Solid waste classification method based on spectrograph

Abstract

The invention discloses a solid waste classification method based on a spectrometer, and relates to the technical field of solid waste analysis, and the method comprises the following steps: S1, preliminary classification: obtaining a sample of unknown solid waste, and observing the characteristics of the sample to obtain characteristic information; s2, selecting a spectrograph: selecting the spectrograph according to the feature information; analyzing the sample by using a spectrograph to obtain a spectrogram; the spectrogram comprises a spectrum curve; s3, spectrogram preprocessing: carrying out normalization processing on the data of the spectrum curve; s4, similarity analysis: for the spectrum curves of the multiple samples, randomly selecting two samples for comparison to obtain a similarity value; if the similarity value is within a preset threshold range, the two samples to be compared belong to the same kind of solid waste. The method is low in operation cost and low in professional degree requirement on workers, and can realize rapid and efficient analysis and classification of solids.

Description

Technical Field

[0001] The invention relates to the technical field of solid waste analysis, and in particular to a solid waste classification method based on a spectrometer. Background Art

[0002] Environmental incidents in hazardous waste identification work have attracted much attention due to their suddenness, complexity and urgency. Environmental incidents mainly include unknown solid waste dumping incidents and unknown solid waste historical landfill incidents. According to the "Technical Specifications for Hazardous Waste Identification" (HJ 298-2019), hazardous waste identification needs to determine the number of sampling portions based on the quality of the solid waste to be identified. The amount of solid waste accumulated in dumping incidents is generally tens of tons, and the amount of solid waste landfilled in historical landfill incidents is generally thousands of tons.

[0003] Due to the large amount of accumulation / landfill of the above substances, the environmental management department law enforcement personnel, hazardous waste identification technicians and other environmental industry practitioners need to collect dozens to hundreds of samples in actual work, and select representative samples as preliminary screening samples, and determine the subsequent testing parameters based on the screening results of the preliminary screening samples. The preliminary screening process usually relies heavily on the experience of the technicians.

[0004] Therefore, collecting dozens to hundreds of samples will lead to a surge in project monitoring costs, labor costs, and time costs, which is not adapted to the urgency of environmental events. Improper selection of initial screening samples will also lead to distorted assessment of the hazardous characteristics of hazardous wastes, and there is a possibility that hazardous wastes will be misjudged as general solid wastes.

[0005] The current technical solutions are more inclined to conduct qualitative analysis and component analysis of unknown substances, that is, to determine the type of substance and the components it contains.

[0006] The prior art provides a method and process for extracting fingerprint features of solid waste, namely: obtaining solid waste samples of a predetermined industry, obtaining predetermined fingerprint factors, taking fingerprint factors as observation values, calculating statistical parameters based on the rank sum of various fingerprint factors in the predetermined industry, calculating statistical parameters based on the rank sum of various fingerprint factors in the predetermined industry, determining whether the specified fingerprint factor meets the screening criteria based on the statistical parameters, and screening out the corresponding fingerprint factors; constructing a fingerprint test group, introducing each of the screened fingerprint factors as a reference variable into the fingerprint test group or removing it from the fingerprint test group; obtaining a comparison index, and judging the best fingerprint factor combination based on the test parameters and the comparison index. However, this type of scheme has limitations in emergency events such as dumping environmental events, and cannot quickly achieve qualitative or classification of substances, which interferes with the subsequent work such as the sample collection link in the identification of hazardous waste. On the other hand, the substances appearing in environmental events are complex and may be a mixture of one or more substances, and there is a high probability that the complex material components cause the components to interfere with each other, and the substances cannot match the established fingerprint library. In addition, because the material components in environmental events are variable, the established fingerprint library is usually not universal.

[0007] The prior art also provides a solid waste fingerprint feature extraction method based on statistical entropy, namely: select a numerical indicator of solid waste, divide the numerical indicator into n levels and n events equally, calculate the ratio of statistical entropy to maximum entropy as the relative rate after normalization according to the statistical entropy method, and compare the calculated relative rate with the judgment relative rate. If the calculated relative rate is less than or equal to the judgment relative rate, it can be judged that the numerical indicator belongs to the characteristic fingerprint of solid waste. However, this type of solution has high requirements for technicians in the numerical indicator selection step and requires a deep understanding of the substance to be analyzed. Summary of the invention

[0008] In view of the problems existing in the prior art, the present invention provides a solid waste classification method based on a spectrometer, which can quickly carry out on-site identification and analysis of substances at the solid waste dump site or environmental event site to determine whether multiple substances to be analyzed belong to the same type of substances. The operation cost is low and the professional requirements for staff are low.

[0009] The technical solution of the present invention is achieved in this way:

[0010] A solid waste classification method based on a spectrometer comprises the following steps:

[0011] S1. Preliminary classification: Obtain samples of unknown solid waste, observe the characteristics of the samples, and obtain characteristic information;

[0012] S2. Selecting a spectrometer: selecting a spectrometer according to the characteristic information; the spectrometer is a portable, movable device, or can be an immovable device in a laboratory; analyzing the sample using the spectrometer to obtain a spectrum; the spectrum includes a spectrum curve;

[0013] S3, spectrum preprocessing: normalizing the data of the spectrum curve;

[0014] S4. Similarity analysis: For the spectral curves of the multiple samples, any two samples are selected for comparison to obtain a similarity value; if the similarity value is within a preset threshold range, the two compared samples belong to the same type of solid waste.

[0015] The classification results of the on-site classification of substances of unknown origin by the classification method of the present invention are more scientific, and are particularly suitable for portable spectral analysis instruments. They are low in cost and time-efficiency, and require less professionalism from technical personnel. They can provide theoretical support for reducing the amount of sample portions and selecting typical samples in hazardous waste identification work for environmental management department law enforcement personnel, hazardous waste identification technicians and other environmental industry-related practitioners. The method of this scheme is applicable to both classification and processing when collecting samples outdoors and processing procedures in laboratories.

[0016] As a further optimization of the above scheme, the preliminary classification is to preliminarily classify the samples according to their appearance, and the categories include liquid materials, amorphous or organic materials, high water content materials, and dark materials.

[0017] As a further optimization of the above solution, the spectrometer includes an X-ray fluorescence spectrometer, an X-ray diffractometer, a Fourier transform infrared spectrometer, and a Raman spectrometer.

[0018] Each type of spectrometer is used to analyze specific materials. Among them, X-ray fluorescence spectrometer is not suitable for non-solid samples, such as gas or liquid; X-ray diffractometer is not suitable for non-crystalline materials or amorphous materials; Fourier infrared spectroscopy is not suitable for samples that are sensitive to water; Raman spectrometer is not suitable for samples that strongly absorb and scatter lasers, such as some black or dark materials.

[0019] As a further optimization of the above solution, the normalization process is:

[0020]

[0021] Wherein, y represents the ordinate value of the data point of the spectral curve; y max and min Respectively represent the maximum vertical coordinate value and the minimum vertical coordinate value; y i and i ′Respectively represent the ordinate values ​​of the data point of the ith item of the spectral curve before and after normalization processing.

[0022] Normalization is intended to eliminate differences in signal intensity caused by differences in intrinsic components in the sample (such as vibration group content, vibration group activity, etc.). After normalization, the data ordinate interval corresponding to the spectral curve is mapped to the range of 0 to 1 and converted into dimensionless data. Dimensionless data refers to data without specific units. They are usually used to eliminate the influence of physical dimensions so that data can be compared between different measurement units.

[0023] As a further optimization of the above scheme, the spectrum graph preprocessing also includes smoothing the data of the spectrum curve;

[0024] The smoothing process is performed using a Savitizky-Golay filter:

[0025]

[0026] Among them, (x i ,y i ) represents the data point of the spectral curve, i is the index of the current data point; X i Represents x i The corresponding smoothing window matrix; a, p and θ i are the constant term, coefficient and coefficient vector in the fitting polynomial respectively; m is the size of the smoothing window; Represents finding the polynomial coefficient θ i , so that X i θ i and Y i The Euclidean distance of i is the hat matrix; Y i is a vector composed of the ordinates of the data points within the smoothing window; Y i The result after filtering.

[0027] Smoothing is to remove noise and interference signals on the curve, so that the curve can be better used for the next step of analysis and comparison. This solution processes the horizontal and vertical coordinate points in the spectrum graph through the Savitizky-Golay filter, and fits a polynomial in the local window of the data so that the polynomial fits the data points in the window best, thereby achieving data smoothing.

[0028] Alternatively, the smoothing method also includes moving average method (Moving Average), exponential smoothing method (Exponential smoothing), polynomial fitting method (Polynomial Fitting), Bezier curve fitting method (Bezier Curve Fitting), local weighted scattered point smoothing method (Loess), Kalman filter method (KalmanFilter), wavelet transform method (Wavelet Transform) and other methods.

[0029] As a further optimization of the above solution, the spectrum preprocessing also includes removing invalid peaks of the spectrum curve; and modifying the ordinate values ​​of the data points corresponding to the selected invalid peaks to preset intensity values.

[0030] Invalid peak correction aims to delete invalid peaks in the spectrum. For example, a portable Raman spectrometer may produce invalid peaks with a wide peak width when interfering with strong fluorescent substances, or it may be interfered by cosmic rays during the detection process and produce invalid peaks. Invalid peaks can be selected through machine learning, deep learning, etc., using equipment and algorithms for automatic identification, or technicians can make manual judgments based on their professional knowledge reserves.

[0031] As a further optimization of the above scheme, when the change trend of the spectral curve is monotonically changing, the similarity value is calculated using the Spearman correlation coefficient, which is specifically calculated as follows:

[0032]

[0033] Among them, r s That is the similarity value; A i and B i They correspond to the ordinate values ​​of the two spectral curves respectively; i is the index of the ordinate value in one of the spectral curves; n represents the number of data points in one of the spectral curves; rank(·) represents the rank.

[0034] The Spearman correlation coefficient is used to measure the monotonic relationship between two variables. rank(·) is used to indicate that each value in the data set is sorted and assigned a rank. For example, sort each value in variables A and B separately, arrange the values ​​in the data set from smallest to largest (or from largest to smallest), and rank them in order. The smallest value is assigned rank 1, the second smallest value is assigned rank 2, and so on.

[0035] As a further optimization of the above scheme, when the change trend of the spectral curve is irregular, the calculation of the similarity value includes adopting a correlation coefficient algorithm based on Euclidean distance conversion, and the specific calculation is:

[0036]

[0037] Wherein, r is the similarity value; (x i ,y i ) and (x i ′ ,y i ′ ) represent the coordinates of the i-th data point of the two spectral curves respectively; n represents the number of data points in one spectral curve; σ x and σ y Indicates the standard deviation of all data points on the horizontal and vertical axes respectively; u x and u y represents the average value of all data points on the horizontal and vertical axes respectively; d is the Euclidean distance.

[0038] As a further optimization of the above scheme, the method further includes the following steps: S5, cluster analysis: for a number of unclassified samples, cluster analysis algorithms are used to classify them.

[0039] In similarity analysis, samples with similarity values ​​within the preset threshold range can be clustered, but there will still be samples whose similarity values ​​cannot be within the preset threshold range with any other samples. In this case, the clustering algorithm is used to perform high-precision analysis and classification on the remaining unclassified samples.

[0040] As a further optimization of the above scheme, the clustering algorithm is calculated as follows:

[0041]

[0042] Wherein, x represents the spectral curve; μ i (0) represents the center of the i-th cluster before the iteration starts; C i (t) represents the set of all data assigned to the i-th cluster in the t-th iteration; μ i (t+1) represents the center of the i-th cluster at the r+1th iteration; k represents the number of classifications;

[0043] When μ i (t+1) =μ i (t) When the preset number of iterations is reached, the iteration is terminated.

[0044] The K-MEANS clustering algorithm is a distance-based iterative solution clustering analysis algorithm that divides the spectral curve into k preset clusters (categories) and calculates the mean of all points at the center of each cluster. By updating the cluster center and recalculating the mean of all points in the cluster, the k value obtained at the end of the iteration is the final cluster, and each cluster corresponds to a category.

[0045] Compared with the prior art, the present invention achieves the following beneficial effects:

[0046] The present invention provides a solid waste classification method based on a spectrometer, which can improve the scientificity and accuracy of on-site classification of substances of unknown origin. Its main advantages include low cost, high efficiency, and low professional and technical requirements for operators. It can provide a theoretical basis for professionals in the environmental industry such as environmental management departments, law enforcement personnel, and hazardous waste identification technicians in the identification of hazardous wastes, helping them reduce the number of samples and select representative samples, thereby improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of a solid waste classification method based on a spectrometer provided in an embodiment of the present invention;

[0048] Figure 2 Schematic diagram of the effects before (left) and after (right) normalization processing provided by an embodiment of the present invention;

[0049] Figure 3 Schematic diagram of the effect before (left) and after (right) smoothing provided by an embodiment of the present invention;

[0050] Figure 4 Schematic diagram of the effect of removing invalid peaks before (left) and after (right) treatment provided by an embodiment of the present invention;

[0051] Figure 5 1 is a schematic diagram of the effect of similarity value calculation based on the Spearman correlation coefficient provided by an embodiment of the present invention;

[0052] Figure 6 1 is a schematic diagram showing the effect of similarity value calculation based on the correlation coefficient algorithm of Euclidean distance conversion provided in an embodiment of the present invention;

[0053] Figure 7 A schematic diagram of the effect of cluster analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present invention more clear, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] This embodiment provides a solid waste classification method based on a spectrometer, such as Figure 1 As shown, the following steps are included:

[0056] S1. Preliminary classification: Obtain samples of unknown solid waste, observe the characteristics of the samples, and obtain characteristic information. Specifically, in this embodiment, the preliminary classification is to classify the samples according to their appearance, and the categories include liquid materials, amorphous or organic materials, high water content materials, dark materials, or other materials.

[0057] S2. Select a spectrometer: select a spectrometer according to the characteristic information; the spectrometer is a portable device. In this embodiment, the spectrometer includes a portable X-ray fluorescence spectrometer, a portable X-ray diffractometer, a mobile Fourier infrared spectrometer, a portable Raman spectrometer, or other spectrometers.

[0058] Each type of spectrometer is used to analyze specific materials. Among them, portable X-ray fluorescence spectrometers are not suitable for non-solid samples, such as gases or liquids; portable X-ray diffractometers are not suitable for non-crystalline or amorphous materials; mobile Fourier infrared spectrometers are not suitable for samples that are sensitive to water; portable Raman spectrometers are not suitable for samples that strongly absorb and scatter lasers, such as certain black or dark materials.

[0059] Analyzing the sample by using a spectrometer to obtain a spectrum diagram; the spectrum diagram includes a spectrum curve;

[0060] S3. Spectral graph preprocessing: normalize, smooth and process invalid peaks of spectral curve data. Save the spectrum obtained after the substance to be analyzed by the portable spectral analyzer, and export the coordinate points in the spectrum. Use mathematical methods to preprocess the spectrum to facilitate subsequent curve similarity comparison.

[0061] like Figure 2 As shown, in this embodiment, the normalization process is:

[0062]

[0063] Where y represents the ordinate value of the data point of the spectral curve; y max and minRespectively represent the maximum ordinate value and the minimum ordinate value; y i and i ′ They respectively represent the ordinate values ​​of the i-th data point of the spectral curve before and after normalization.

[0064] Normalization is intended to eliminate differences in signal intensity caused by differences in intrinsic components in the sample (such as vibration group content, vibration group activity, etc.). After normalization, the data ordinate interval corresponding to the spectral curve is mapped to the range of 0 to 1 and converted into dimensionless data. Dimensionless data refers to data without specific units. They are usually used to eliminate the influence of physical dimensions so that data can be compared between different measurement units.

[0065] like Figure 3 As shown, in this embodiment, the spectrum graph preprocessing also includes smoothing the data of the spectrum curve;

[0066] The smoothing process is done using the Savitizky-Golay filter:

[0067]

[0068] Among them, (x i ,y i ) represents the data point of the spectrum curve, i is the index of the current data point; X i Represents x i The corresponding smoothing window matrix; a, p and θ i are the constant term, coefficient and coefficient vector in the fitting polynomial respectively; m is the size of the smoothing window; Represents finding the polynomial coefficient θ i , so that X i θ i and Y i The Euclidean distance of i is the hat matrix; Y i is a vector consisting of the vertical coordinates of the data points within the smoothing window; Y i The result after filtering.

[0069] Smoothing is to remove noise and interference signals on the curve, so that the curve can be better used for the next step of analysis and comparison. This solution processes the horizontal and vertical coordinate points in the spectrum graph through the Savitizky-Golay filter, and fits a polynomial in the local window of the data so that the polynomial fits the data points in the window best, thereby achieving data smoothing.

[0070] Alternatively, the smoothing method also includes moving average method (Moving Average), exponential smoothing method (Exponential smoothing), polynomial fitting method (Polynomial Fitting), Bezier curve fitting method (Bezier Curve Fitting), local weighted scattered point smoothing method (Loess), Kalman filter method (KalmanFilter), wavelet transform method (Wavelet Transform) and other methods.

[0071] like Figure 4 As shown, in this embodiment, the spectrum graph preprocessing also includes removing invalid peaks of the spectrum curve; the ordinate value of the data point corresponding to the selected invalid peak is modified to a preset intensity value.

[0072] Invalid peak correction aims to delete invalid peaks in the spectrum. For example, a portable Raman spectrometer may produce invalid peaks with a wide peak width when interfering with strong fluorescent substances, or it may be interfered by cosmic rays during the detection process and produce invalid peaks. Invalid peaks can be selected through machine learning, deep learning, etc., using equipment and algorithms for automatic identification, or technicians can make manual judgments based on their professional knowledge reserves.

[0073] S4. Similarity analysis: For the spectral curves of multiple samples, arbitrarily select two samples for comparison to obtain a similarity value; if the similarity value is within the preset threshold range, the two samples being compared belong to the same type of solid waste. If the similarity of any two or more curves in the spectrum is greater than 0.90, it can be determined that the above curves belong to the same type. In addition, if the similarity is less than 0.50, it can be determined that the comparison curve does not belong to the same type of curve. The specific preset threshold range can be set according to demand. The threshold range of this embodiment is [0.9, 1].

[0074] In this embodiment, when the changing trend of the spectral curve is monotonically changing, such as monotonically increasing, monotonically decreasing, etc., the similarity value is calculated using the Spearman correlation coefficient; if the changing trend of the spectral curve is irregularly changing, such as fluctuating, the similarity value is calculated using a correlation coefficient algorithm based on Euclidean distance conversion.

[0075] Specifically, Figure 5 As shown, in this embodiment, the calculation of the Spearman correlation coefficient is:

[0076]

[0077] Among them, r s is the similarity value; A i and B iThey correspond to the ordinate values ​​of two spectral curves respectively; i is the index of the ordinate value in a spectral curve; n represents the number of data points in a spectral curve; rank(·) represents the rank.

[0078] The Spearman correlation coefficient is used to measure the monotonic relationship between two variables. rank(·) is used to indicate that each value in the data set is sorted and assigned a rank. For example, sort each value in variables A and B separately, arrange the values ​​in the data set from smallest to largest (or from largest to smallest), and rank them in order. The smallest value is assigned rank 1, the second smallest value is assigned rank 2, and so on.

[0079] like Figure 6 As shown, the specific calculation of the correlation coefficient algorithm based on Euclidean distance conversion is:

[0080]

[0081] Among them, r is the similarity value; (x i ,y i ) and (x i ′ ,y i ′ ) represent the coordinates of the i-th data point of the two spectral curves; n represents the number of data points in a spectral curve; σ x and σ y Indicates the standard deviation of all data points on the horizontal and vertical axes respectively; u x and u y represents the average value of all data points on the horizontal and vertical axes respectively; d is the Euclidean distance.

[0082] S5. Cluster analysis: For several samples that have not been classified, cluster analysis algorithm is used for classification. Figure 7 As shown, the clustering algorithm is calculated as follows:

[0083]

[0084] Where x represents the spectral curve; μ i (0) represents the center of the i-th cluster before the iteration starts; C i (t) represents the set of all data assigned to the i-th cluster in the t-th iteration; μ i (t+1) represents the center of the i-th cluster at the r+1th iteration; k represents the number of classifications;

[0085] When μ i (t+1) =μ i(t) When the preset number of iterations is reached, the iteration is terminated.

[0086] In similarity analysis, samples with similarity values ​​within the preset threshold range can be clustered, but there will still be samples whose similarity values ​​cannot be within the preset threshold range with any other samples. In this case, the clustering algorithm is used to perform high-precision analysis and classification on the remaining unclassified samples.

[0087] The K-MEANS clustering algorithm is a distance-based iterative solution clustering analysis algorithm that divides the spectral curve into k preset clusters (categories) and calculates the mean of all points at the center of each cluster. By updating the cluster center and recalculating the mean of all points in the cluster, the k value obtained at the end of the iteration is the final cluster, and each cluster corresponds to a category.

[0088] According to the disclosure and teaching of the above description, those skilled in the art to which the present invention belongs may also make changes and modifications to the above embodiments. Therefore, the present invention is not limited to the specific embodiments disclosed and described above, and some modifications and changes to the present invention should also fall within the scope of protection of the claims of the present invention. In addition, although some specific terms are used in this specification, these terms are only for the convenience of description and do not constitute any limitation to the present invention.

Claims

1. A solid waste classification method based on a spectrometer, characterized in that: The steps include: S1. Preliminary classification: Obtain samples of unknown solid waste, observe the characteristics of the samples, and obtain characteristic information; S2, selecting a spectrometer: selecting a spectrometer according to the characteristic information; analyzing the sample using the spectrometer to obtain a spectrum; the spectrum includes a spectrum curve; S3, spectrum preprocessing: normalizing the data of the spectrum curve; S4. Similarity analysis: For the spectral curves of the multiple samples, any two samples are selected for comparison to obtain a similarity value; if the similarity value is within a preset threshold range, the two compared samples belong to the same type of solid waste.

2. A method for solid waste classification based on a spectrometer according to claim 1, characterized in that: The preliminary classification is to classify the samples according to their appearance, and the categories include liquid materials, amorphous or organic materials, high water content materials, and dark materials.

3. A method for solid waste classification based on a spectrometer according to claim 2, characterized in that: The spectrometer includes an X-ray fluorescence spectrometer, an X-ray diffractometer, a Fourier transform infrared spectrometer, and a Raman spectrometer.

4. The method for solid waste classification based on a spectrometer according to claim 1, characterized in that: The normalization process is: Wherein, y represents the ordinate value of the data point of the spectral curve; y max and min Respectively represent the maximum vertical coordinate value and the minimum vertical coordinate value; y i and i ′ Respectively represent the ordinate values ​​of the data point of the ith item of the spectral curve before and after normalization processing.

5. The method for solid waste classification based on spectrometer according to claim 1, characterized in that: The spectrum graph preprocessing also includes smoothing the data of the spectrum curve.

6. The method for solid waste classification based on spectrometer according to claim 1, characterized in that: The spectrum preprocessing also includes removing invalid peaks of the spectrum curve; and modifying the ordinate values ​​of the data points corresponding to the selected invalid peaks to preset intensity values.

7. The method for solid waste classification based on spectrometer according to claim 1, characterized in that: When the variation trend of the spectral curve is monotonous, the similarity value is calculated using the Spearman correlation coefficient, which is specifically calculated as follows: Among them, r s That is the similarity value; A i and B i They correspond to the ordinate values ​​of the two spectral curves respectively; i is the index of the ordinate value in one of the spectral curves; n represents the number of data points in one of the spectral curves; rank(·) represents the rank.

8. The method for solid waste classification based on spectrometer according to claim 1, characterized in that: When the variation trend of the spectral curve is irregular, the calculation of the similarity value includes adopting a correlation coefficient algorithm based on Euclidean distance conversion, which is specifically calculated as follows: Wherein, r is the similarity value; (x i ,y i ) and (x i ′ ,y i ′ ) represent the coordinates of the i-th data point of the two spectral curves respectively; n represents the number of data points in one spectral curve; σ x and σ y Indicates the standard deviation of all data points on the horizontal and vertical axes respectively; u x and u y represents the average value of all data points on the horizontal and vertical axes respectively; d is the Euclidean distance.

9. The method for solid waste classification based on spectrometer according to claim 1, characterized in that: The method further comprises the step: S5, cluster analysis: for a number of unclassified samples, cluster analysis algorithms are used to classify them.

10. A method for solid waste classification based on a spectrometer according to claim 9, characterized in that: The clustering algorithm is calculated as follows: Wherein, x represents the spectral curve; μ i (0) represents the center of the i-th cluster before the iteration starts; C i (t) represents the set of all data assigned to the i-th cluster in the t-th iteration; μ i (t+1) represents the center of the i-th cluster at the r+1th iteration; k represents the number of classifications; When μ i (t+1) =μ i (t) When the preset number of iterations is reached, the iteration is terminated.

Images