit, an effective pixel region defining unit and a data acquisition and analysis unit, wherein the reference value calibration unit is used for calibrating a reference value for distinguishing the signal intensity of a coating pixel region; the effective pixel region defining unit is used for defining the pixel position of an effective pixel region; the material result judging unit is used for judging the components of the material to be detected; and the sorting module is used for placing the identified components of the to-be-detected material into corresponding sorting boxes, high-precision identification and separation are carried out through multiple spectrums based on the spectral characteristics of substances, and the distinguishing precision is more precise.

Description

Technical Field

[0001] The invention relates to the technical field of multispectral imaging, and in particular to a plastic sorting system based on multispectrum. Background Art

[0002] PET and PVC are two common plastics in our daily life. Being able to correctly distinguish between PET and PVC in the recycling process has important environmental, safety and economic significance. Generally speaking, PET is more expensive and has more recycling value. At present, the methods used in industry to distinguish between PET and PVC mainly include multiple separation, melt separation, density separation and electrostatic separation. The above methods have the weaknesses of low precision, environmental pollution and low automation to varying degrees. Summary of the invention

[0003] Based on the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a plastic sorting system based on multi-spectrum to solve the above-mentioned technical problems.

[0004] To achieve the above object, the present invention provides the following technical solution: a plastic sorting system based on multi-spectrum, comprising: a light source, a material to be detected and a lens; characterized in that it also includes:

[0005] A film-coated sensor detector, used to convert light intensity signals into electrical signals of different intensities through filters and detector conversion, wherein the film-coated sensor detector includes a film-coated pixel area, a circuit driver, a photoelectric converter, an ADC and an operational amplifier;

[0006] A data acquisition and analysis module is used to determine the composition of the material to be detected by acquiring and analyzing the electrical signal strength of different coated pixel areas after the detector conversion. The data acquisition and analysis module includes a reference value calibration unit, an effective pixel area definition unit and a material result determination unit. The reference value calibration unit is used to calibrate the reference value used to distinguish the signal strength of the coated pixel area; the effective pixel area definition unit is used to define the pixel position of the effective pixel area; the material result determination unit is used to compare the mean value of the pixel position of the effective pixel area with the reference value to determine the composition of the material to be detected;

[0007] The sorting module is used to place the identified components of the material to be tested into corresponding sorting boxes.

[0008] The present invention is further configured such that the light source is a halogen tungsten lamp in the wavelength range of 350nm--2500nm.

[0009] The present invention is further configured as follows: in the coated sensor detector, the coated sensor is a bare Die chip that is not packaged, and the pixel area is set in the middle position of the bare Die chip. The size of the pixel area is 15mm*15mm, and the size of a single pixel is 15um*15um; there are 1000 pixels in each row, a total of 1000 rows, and a total of 1 million pixels, and all pixel areas need to be coated.

[0010] The present invention is further configured that the coating of the coated pixel area is provided with two band pass filters, which are named E and V respectively, wherein E is a band pass filter of the 1180nm-1220nm frequency band, and V is a band pass filter of the 1580nm-1670nm frequency band, and the E and V of each row are arranged in odd and even crosses, and E is in an odd position, and V is in an even position. E and V occupy 50% of the total pixels respectively, and the band pass spectrum filter parameters of E are set as follows: band pass frequency: 1180nm-1220nm, center frequency 1190nm, band pass spectrum band transmittance:>92%, the spectrum bands less than 1180nm and greater than 1220nm are cut off, and the cut off depth is 8%; the band pass spectrum filter parameters of V are set as follows: band pass frequency: 1580nm-1670nm, center frequency 1660nm, band pass spectrum band transmittance:>92%, the spectrum bands less than 1580nm and greater than 1670nm are cut off, and the cut off depth is 8%.

[0011] The present invention is further configured such that the calibration logic of the reference value calibration unit includes:

[0012] Select PET as the material to be detected, place the PET material to be detected in the imaging area of ​​the lens, record the average values ​​of 1024 pixels in the E area and the V area respectively, record them as ave_e1 and ave_v1, select the middle value of ave_e1 and ave_v1 as the reference value, that is, (ave_v1+ave_e1) / 2, and record this reference value as ref1;

[0013] Select PVC as the material to be detected, and place the PVC material to be detected in the imaging area of ​​the lens, record the average values ​​of 1024 pixels in area E and area V respectively, recorded as ave_e2 and ave_v2, and select the middle value of ave_e2 and ave_v2 as the reference value, that is, (ave_v2+ave_e2) / 2, and record this reference value as ref2.

[0014] The present invention is further configured such that the definition logic of the effective pixel area definition unit includes:

[0015] Select ref1 as the effective reference value, start from the pixel coordinate position (0 0), compare each pixel data with the effective reference value ref1 in turn from left to right and from bottom to top, and mark the parity of the currently compared pixel position. When the comparison value changes from positive to negative, the corresponding pixel position is defined as the beginning of the effective pixel area. In order to eliminate misjudgment caused by interference, when the corresponding pixel position has 10 consecutive E zone or V zone data smaller than the effective reference value ref1, the pixel position is defined as the beginning of the effective area.

[0016] According to the arrangement rule of the coated pixel area and the parity of the pixel position in this row, determine whether the beginning of the effective position is the E zone or the V zone, find out 1024 effective imaging pixels in the E zone and the V zone respectively, and calculate the average value of the 1024 effective imaging pixels as the final effective intensity value.

[0017] The present invention is further configured such that the determination logic of the material result determination unit includes:

[0018] Select a suitable reference value from ref1 and ref2, wherein if the average value of 10 consecutive data in the effective imaging area of ​​area E is less than that of area V, then select the comparison reference value ref1; otherwise select the comparison reference value ref2;

[0019] The 1024 average values ​​of the effective pixel areas E and V are compared with the selected reference values ​​respectively. There are three comparison results: when the mean value of the E area is less than the reference value and the mean value of the V area is greater than the reference value, it means that the spectrum near 1190nm is absorbed, and the material to be detected is determined to be PET; when the mean value of the E area is greater than the reference value and the mean value of the V area is less than the reference value, it means that the spectrum near 1660nm is absorbed, and the material to be detected is determined to be PVC; in any other case, it is determined that the material to be detected is neither PVT nor PET.

[0020] The present invention provides a plastic sorting system based on multi-spectrum, comprising a light source, a material to be detected and a lens; a coating sensor detector, which is used to convert a light intensity signal into an electrical signal of different intensities through a filter and a detector conversion, and the coating sensor detector comprises a coating pixel area, a circuit driver, a photoelectric converter, an ADC and an operational amplifier; a data acquisition and analysis module, which is used to determine the composition of the material to be detected by collecting and analyzing the electrical signal intensity of different coating pixel areas after the detector conversion, and the data acquisition and analysis module comprises a reference value calibration unit, an effective pixel area definition unit and a material result determination unit, and the reference value calibration unit is used to calibrate a reference value for distinguishing the strength of the signal of the coating pixel area; the effective pixel area definition unit is used to define the pixel position of the effective pixel area; the material result determination unit is used to compare the mean value of the pixel position of the effective pixel area with the reference value to determine the composition of the material to be detected; a sorting module is used to place the identified components of the material to be detected in a corresponding sorting box, and the beneficial effects produced include:

[0021] 1. With higher accuracy, multi-spectrum is based on the spectral characteristics of the material for high-precision identification and separation, thus having more precise distinction accuracy;

[0022] 2. It is more environmentally friendly. Compared with the traditional melting separation method and the complex separation method, the multi-spectral method does not require additional chemical reagents, thus reducing the pollution to the environment;

[0023] 3. With a higher degree of automation, multi-spectral sorting technology can realize an automated production process, reduce the interference of human operation, and improve the stability and consistency of separation.

[0024] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0026] Figure 1 A schematic structural diagram of a plastic sorting system based on multi-spectrum is shown as an exemplary embodiment of the present invention;

[0027] Figure 2A schematic diagram of the structure of a film-coated sensor detector is shown as an exemplary embodiment of the present invention;

[0028] Figure 3 A schematic structural diagram of an EV pixel arrangement is shown as an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0030] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0031] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0032] A plastic sorting system based on multi-spectrum, such as Figure 1 As shown, it includes: a light source, a material to be detected and a lens; and also includes:

[0033] A film-coated sensor detector, used to convert light intensity signals into electrical signals of different intensities through filters and detector conversion, wherein the film-coated sensor detector includes a film-coated pixel area, a circuit driver, a photoelectric converter, an ADC and an operational amplifier;

[0034] A data acquisition and analysis module is used to determine the composition of the material to be detected by acquiring and analyzing the electrical signal strength of different coated pixel areas after the detector conversion. The data acquisition and analysis module includes a reference value calibration unit, an effective pixel area definition unit and a material result determination unit. The reference value calibration unit is used to calibrate the reference value used to distinguish the signal strength of the coated pixel area; the effective pixel area definition unit is used to define the pixel position of the effective pixel area; the material result determination unit is used to compare the mean value of the pixel position of the effective pixel area with the reference value to determine the composition of the material to be detected;

[0035] The sorting module is used to place the identified components of the material to be tested into corresponding sorting boxes.

[0036] Specifically, multispectral imaging technology can obtain spectral information of multiple frequency bands on the surface of an object, and can provide rich and detailed object features. Its technical principle mainly relies on the different absorption, reflection and scattering characteristics of different substances to different wavelengths of light. According to the unique spectral characteristics of each substance, these spectral characteristics are collected and analyzed to identify and analyze the composition and state of the substance.

[0037] Multispectral imaging systems usually consist of three parts: light source, imaging equipment and data processing system. The imaging equipment is responsible for collecting spectral information of different bands, separating different spectra through spectral separators, and then converting these spectra into different electrical signals by photodetectors. Finally, the data processing system performs data analysis and interpretation on the electrical signals. Multispectral imaging can distinguish hundreds of independent spectral channels within a relatively wide spectral frequency band and obtain continuous spectral information of the object being photographed, so it can more accurately identify and analyze the chemical composition and physical state of the object.

[0038] Specifically, in order to improve the detection accuracy, the surface stains of the PET / PVC material to be inspected need to be removed in advance. When the light can pass through the object to be inspected, the coating sensor detector set at the rear receives the incident light and obtains the absorption spectrum of the object. When the light cannot pass through the object to be inspected, the coating sensor detectors set on both sides analyze the reflected light and obtain the absorption spectrum of the object.

[0039] The present invention is further configured such that the light source is a halogen tungsten lamp with a wavelength band of 350nm--2500nm. Specifically, since halogen tungsten lamps tend to be natural light sources, the light source uses a halogen tungsten lamp with a wavelength band of 350nm--2500nm.

[0040] This system extracts spectral signals within a specific frequency band and uses the spectral response curves of different materials to discriminate material properties in different bands. Signal extraction within a specific spectrum band is achieved through a coated sensor detector, that is, a filter film is coated on a single pixel area to allow only one wavelength of light, 1290nm or 1660nm, to pass through. Coated sensor detectors are an important part of plastic sorting systems, such as Figure 2 As shown, the present invention is further configured as follows: in the coated sensor detector, the coated sensor is a bare Die chip that is not packaged, the pixel area is set in the middle position of the bare Die chip, the size of the pixel area is 15mm*15mm, and the size of a single pixel is 15um*15um; there are 1000 pixels per row, 1000 rows in total, and 1 million pixels in total, and all pixel areas need to be coated.

[0041] This system detects two materials, PET and PVC. Since PET has weak absorption of spectral signals near the wavelength of 1190nm and strong absorption of spectral signals near the wavelength of 1660nm, PVC has strong absorption of spectral signals near the wavelength of 1190nm and weak absorption of spectral signals near the wavelength of 1660nm, therefore, Figure 3 As shown, the present invention is further configured such that the coating in the coated pixel area is provided with two frequency bands of bandpass filters, respectively named E and V, wherein E is a bandpass filter in the 1180nm-1220nm frequency band, and V is a bandpass filter in the 1580nm-1670nm frequency band, and E and V in each row are arranged in odd and even cross-arrangements, with E at odd positions and V at even positions. E and V occupy 50% of the total pixels respectively. The bandpass spectrum filter parameters of E are set as follows: bandpass frequency: 1180nm~1220nm, center frequency 1190nm, bandpass spectrum transmittance: >92%, the spectrum segments less than 1180nm and greater than 1220nm are cut off, and the cutoff depth is 8%; the bandpass spectrum filter parameters of V are set as follows: bandpass frequency: 1580nm-1670nm, center frequency 1660nm, bandpass spectrum transmittance: >92%, the spectrum segments less than 1580nm and greater than 1670nm are cut off, and the cutoff depth is 8%; further, the single pixel coating size requirements are:

[0042] The entire pixel area of ​​15um*15um is coated;

[0043] The accuracy of the pixel coating edge is required to be controlled within a positive deviation of 0.5um;

[0044] The edges of the coating between pixels can overlap, and no uncoated gaps should be left;

[0045] Coating material requirements:

[0046] Select magnesium fluoride, H4 (lanthanum titanate), tantalum pentoxide, and aluminum trioxide. The above materials can reduce the reflection of light, reduce halo, and have strong transmittance to light within 1000nm to 2000nm.

[0047] The data acquisition and analysis module collects and analyzes the data converted by the detector. The collected data may appear in three situations:

[0048] The signal in the E region is strong, and the signal in the V region is weak: this indicates that the spectrum near 1190nm is not absorbed, and PVC absorbs the spectrum near 1190nm weakly and absorbs the spectrum near 1660nm strongly, so it can be determined that the current material is PVC.

[0049] The signal in the E region is weak, and the signal in the V region is strong: this indicates that the spectrum near 1660nm is not absorbed, while PET has strong absorption of the spectrum near 1190nm and weak absorption of the spectrum near 1660nm, so it can be determined that the current material is PET.

[0050] There is no obvious difference in strength between the E area and the V area: no materials are currently placed or other materials are placed.

[0051] As mentioned above, the data acquisition and analysis module determines the composition of the material to be tested by analyzing the intensity of the signals in the E and V zones after acquisition. Correctly analyzing the signal intensity in the EV area is the key to accurate material detection. Therefore, the data acquisition and analysis module includes a reference value calibration unit, an effective pixel area definition unit and a material result determination unit.

[0052] The present invention is further configured such that the calibration logic of the reference value calibration unit includes:

[0053] Select PET as the material to be detected, place the PET material to be detected in the imaging area of ​​the lens, record the average values ​​of 1024 pixels in the E area and the V area respectively, record them as ave_e1 and ave_v1, select the middle value of ave_e1 and ave_v1 as the reference value, that is, (ave_v1+ave_e1) / 2, and record this reference value as ref1;

[0054] Select PVC as the material to be detected, and place the PVC material to be detected in the imaging area of ​​the lens, record the average values ​​of 1024 pixels in area E and area V respectively, recorded as ave_e2 and ave_v2, and select the middle value of ave_e2 and ave_v2 as the reference value, that is, (ave_v2+ave_e2) / 2, and record this reference value as ref2.

[0055] Specifically, after the halogen tungsten lamp light is transmitted or reflected by the PVC / PET material to be inspected, it is filtered by the coated sensor detector, and the spectral signal in the passband is converted into electrical signals of different intensities by the detector. Due to the differences in size and shape of the materials to be inspected, all pixel areas will be divided into three areas after imaging, namely the imaging area of ​​the non-material to be inspected, the imaging area E of the material to be inspected, and the imaging area V of the material to be inspected. A reasonable reference value is introduced, and the average values ​​of the three areas are compared with this reference value respectively. If it is less than the reference value, the signal intensity of the area is considered to be weak. If it is greater than the reference value, the signal intensity of the area is considered to be strong. The selection of reference values ​​should follow the following two principles: first, the reference value must be the actual sampling value for the PVT / PET detection scenario, and second, there must be a certain dynamic range, otherwise the anti-interference performance will be relatively poor. The reference value needs to be calibrated before formal use. The calibration method is as follows:

[0056] ①Select PET as the material to be tested, and place the material in all imaging areas of the camera, and record the average values ​​of 1024 pixels in area E and area V, respectively, and record them as ave_e1 and ave_v1. The reference value is the middle value of the two, that is, (ave_v1+ave_e1) / 2, and record this reference value as ref1.

[0057] ②Select PVC as the material to be sampled, and place the material in all imaging areas of the camera, and record the average values ​​of 1024 pixels in area E and area V, respectively, and record them as ave_e2 and ave_v2. Similarly, select the middle value (ave_v2+ave_e2) / 2 as the reference value, and record the reference value at this time as ref2.

[0058] The reason for selecting two reference values ​​is to avoid the influence of the filtering difference of the two bandpass filters on the reference value. For example, when the test material is PET, the average values ​​of the E zone and the V zone are 100 and 500 respectively, then the reference value is 300 and the dynamic range is 200; when the test material is PVC, the average values ​​of the E zone and the V zone are 600 and 200 respectively, then the reference value is 400 and the dynamic range is also 200. If the reference value is not distinguished and any one of them is used as the reference value, the dynamic range is only 100, which will increase the false detection rate.

[0059] The present invention is further configured such that the definition logic of the effective pixel area definition unit includes:

[0060] Select ref1 as the effective reference value, start from the pixel coordinate position (0 0), compare each pixel data with the effective reference value ref1 in turn from left to right and from bottom to top, and mark the parity of the currently compared pixel position. When the comparison value changes from positive to negative, the corresponding pixel position is defined as the beginning of the effective pixel area. In order to eliminate misjudgment caused by interference, when the corresponding pixel position has 10 consecutive E zone or V zone data smaller than the effective reference value ref1, the pixel position is defined as the beginning of the effective area.

[0061] According to the arrangement rule of the coated pixel area and the parity of the pixel position in this row, determine whether the beginning of the effective position is the E zone or the V zone, find out 1024 effective imaging pixels in the E zone and the V zone respectively, and calculate the average value of the 1024 effective imaging pixels as the final effective intensity value.

[0062] Specifically, due to the differences in shape and size of the materials to be inspected, the pixel imaging area is not entirely the imaging area of ​​the materials to be inspected. Only when the effective pixel area (i.e., the actual imaging area of ​​the materials to be inspected) is found can the effective pixel data be calculated. As mentioned above, the absorption center frequency of the conveyor belt (background area) to the spectrum is far away from 1190nm and 1660nm, so the signal in the invalid pixel area (non-material imaging area to be inspected) is stronger than that in the effective pixel area. First, select ref1 as the effective reference value. Starting from the position (0 0) of the pixel coordinate, we compare each pixel data with the reference value in turn from left to right and from bottom to top, and mark the odd and even of the pixel position currently compared. When the comparison value changes from positive to negative, the pixel position at this time is considered to be the beginning of the effective pixel area. In order to eliminate misjudgment caused by interference, this system believes that if the data of 10 consecutive E areas (odd positions) or V areas (even positions) at this pixel position are smaller than the reference value, then this pixel position is considered to be the beginning of the effective area. According to the arrangement rule of the pixel filter and the parity of the pixel position in this row, it can be determined whether the effective position starts in area E or area V. According to this method, 1024 effective imaging pixels in area E and area V are found respectively, and the average value of these 1024 pixels is calculated as the final effective intensity value of the area.

[0063] The present invention is further configured such that the determination logic of the material result determination unit includes:

[0064] Select a suitable reference value from ref1 and ref2, wherein if the average value of 10 consecutive data in the effective imaging area of ​​area E is less than that of area V, then select the comparison reference value ref1; otherwise select the comparison reference value ref2;

[0065] The 1024 average values ​​of the effective pixel areas E and V are compared with the selected reference values ​​respectively. There are three comparison results: when the mean value of the E area is less than the reference value and the mean value of the V area is greater than the reference value, it means that the spectrum near 1190nm is absorbed, and the material to be detected is determined to be PET; when the mean value of the E area is greater than the reference value and the mean value of the V area is less than the reference value, it means that the spectrum near 1660nm is absorbed, and the material to be detected is determined to be PVC; in any other case, it is determined that the material to be detected is neither PVT nor PET.

[0066] Specifically, the comparison of effective pixel data is carried out in two steps: the first step is a rough comparison, and a suitable reference value is selected from ref1 and ref2. If the average value of 10 consecutive data in the effective imaging area of ​​zone E is less than that of zone V, the comparison reference value ref1 is selected. Otherwise, the comparison reference value ref2 is selected. The second step is a detailed comparison, that is, the 1024 average values ​​of the effective pixel area EV are compared with the selected reference values ​​respectively. The comparison results should have three cases: when the mean value of zone E is less than the reference value and the mean value of zone V is greater than the reference value, it means that the spectrum near 1190nm is absorbed, and the material is PET. When the mean value of zone E is greater than the reference value and the mean value of zone V is less than the reference value, it means that the spectrum near 1660nm is absorbed, and the material is PVC. In any other case, it is judged that the material is not any of PVT and PET.

[0067] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0068] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0069] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0070] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0071] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0072] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0073] In the several embodiments provided in the present application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0074] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0075] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0076] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0077] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A plastic sorting system based on multi-spectrum, include: A light source, a material to be detected and a lens; characterized in that it also includes: A film-coated sensor detector, used to convert light intensity signals into electrical signals of different intensities through filters and detector conversion, wherein the film-coated sensor detector includes a film-coated pixel area, a circuit driver, a photoelectric converter, an ADC and an operational amplifier; A data acquisition and analysis module is used to determine the composition of the material to be detected by acquiring and analyzing the electrical signal strength of different coated pixel areas after the detector conversion. The data acquisition and analysis module includes a reference value calibration unit, an effective pixel area definition unit and a material result determination unit. The reference value calibration unit is used to calibrate the reference value used to distinguish the signal strength of the coated pixel area; the effective pixel area definition unit is used to define the pixel position of the effective pixel area; the material result determination unit is used to compare the mean value of the pixel position of the effective pixel area with the reference value to determine the composition of the material to be detected; The sorting module is used to place the identified components of the material to be tested into corresponding sorting boxes.

2. A plastic sorting system based on multi-spectrum according to claim 1, It is characterized in that The light source is a halogen tungsten lamp with a wavelength range of 350nm--2500nm.

3. A plastic sorting system based on multi-spectrum according to claim 1, It is characterized in that In the coated sensor detector, the coated sensor is a bare die chip that has not been packaged. The pixel area is set in the middle position of the bare die chip. The size of the pixel area is 15mm*15mm, and the size of a single pixel is 15um*15um. There are 1000 pixels in each row, 1000 rows in total, and 1 million pixels in total. All pixel areas need to be coated.

4. A plastic sorting system based on multi-spectrum according to claim 3, It is characterized in that The coating of the coated pixel area is provided with two bands of bandpass filters, named E and V, respectively, wherein E is a bandpass filter of the 1180nm-1220nm band, and V is a bandpass filter of the 1580nm-1670nm band. The E and V of each row are arranged in odd and even positions, and E is in odd positions and V is in even positions. E and V occupy 50% of the total pixels respectively, and the bandpass spectrum filter parameters of E are set as follows: bandpass frequency: 1180nm-1220nm, center frequency 1190nm, bandpass spectrum transmittance: >92%, the spectrum segments less than 1180nm and greater than 1220nm are cut off, and the cutoff depth is 8%; the bandpass spectrum filter parameters of V are set as follows: bandpass frequency: 1580nm-1670nm, center frequency 1660nm, bandpass spectrum transmittance: >92%, the spectrum segments less than 1580nm and greater than 1670nm are cut off, and the cutoff depth is 8%.

5. A plastic sorting system based on multi-spectrum according to claim 1, It is characterized in that The calibration logic of the reference value calibration unit includes: Select PET as the material to be detected, place the PET material to be detected in the imaging area of ​​the lens, record the average values ​​of 1024 pixels in the E area and the V area respectively, record them as ave_e1 and ave_v1, select the middle value of ave_e1 and ave_v1 as the reference value, that is, (ave_v1+ave_e1) / 2, and record this reference value as ref1; Select PVC as the material to be detected, and place the PVC material to be detected in the imaging area of ​​the lens, record the average values ​​of 1024 pixels in area E and area V respectively, recorded as ave_e2 and ave_v2, and select the middle value of ave_e2 and ave_v2 as the reference value, that is, (ave_v2+ave_e2) / 2, and record this reference value as ref2.

6. A plastic sorting system based on multi-spectrum according to claim 1, It is characterized in that The definition logic of the effective pixel area definition unit includes: Select ref1 as the effective reference value, start from the pixel coordinate position (0 0), compare each pixel data with the effective reference value ref1 in turn from left to right and from bottom to top, and mark the parity of the currently compared pixel position. When the comparison value changes from positive to negative, the corresponding pixel position is defined as the beginning of the effective pixel area. In order to eliminate misjudgment caused by interference, when the corresponding pixel position has 10 consecutive E zone or V zone data smaller than the effective reference value ref1, the pixel position is defined as the beginning of the effective area. According to the arrangement rule of the coated pixel area and the parity of the pixel position in this row, determine whether the beginning of the effective position is the E zone or the V zone, find out 1024 effective imaging pixels in the E zone and the V zone respectively, and calculate the average value of the 1024 effective imaging pixels as the final effective intensity value.

7. A plastic sorting system based on multi-spectrum according to claim 1, It is characterized in that The determination logic of the material result determination unit includes: Select a suitable reference value from ref1 and ref2, wherein if the average value of 10 consecutive data in the effective imaging area of ​​area E is less than that of area V, then select the comparison reference value ref1; otherwise select the comparison reference value ref2; The 1024 average values ​​of the effective pixel areas E and V are compared with the selected reference values ​​respectively. There are three comparison results: when the mean value of the E area is less than the reference value and the mean value of the V area is greater than the reference value, it means that the spectrum near 1190nm is absorbed, and the material to be detected is determined to be PET; when the mean value of the E area is greater than the reference value and the mean value of the V area is less than the reference value, it means that the spectrum near 1660nm is absorbed, and the material to be detected is determined to be PVC; in any other case, it is determined that the material to be detected is neither PVT nor PET.

Images