A Plastic Material Identification Method Based on the Slopes on Both Sides of the Trough of Near-Infrared Spectra

Abstract

The present invention relates to the field of material identification, and discloses a plastic material identification method based on the slopes on both sides of the wave valley of near-infrared spectra, comprising the following steps: S1: Prepare several plastic sample groups of different materials; S2: Obtain the curve of the reflectance varying with the wavelength of each plastic sample group of each material through a near-infrared spectrometer; S3: Analyze the curve of the reflectance varying with the wavelength of each plastic sample group of each material to obtain the representative curve of each material; S4: Select a specified material through a specified module; S5: Analyze the representative curve of each material and the specified material to obtain the characteristic wavelength range and corresponding characteristic wavelengths; S6: Determine whether it is the specified material by obtaining the slopes on both sides of the corresponding characteristic wavelengths within the characteristic wavelength range of the plastic to be detected; during the detection process, it is only necessary to obtain the infrared spectrum within the characteristic wavelength range of the plastic to be detected to quickly determine whether it is the plastic of the specified material; the detection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of material identification, and particularly to a method for identifying plastic materials based on the slopes on both sides of the near-infrared spectral trough. Background Art

[0002] Plastic recycling is an important way to reduce plastic waste and environmental burden. Since different plastics require different treatment methods and processes, it is necessary to identify and classify the recycled plastics.

[0003] Currently, plastics can be identified and classified by using near-infrared spectroscopy. Since the main components of different plastics are different, the infrared spectra of various plastics obtained by a near-infrared spectrometer are different. According to the near-infrared spectrum, the main components in the plastic to be detected can be analyzed, and then the type of the plastic can be determined based on the main components in the plastic.

[0004] However, during the detection process, in order to improve the accuracy of identification, a near-infrared spectrum of the entire near-infrared wavelength range needs to be obtained for each plastic to be detected. And it takes a long time to obtain a complete near-infrared spectrum. When the number of plastics to be detected is large, obtaining a complete near-infrared spectrum for each plastic to be detected wastes a lot of time, and the efficiency of plastic identification is low. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for identifying plastic materials based on the slopes on both sides of the near-infrared spectral trough, and solve the following technical problems:

[0006] How to improve the identification efficiency of plastics to be detected.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] A method for identifying plastic materials based on the slopes on both sides of the near-infrared spectral trough includes the following steps:

[0009] S1: Prepare several groups of plastic samples of different materials;

[0010] S2: Obtain the curve of the reflectance of each group of plastic samples of different materials varying with the wavelength through a near-infrared spectrometer;

[0011] S3: Analyze the curve of the reflectance of each group of plastic samples of different materials varying with the wavelength to obtain the representative curve of each material;

[0012] S4: Select a specified material through a specified module;

[0013] S5: Analyze the representative curve of each material and the specified material to obtain the characteristic wavelength range and corresponding characteristic wavelengths;

[0014] S6: Determine whether it is the specified material by obtaining the slopes on both sides of the corresponding characteristic wavelength within the characteristic wavelength range of the plastic to be detected.

[0015] As a further solution of the present invention: The obtaining process of the characteristic wavelength range includes the following steps:

[0016] S10: Identify the representative curve of the specified material through the identification unit to obtain the wavelengths corresponding to the valleys of the specified material on the representative curve of the specified material;

[0017] S20: Obtain the first reference wavelength range corresponding to each valley according to the wavelengths corresponding to the valleys of the specified material by the analysis unit according to the preset rules;

[0018] S30: Obtain the slopes on both sides of each valley of each representative curve within each first reference wavelength range by the analysis unit; and analyze according to the slopes on both sides of each valley of each representative curve to obtain the slope difference index of the specified material; and select the second reference wavelength range according to the slope difference index of the specified material;

[0019] S40: Analyze the curves of the reflectance of the plastic sample groups of each material within the second reference wavelength range changing with the wavelength to obtain the slope distribution index on both sides of the specified material; and obtain the characteristic wavelength range according to the slope distribution index on both sides of the specified material.

[0020] As a further solution of the present invention: By the formula:

[0021]

[0022] Calculate the slope difference index D between the nth valley of the specified material and the two sides of the mth non-specified material nm ;

[0023] Wherein, N is the total number of valleys of the specified material, n ∈ N; W n is the wavelength corresponding to the nth valley of the specified material; W0 is the preset wavelength interval; F i (W n ) is the reflectance corresponding to the wavelength W n on the representative curve of the specified material; F Z (W n -W0) is the reflectance corresponding to the wavelength W n -W0 on the representative curve of the specified material; F Z (W n ) is the reflectance corresponding to the wavelength W n +W0 on the representative curve of the specified material; M is the total number of non-specified materials among all materials, m ∈ M; F m (W n) is the reflectance corresponding to the wavelength W on the representative curve of the m-th non-specified material n ; F m (W n - W0) is the reflectance corresponding to the wavelength W on the representative curve of the m-th non-specified material n ; F m (W n + W0) is the reflectance corresponding to the wavelength W + W0 on the representative curve of the m-th non-specified material. n

[0024] As a further solution of the present invention: The selection process of the second reference wavelength range includes the following steps:

[0025] S100: Analyze the slope difference index between each trough of the specified material and the two sides of each non-specified material to obtain a difference judgment index;

[0026] S200: Determine the second reference wavelength range through the difference judgment index.

[0027] As a further solution of the present invention: In step S100, through the formula:

[0028]

[0029] Calculate the comprehensive slope difference index C of the n-th trough of the specified material n ;

[0030] Among them, f(X) is a judgment function. When X > 0, f(X) = 1; when X ≤ 0, f(X) = 0; D a is the first preset value; D L is the second preset value; D ns is the smallest slope difference index on both sides among the M non-specified materials.

[0031] As a further solution of the present invention: In step S200, the determination process of the second reference wavelength range is:

[0032] Select T troughs with a comprehensive slope difference index C n of 1, and the preset wavelength range corresponding to the selected troughs is determined as the second reference wavelength range.

[0033] As a further solution of the present invention: In step S40, the acquisition process of the characteristic wavelength range further includes the following steps:

[0034] S1000: Analyze the curves of the reflectance of plastic sample groups of each material changing with wavelength, and obtain the slope values on both sides of the wavelength W t in the second reference wavelength range of the t-th segment of the curves of the reflectance of plastic sample groups of each material changing with wavelength;

[0035] S2000: Plot the central scatter plot of the slope values on both sides of the t-th second reference wavelength range at the wavelength W according to the curves of the reflectance of each plastic sample group varying with the wavelength. t For the two slope values on both sides of the wavelength W within the t-th second reference wavelength range, respectively draw the central scatter plot of the slope values on both sides of the t-th.

[0036] S3000: Analyze the central scatter plot of the slope values on both sides of the t-th through the identification module to obtain the dispersion index, and determine the characteristic wavelength range according to the dispersion index.

[0037] As a further solution of the present invention: Through the formula:

[0038]

[0039] Calculate the dispersion index S of the t-th second reference wavelength range t ;

[0040] Wherein, S tm Is the area value of the overlapping part of the distribution area of the m-th non-specified material and the distribution area of the specified material on the central scatter plot of the t-th second reference wavelength range.

[0041] Advantages of the present invention:

[0042] The present invention first prepares several plastic sample groups of different materials; obtains the curves of the reflectance of each plastic sample group of each material varying with the wavelength through a near-infrared spectrometer; specifically, selects the specified material through the specified module; analyzes the representative curves of each material and the specified material to obtain the characteristic wavelength range and the corresponding characteristic wavelengths; then analyzes the representative curves of each material and the specified material to obtain the characteristic wavelength range and the corresponding characteristic wavelengths; finally, determines whether it is the specified material by obtaining the slopes on both sides of the corresponding characteristic wavelengths within the characteristic wavelength range of the plastic to be detected; during the detection process, it is only necessary to obtain the infrared spectrum within the characteristic wavelength range of the plastic to be detected to quickly determine whether it is the plastic of the specified material; improves the identification efficiency of the plastic to be detected. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The present invention will be further described below in conjunction with the accompanying drawings.

[0044] Figure 1 Is the flowchart of the method of an embodiment of the present invention;

[0045] Figure 2 Is the representative curve of each plastic sample group of each material in an embodiment of the present invention Figure 1 ;

[0046] Figure 3 Is the representative curve of each plastic sample group of each material in an embodiment of the present invention Figure 2 ;

[0047] Figure 4 It is the central scatter plot of the second reference wavelength range in the first paragraph of an embodiment of the present invention;

[0048] Figure 5 It is the central scatter plot of the second reference wavelength range in the second paragraph of an embodiment of the present invention;

[0049] Figure 6 It is the central scatter plot of the second reference wavelength range in the third paragraph of an embodiment of the present invention;

[0050] Figure 7 It is the central scatter plot of the second reference wavelength range in the fourth paragraph of an embodiment of the present invention;

[0051] Figure 8 It is the central scatter plot of the second reference wavelength range in the fifth paragraph of an embodiment of the present invention;

[0052] Figure 9 It is the central scatter plot of the second reference wavelength range in the sixth paragraph of an embodiment of the present invention. Detailed implementation manners

[0053] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0054] Please refer to Figures 1-2 As shown, in one embodiment, a plastic material identification method based on the slopes on both sides of the near-infrared spectral valley is provided, including the following steps:

[0055] S1: Prepare several groups of plastic samples of different materials;

[0056] S2: Obtain the curve of the reflectance of each group of plastic samples of different materials changing with the wavelength through a near-infrared spectrometer;

[0057] S3: Analyze the curves of the reflectance of each group of plastic samples of different materials changing with the wavelength to obtain the representative curves of each material;

[0058] S4: Select a specified material through a specified module;

[0059] S5: Analyze the representative curves of each material and the specified material to obtain the characteristic wavelength range and corresponding characteristic wavelengths;

[0060] S6: Determine whether it is the specified material by obtaining the slopes on both sides of the characteristic wavelength within the characteristic wavelength range of the plastic to be detected.

[0061] Through the above technical solution, in this embodiment, several groups of plastic samples of different materials are first prepared; in this embodiment, the number of plastic materials prepared is seven, and the seven plastic materials are PET, PE, HDPE, PS, PVC, ABS, and PP; the change curves of the reflectance of each group of plastic samples of different materials with the wavelength are obtained through a near-infrared spectrometer; specifically, the near-infrared spectrometer used in this embodiment is NIRQuest Spectrometers, whose wavelength range is from 900nm to 2500nm, and its optical resolution is 2.8nm FWHM; the reflectance is obtained after being processed by the spectrometer, and then the spectral data is saved to a computer for subsequent analysis. Before obtaining the plastic spectral data at the beginning of the experiment, it is necessary to correct the reflection effect, that is, to correct with a PTFE material calibration whiteboard. Collect the PTFE whiteboard spectrum once in a bright environment, and then collect the PTFE whiteboard dark spectrum again in a dark environment. After the collection is successful, the spectral calibration before the experiment is completed; each group of plastic samples includes 10 samples, and the colors and thicknesses of the 10 samples are different. 40 spectral data are obtained for each sample. Therefore, a total of 400 groups of spectral data are obtained for each group of plastic samples. The average value of the spectral data of each group of plastic samples is taken to obtain the representative curves of the seven materials of plastic; the representative curves of the seven materials of plastic are as Figure 2 shown; select the specified material through the specified module; in this embodiment, the specified material is PET; by analyzing the representative curves of each material and the specified material, the characteristic wavelength range and the corresponding characteristic wavelength are obtained; finally, determine whether it is the specified material by obtaining the slopes on both sides of the characteristic wavelength within the characteristic wavelength range of the plastic to be detected; during the detection process, it is only necessary to obtain the infrared spectrum within the characteristic wavelength range of the plastic to be detected to quickly determine whether it is the plastic of the specified material; the identification efficiency of the plastic to be detected is improved.

[0062] As an implementation manner of the present invention, the analysis module includes an identification unit and an analysis unit;

[0063] The identification unit is a trained neural network model; the identification unit identifies the representative curve of the specified material and obtains the wavelengths corresponding to the wave valleys of the specified material on the representative curve of the specified material;

[0064] It should be noted that the training process of the identification unit is prior art and will not be elaborated here.

[0065] As an implementation manner of the present invention, the process of obtaining the characteristic wavelength range includes the following steps:

[0066] S10: Identify the representative curve of the specified material through the identification unit, and obtain the wavelengths corresponding to the valleys of the specified material on the representative curve of the specified material;

[0067] S20: Obtain the first reference wavelength range corresponding to each valley according to the preset rules through the analysis unit based on the wavelengths corresponding to the valleys of the specified material;

[0068] S30: Obtain the slopes on both sides of the valleys of the specified material on each representative curve within each first reference wavelength range through the analysis unit; and analyze according to the slopes on both sides of the valleys of the specified material on each representative curve to obtain the slope difference index of the specified material; and select the second reference wavelength range according to the slope difference index of the specified material;

[0069] S40: Analyze the curves of the reflectance of the plastic sample groups of each material within the second reference wavelength range changing with the wavelength to obtain the slope distribution index on both sides of the specified material; and obtain the characteristic wavelength range according to the slope distribution index on both sides of the specified material;

[0070] Through the above technical solution, in this embodiment, first, the identification unit identifies the representative curve of the specified material to obtain the wavelengths corresponding to the valleys of the specified material on the representative curve of the specified material; then, the analysis unit obtains the first reference wavelength range corresponding to each valley according to the preset rules based on the wavelengths corresponding to the valleys of the specified material; then, the analysis unit obtains the slopes on both sides of the valleys of the specified material on each representative curve within each first reference wavelength range; and analyzes according to the slopes on both sides of the valleys of the specified material on each representative curve to obtain the slope difference index of the specified material; and selects the second reference wavelength range according to the slope difference index of the specified material; finally, analyzes the curves of the reflectance of the plastic sample groups of each material within the second reference wavelength range changing with the wavelength to obtain the slope distribution index on both sides of the specified material; and obtains the characteristic wavelength range according to the slope distribution index on both sides of the specified material.

[0071] As an implementation manner of the present invention, through the formula:

[0072]

[0073] Calculate the slope difference index D between the two sides of the nth valley of the specified material and the mth non-specified material nm ;

[0074] where N is the total number of valleys of the specified material, n ∈ N; W n is the wavelength corresponding to the nth valley of the specified material; W0 is the preset wavelength interval; F i (W n ) is the reflectance corresponding to the wavelength W n on the representative curve of the specified material; F Z (Wn -W0) is the reflectance corresponding to the wavelength W on the representative curve of the specified material; F n -W0; F Z (W n +W0) is the reflectance corresponding to the wavelength W n +W0 on the representative curve of the specified material; M is the total number of non-specified materials among all materials, m ∈ M; F m (W n ) is the reflectance corresponding to the wavelength W n on the representative curve of the m-th non-specified material; F m (W n -W0) is the reflectance corresponding to the wavelength W n on the representative curve of the m-th non-specified material; F m (W n +W0) is the reflectance corresponding to the wavelength W n +W0 on the representative curve of the m-th non-specified material;

[0075] Through the above technical solution, in this embodiment is the slope on the left side of the n-th trough on the representative curve of the specified material; is the slope on the left side of the position where the wavelength is W n on the representative curve of the m-th non-specified material; is the absolute value of the difference between the slope on the left side of the n-th trough on the representative curve of the specified material and the slope on the left side of the position where the wavelength is W n on the representative curve of the m-th non-specified material; is the slope on the right side of the n-th trough on the representative curve of the specified material; is the slope on the right side of the position where the wavelength is W n on the representative curve of the m-th non-specified material; is the absolute value of the difference between the slope on the right side of the n-th trough on the representative curve of the specified material and the slope on the right side of the position where the wavelength is W n on the representative curve of the m-th non-specified material; is the sum of the absolute value of the difference between the slope on the left side of the n-th trough on the representative curve of the specified material and the slope on the left side of the position where the wavelength is W n on the representative curve of the m-th non-specified material and the absolute value of the difference between the slope on the right side of the n-th trough on the representative curve of the specified material and the slope on the right side of the position where the wavelength is W n on the representative curve of the m-th non-specified material, the slope on the left side of the n-th trough on the representative curve of the specified material and the slope on the left side of the position where the wavelength is W nThe sum of the absolute value of the difference in the slope on the left side of the position and the absolute value of the difference in the slope on the right side of the nth trough on the representative curve of the specified material and the slope on the right side of the wavelength W on the representative curve of the mth non-specified material n is larger, the slope difference index D of both sides of the nth trough of the specified material and the mth non-specified material is larger; nm The larger;

[0076] It should be noted that the preset wavelength interval W0 is a preset value, obtained based on experience, and will not be elaborated here.

[0077] As an implementation manner of the present invention, the selection process of the second reference wavelength range includes the following steps:

[0078] S100: Analyze the slope difference index of both sides of each trough of the specified material and each non-specified material to obtain a difference judgment index;

[0079] S200: Determine the second reference wavelength range through the difference judgment index;

[0080] Through the above technical solution, in this embodiment, first, analyze the slope difference index of both sides of each trough of the specified material and each non-specified material to obtain a difference judgment index; then determine the second reference wavelength range through the difference judgment index; perform a preliminary screening on the troughs to reduce the subsequent calculation amount;

[0081] As an implementation manner of the present invention, in step S100, through the formula:

[0082]

[0083] Calculate the comprehensive slope difference index C of the nth trough of the specified material n ;

[0084] where f(X) is a judgment function, when X>0, f(X)=1; when X≤0, f(X)=0; D a is the first preset value; D L is the second preset value; D ns is the smallest slope difference index of both sides among the M non-specified materials;

[0085] Through the above technical solution, this embodiment is the average slope difference index of both sides of the nth trough of the specified material and the M non-specified materials; is the difference between the average slope difference index of both sides of the nth trough of the specified material and the M non-specified materials and the first preset value; in the formula , X in the judgment function f(X) refers to When When it indicates that the difference index of the slopes on both sides of the n-th trough of the specified material and the average of the M non-specified materials is small, therefore When it indicates that the difference index of the slopes on both sides of the n-th trough of the specified material and the average of the M non-specified materials is large, therefore D ns -D L is the difference between the smallest difference index of the slopes on both sides among the M non-specified materials and the second preset value; in the formula f(D ns -D L ), it is judged that X in the function f(X) refers to D ns -D L ; when D ns -D L ≤0, it indicates that the smallest difference index of the slopes on both sides among the M non-specified materials is small, so f(D ns -D L ) = 0; when D ns -D L > 0, it indicates that the smallest difference index of the slopes on both sides among the M non-specified materials is large, so f(D ns -D L ) = 1;

[0086] It should be noted that the first preset value D a and the second preset value D L are preset values obtained according to experience and will not be elaborated here.

[0087] As an implementation manner of the present invention, in step S200, the process of determining the second reference wavelength range is as follows:

[0088] Screen out T troughs with a comprehensive slope difference index C n of 1, and the preset wavelength range corresponding to the screened troughs is determined as the second reference wavelength range;

[0089] Through the above technical solution, this embodiment screens out T troughs with a comprehensive slope difference index C n of 1, so there are T second reference wavelength ranges, t ∈ T; the preset wavelength range corresponding to the n-th trough is [W n -W0, W n +W0]; therefore, the t-th second reference wavelength range is denoted as [W t -W0, W t +W0]; specifically, in this embodiment, 6 troughs with a screened comprehensive slope difference index C n of 1 are screened out; as Figure 3As shown, the wavelengths corresponding to the 6 wave valleys are 1210nm, 1393nm, 1660nm, 1720nm, 2130nm, and 2290nm respectively. W0 is 10nm in this embodiment. Therefore, the 6 corresponding second reference wavelength ranges are (1200nm, 1220nm), (1383nm, 1403nm), (1650nm, 1670nm), (1710nm, 1730nm), (2120nm, 2140nm), and (2280nm, 2300nm).

[0090] Please refer to Figures 4-9 As shown, as an embodiment of the present invention, in step S40, the process of obtaining the characteristic wavelength range further includes the following steps:

[0091] S1000: By analyzing the curves of the reflectance of plastic sample groups of each material versus wavelength, obtain the slope values on both sides of the wavelength W within the t-th second reference wavelength range of the curves of the reflectance of each plastic sample group versus wavelength. t of the slope values on both sides;

[0092] S2000: According to the slope values on both sides of the wavelength W within the t-th second reference wavelength range of the curves of the reflectance of each plastic sample group versus wavelength, t respectively draw the central scatter plot of the slope values on both sides of the t-th;

[0093] S3000: Analyze the central scatter plot of the slope values on both sides of the t-th by the recognition module to obtain the dispersion index, and determine the characteristic wavelength range according to the dispersion index;

[0094] Through the above technical solution, in this embodiment, by analyzing the curves of the reflectance of plastic sample groups of each material versus wavelength, the slope values on both sides of the wavelength W within the t-th second reference wavelength range of the curves of the reflectance of each plastic sample group versus wavelength are obtained. t Then, according to the slope values on both sides of the wavelength W within the t-th second reference wavelength range of the curves of the reflectance of each plastic sample group versus wavelength, t respectively draw the central scatter plot of the slope values on both sides of the t-th; Figures 4-9 They are respectively the central scatter plots of the slope values on both sides of the 6 second reference wavelength ranges; the horizontal axis of the coordinate represents the left slope of each plastic, and the vertical axis of the coordinate represents the right slope; mark the characteristic points of the slope values on both sides of the 400 groups of spectral data of each plastic sample group on the central scatter plot, and each plastic sample group is marked with a different color; through Figures 4-9, it can be seen that the distributions of each type of plastic under the characteristics of the left slope and the right slope are significantly different; finally, the recognition module recognizes the central scatter plot of the t-th left and right slope values, and respectively obtains the distribution regions of various color marked points according to the colors. The distribution region of one color marked point is the distribution region of the left and right slope values of one plastic sample group. Then, the dispersion index is obtained by analyzing according to the distribution regions of each color marked point. The second reference wavelength range with the most obvious distribution of the specified material and the non-specified material is obtained through the dispersion index as the characteristic wavelength range.

[0095] As an implementation manner of the present invention, through the formula:

[0096]

[0097] Calculate the dispersion index S of the second reference wavelength range of the t-th segment t ;

[0098] Among them, S tm is the area value of the overlapping part of the distribution region of the m-th non-specified material and the distribution region of the specified material on the central scatter plot of the second reference wavelength range of the t-th segment;

[0099] Through the above technical solution, in this embodiment is the cumulative value of the area values of the overlapping parts of the distribution regions of M non-specified materials and the distribution region of the specified material on the central scatter plot of the second reference wavelength range of the t-th segment; the cumulative value of the area values of the overlapping parts of the distribution regions of M non-specified materials and the distribution region of the specified material The larger it is, the more difficult it is to screen out the specified material from various plastic materials, and the lower the accuracy rate. The dispersion index S of the second reference wavelength range of the t-th segment t is smaller; the cumulative value of the area values of the overlapping parts of the distribution regions of M non-specified materials and the distribution region of the specified material The smaller it is, the easier it is to screen out the specified material from various plastic materials, and the higher the accuracy rate. The dispersion index S of the second reference wavelength range of the t-th segment t is larger; when , there is no overlapping part between the distribution regions of M non-specified materials and the distribution region of the specified material; therefore, the second reference wavelength range with the dispersion index S t =0 is selected as the characteristic wavelength range; the wavelength corresponding to the trough of the representative curve of the specified material within the characteristic wavelength range is the corresponding characteristic wavelength; the dispersion index S of the first second reference wavelength range (1200nm, 1220nm) of this embodiment t =0; therefore, (1200nm, 1220nm) is the characteristic wavelength range; therefore, 1210nm is the corresponding characteristic wavelength;

[0100] It should be noted that obtaining the distribution regions based on the color marked points and obtaining the area values of the overlapping parts of the distribution regions are prior arts, which will not be elaborated here.

[0101] The above has described a specific embodiment of the present invention in detail. However, the above content is only a preferred embodiment of the present invention and should not be considered as limiting the scope of implementation of the present invention. Any equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A plastic material identification method based on the slopes on both sides of the trough of the near-infrared spectrum, characterized in that, It includes the following steps: S1: Prepare several groups of plastic samples made of different materials; S2: Obtain the curves of the reflectance of each group of plastic samples made of different materials varying with wavelength through a near-infrared spectrometer; S3: Analyze the curves of the reflectance of each group of plastic samples made of different materials varying with wavelength to obtain the representative curves of each material; S4: Select a specified material through a specified module; S5: Analyze the representative curves of each material and the specified material to obtain the characteristic wavelength range and the corresponding characteristic wavelengths; S6: Determine whether it is the specified material by obtaining the slopes on both sides of the corresponding characteristic wavelengths within the characteristic wavelength range of the plastic to be detected; The process of obtaining the characteristic wavelength range includes the following steps: S10: Identify the representative curve of the specified material through an identification unit to obtain the wavelengths corresponding to the valleys of the specified material on the representative curve of the specified material; S20: Obtain the first reference wavelength range corresponding to each valley through an analysis unit according to the wavelengths corresponding to the valleys of the specified material according to a preset rule; S30: The analysis unit obtains the slopes on both sides of the valleys of the specified material within each first reference wavelength range for each representative curve; and analyzes according to the slopes on both sides of the valleys of the specified material for each representative curve to obtain the slope difference index of the specified material; and selects the second reference wavelength range according to the slope difference index of the specified material; S40: Analyze the curves of the reflectance of each group of plastic samples made of different materials varying with wavelength within the second reference wavelength range to obtain the slope distribution index on both sides of the specified material; and obtain the characteristic wavelength range according to the slope distribution index on both sides of the specified material.

2. The plastic material identification method based on the slopes on both sides of the near-infrared spectral valley according to claim 1, wherein Through the formula: Calculate the slope difference index D between the nth trough of the specified material and both sides of the mth non-specified material nm ; Where N is the total number of valleys of the specified material, n ∈ N; W n is the wavelength corresponding to the n-th valley of the specified material; W0 is the preset wavelength interval; F Z (W n ) is the reflectivity corresponding to the wavelength W n on the representative curve of the specified material; F Z (W n - W0) is the reflectivity corresponding to the wavelength W n - W0 on the representative curve of the specified material; F Z (W n + W0) is the reflectivity corresponding to the wavelength W n + W0 on the representative curve of the specified material; M is the total number of non-specified materials among all materials, m ∈ M; F m (W n ) is the reflectivity corresponding to the wavelength W n on the representative curve of the m-th non-specified material; F m (W n - W0) is the reflectivity corresponding to the wavelength W n on the representative curve of the m-th non-specified material; F m (W n + W0) is the reflectivity corresponding to the wavelength W n + W0 on the representative curve of the m-th non-specified material.

3. The plastic material identification method based on the slopes on both sides of the near-infrared spectral trough according to claim 2, characterized in that, The process of selecting the second reference wavelength range includes the following steps: S100: Analyze the slope difference index between each valley of the specified material and both sides of each non-specified material to obtain a difference judgment index; S200: Determine the second reference wavelength range through the difference judgment index.

4. The plastic material identification method based on the slopes on both sides of the near-infrared spectral valley according to claim 3, characterized in that In step S100, through the formula: Calculate the comprehensive slope difference index C of the nth trough of the specified material n ; Among them, f(X) is a judgment function. When X > 0, f(X) = 1; when X ≤ 0, f(X) = 0; D a is the first preset value; D L is the second preset value; D ns is the smallest slope difference index between two sides among M non-specified materials.

5. A method for identifying plastic materials based on the slopes on both sides of the trough of near-infrared spectra according to claim 4, characterized in that In step S200, the process of determining the second reference wavelength range is: Filter out T comprehensive slope difference indices C n For the trough with a value of 1, the preset wavelength range corresponding to the filtered trough is determined as the second reference wavelength range.

6. The plastic material identification method based on the slopes on both sides of the near-infrared spectral trough according to claim 5, wherein In step S40, the process of obtaining the characteristic wavelength range further includes the following steps: S1000: By analyzing the curves of the reflectance of plastic sample groups of various materials with respect to wavelength, obtain the slope values on both sides of the wavelength W within the second reference wavelength range of the t-th segment of the curves of the reflectance of each plastic sample group with respect to wavelength. t of the reflectance curve. S2000: Plot a central scatter diagram of the slope values on both sides of the t-th based on the slope values on both sides of the wavelength W within the t-th second reference wavelength range according to the curve of the reflectance of each plastic sample group varying with the wavelength. t of the t-th slope values on both sides; S3000: Analyze the central scatter plot of the t-th slope value on both sides through an identification module to obtain a dispersion index, and determine the characteristic wavelength range according to the dispersion index.

7. A method for identifying plastic materials based on the slopes on both sides of the near-infrared spectral trough according to claim 6, characterized in that, Through the formula: Calculate the dispersion index S of the second reference wavelength range in the t-th segment t ; Among them, S tm is the area value of the overlapping part between the distribution area of the m-th non-specified material and the distribution area of the specified material on the central scatter plot of the second reference wavelength range in the t-th segment.

Images