Mixed plastic sorting system and method based on infrared spectrum

Abstract

The invention discloses a mixed plastic sorting system and method based on an infrared spectrum, relates to the technical field of plastic sorting, and solves the technical problems that existing sorting equipment is low in sorting precision, poor in sorting effect on complex mixed plastic, complex in technological process and high in cost. The method comprises the following steps: acquiring standard infrared spectrum curves of various types of plastics; based on the standard infrared spectrum curve, analyzing standard spectrum information of various types of plastics; identifying an absorption characteristic peak of the to-be-classified plastic, and obtaining spectral information of the to-be-classified plastic; comparing the spectral information of the to-be-classified plastic with standard spectral information, and judging the type of the to-be-classified plastic; images of to-be-classified plastics are collected, and the quality of the to-be-classified plastics is analyzed; classifying the to-be-classified plastic according to the type and quality of the to-be-classified plastic; according to the invention, the sorting of the mixed plastic can be efficiently and accurately realized, and an advanced technical means is provided for the plastic recycling industry.

Description

Technical Field

[0001] The present invention belongs to the field of plastic sorting, and specifically relates to a mixed plastic sorting system and method based on infrared spectroscopy. Background Art

[0002] In the plastic recycling industry, the sorting of mixed plastics has always been a key problem. Existing equipment such as color sorters and separators mainly sorts materials based on appearance features such as color and shape. However, these methods have obvious limitations. On the one hand, for plastics with similar colors, similar appearances but different materials, existing sorting equipment is difficult to accurately distinguish, resulting in low sorting accuracy, low purity of recycled plastics, and affecting the subsequent processing and utilization value. On the other hand, existing sorting equipment cannot effectively identify the true material of some plastics whose appearances have changed after being dyed, aged, etc., causing sorting errors and reducing the sorting efficiency. In addition, when traditional separators process complex mixed plastics, multiple pieces of equipment are often required to cooperate, the process flow is complex, and the cost is high.

[0003] Therefore, the present invention provides a mixed plastic sorting system and method based on infrared spectroscopy. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; for this purpose, the present invention proposes a mixed plastic sorting system and method based on infrared spectroscopy to solve the technical problems of low sorting accuracy of existing sorting equipment, poor sorting effect on complex mixed plastics, complex process flow, and high cost.

[0005] To achieve the above object, the first aspect of the present invention provides a method for sorting mixed plastics based on infrared spectroscopy, including:

[0006] Obtain the standard infrared spectral curves of various types of plastics; based on the standard infrared spectral curves, analyze the standard spectral information of various types of plastics; wherein, the standard spectral information includes the standard peak value, standard area, and standard position information of the characteristic absorption peaks;

[0007] Identify the absorption characteristic peaks of the plastics to be classified, and obtain the spectral information of the plastics to be classified; compare the spectral information of the plastics to be classified with the standard spectral information to determine the type of the plastics to be classified; wherein, the spectral information includes the peak value, area, and position information of the characteristic absorption peaks; and,

[0008] Collect images of the plastics to be classified and analyze the quality of the plastics to be classified;

[0009] Classify the plastics to be classified according to the type and quality of the plastics to be classified.

[0010] Preferably, the obtaining of the standard infrared spectral curves of various types of plastics includes:

[0011] Extract a number of plastic samples of each type and obtain the infrared spectral curves of plastic samples of each type;

[0012] Divide the infrared spectral curves into several segments according to the changing trend, and extract several coordinate points from each segment of the curve; among them, the abscissas of the coordinate points extracted from the infrared spectral curves of the same type are the same;

[0013] Extract the ordinate values corresponding to the same abscissa from the infrared spectral curves of the same type, and the median of the ordinate values is marked as the standard ordinate value; the abscissa and the standard ordinate value form a standard coordinate point; among them, the infrared spectral curves of the same type are the infrared spectral curves of the same type of plastic.

[0014] Fit a number of standard coordinate points to obtain the standard infrared spectral curves of each type of plastic.

[0015] In the present invention, for the infrared spectral curves of the same type, coordinate points with the same abscissa are extracted, and the median of the ordinate values of these points is calculated as the standard ordinate value to form standard coordinate points. This process unifies the original infrared spectral data of different samples of the same type under the same standard, eliminates the measurement value differences caused by factors such as experimental conditions and instrument responses between different samples, makes the data of different samples comparable, provides a high-quality and standardized data basis for the subsequent fitting of the standard infrared spectral curves. Based on the standard coordinate points, the standard infrared spectral curves of each type of plastic are obtained. Since the standard coordinate points have undergone data standardization processing, excluding the interference of outliers and random errors, they can more accurately reflect the common characteristics and changing laws of the infrared spectra of the same type of plastic, so that the fitted standard infrared spectral curves are closer to the actual situation, improving the accuracy and reliability of curve fitting.

[0016] Preferably, the analysis of the standard spectral information of each type of plastic includes:

[0017] Based on the standard infrared spectral curve, obtain the peak value, area and position information of the characteristic absorption peak; among them, the position information of the characteristic absorption peak includes the sharp peak position, starting position, ending position and full width at half maximum; the starting position is the position where the characteristic absorption peak starts, and the ending position is the position where the characteristic absorption peak ends;

[0018] The area calculation of the characteristic absorption peak is as follows:

[0019] Extract several coordinate points from the characteristic absorption peak, and construct the curve equation of the characteristic absorption peak based on curve equation fitting; based on the starting position and ending position of the absorption characteristic peak, integrate the curve equation to obtain the standard area of the characteristic absorption peak.

[0020] The present invention determines the highest point position, starting position, ending position, and full width at half maximum of the characteristic absorption peak, and obtains the area of the characteristic absorption peak through curve equation fitting and integral calculation. By comprehensively considering the shape and intensity of the absorption peak, it can more accurately reflect the total amount of chemical bonds or functional groups represented by the characteristic absorption peak. Compared with only using the peak value, the area calculation can better reflect the overall information of the absorption peak and reduce the error caused by the irregular shape of the absorption peak. Extracting several coordinate points from the characteristic absorption peak and constructing the curve equation of the characteristic absorption peak based on curve equation fitting can more accurately describe the shape and change trend of the absorption peak. Compared with simple linear fitting or polynomial fitting, using a more appropriate curve equation can better fit the actual infrared spectrum absorption peak and improve the accuracy of calculation.

[0021] Preferably, the identification of the absorption characteristic peak of the plastic to be classified includes:

[0022] Based on the standard spectral information, extract the peak values of the characteristic absorption peaks of various types of plastics to obtain a peak value sequence; among them, the peak values in the peak value sequence are different;

[0023] Extract the peak to be identified from the infrared spectrum curve of the plastic to be classified, calculate the difference between the peak value of the peak to be identified and each peak value in the peak value sequence, and determine whether the difference is less than the difference threshold; if so, mark the peak to be identified as a characteristic absorption peak; if not, do not mark it; among them, the peak to be identified is the maximum point in the infrared spectrum curve of the plastic to be classified.

[0024] The standard spectral information of the present invention has been verified by a large number of samples and scientifically analyzed. The peak values of its characteristic absorption peaks are representative and stable. By extracting the peak values in the standard spectral information to form a peak value sequence, it provides a reliable reference standard for the identification of the characteristic absorption peaks of the plastic to be classified, and allows for a small difference between the peak value of the peak to be identified and each peak value in the peak value sequence, effectively avoiding misjudgment caused by factors such as measurement errors and instrument fluctuations.

[0025] Preferably, the discrimination of the type of the plastic to be classified includes:

[0026] Count the number of peak values that are the same between the peak values of the plastic to be classified and the standard peak values of various types of plastics. The plastic type with the number of the same peak values exceeding the number threshold is the candidate type of the plastic to be classified;

[0027] Calculate the absolute value of the area difference between the area of the characteristic absorption peak of the plastic to be classified and the standard area of each same absorption characteristic peak in the candidate type, and calculate the ratio of the absolute value of the area difference to the standard area of the same absorption characteristic peak to obtain the area difference rate;

[0028] Calculate the absolute value of the difference between the position information of the absorption characteristic peaks of the plastic to be classified and the standard position information of each identical absorption characteristic peak in the candidate types, and sum the ratios with the corresponding standard position information of the identical absorption characteristic peaks to obtain the position difference rate;

[0029] Calculate the weighted sum between the difference rate and the position difference rate to obtain the similarity index; determine the type of the plastic to be classified based on the similarity index.

[0030] The present invention comprehensively considers three characteristic dimensions of peak value, area, and position information to evaluate the similarity between the plastic to be classified and the standard plastics of each type. This multi-dimensional matching method can more comprehensively and accurately reflect the characteristics of plastics, avoid the deviation that may be brought by single-characteristic matching, and thus improve the accuracy and reliability of classification. For example, relying solely on peak matching may lead to misjudgment due to similar peak values but large differences in area or position, while this method can effectively reduce the probability of such situations by integrating multiple characteristics.

[0031] Preferably, the difference between the peak value of the to-be-identified peak and the standard peak value of the identical absorption characteristic peak is less than the difference threshold.

[0032] Preferably, the weight coefficients of the area and position information of the characteristic absorption peaks are obtained through the following methods, including:

[0033] Extract several plastic samples of each type, and calculate the mean and variance of the spectral information of the plastic samples of each type;

[0034] Through the formula Calculate the importance degree FDR of the plastic spectral information; where i is the plastic type, k is the area or position information of the absorption characteristic peak, usually represented by natural numbers; uik is the mean of the spectral information k of the i-type plastic, sik is the standard spectral information k of the i-type plastic, and σi k is the variance of the spectral information k of the i-type plastic, and Σ is the summation of k;

[0035] Based on the importance degree, determine the weight coefficients of the area and position information of the characteristic absorption peaks.

[0036] The present invention standardizes the characteristic differences into comparable values by calculating the difference between the spectral information mean and the standard value and dividing by the sum of the squares of the variances, effectively integrating the absorption peak area and position information, realizing the quantitative evaluation of the importance degree of characteristics through weight assignment, and assigning weight coefficients based on the calculation results, which can be dynamically adjusted according to the sensitivity of different plastic types to the area and position information. For example, in the classification of polyvinyl chloride (PVC), if the position information has a greater impact on the classification, its weight coefficient can be increased; if the area characteristic is more critical, the weight can be increased accordingly. This dynamic adjustment mechanism enables the classification model to adapt to the characteristics of different plastic types and improves the classification accuracy and flexibility.

[0037] Preferably, analyzing the quality of the plastic to be classified includes:

[0038] Inputting the image of the plastic to be classified into a quality evaluation model, and the quality evaluation model outputs a quality label for the plastic to be classified; wherein, the quality label includes a good label and a defect label, and the quality evaluation model is constructed by an artificial intelligence model.

[0039] Preferably, the quality evaluation model is constructed by an artificial intelligence model, including:

[0040] Obtaining a plurality of plastic images of various types and corresponding quality labels, and marking the defects in the plastic images to obtain marked images;

[0041] Integrating the marked images and quality labels into a plurality of sets of training data and test data; training the artificial intelligence model using the training data; testing the trained artificial intelligence model using the test data, and adjusting the artificial intelligence model according to the test results; finally obtaining a quality evaluation model with the marked image as the input and the quality label as the output; wherein, the artificial intelligence model is a BP neural network model or an RBF neural network model.

[0042] Preferably, a second aspect of the present invention provides a sorting system for mixed plastics based on infrared spectroscopy, including an analysis module and a classification module;

[0043] Analysis module: used to obtain the standard infrared spectral curves of various types of plastics; based on the standard infrared spectral curves, analyze the standard spectral information of various types of plastics; wherein, the standard spectral information includes the standard peak value, standard area, and standard position information of the characteristic absorption peak;

[0044] Identifying the absorption characteristic peaks of the plastic to be classified, obtaining the spectral information of the plastic to be classified; comparing the spectral information of the plastic to be classified with the standard spectral information to determine the type of the plastic to be classified; and,

[0045] Collecting the image of the plastic to be classified and analyzing the quality of the plastic to be classified;

[0046] Classification module: used to classify the plastic to be classified according to the type and quality of the plastic to be classified.

[0047] Compared with the prior art, the beneficial effects of the present invention are:

[0048] The present invention obtains the standard infrared spectral curves of various types of plastics and deeply analyzes their standard spectral information, including the standard peak values, standard areas, and standard position information of characteristic absorption peaks, providing an accurate reference benchmark for subsequent classification. After identifying the absorption characteristic peaks of the plastics to be classified and obtaining their spectral information, a detailed comparison with the standard spectral information can accurately determine the types of the plastics to be classified. Compared with the existing sorting machines based on color and shape, the present invention, based on infrared spectroscopy technology, can accurately identify plastics of different materials, and even plastics with similar colors and appearances can be effectively distinguished, greatly improving the sorting accuracy. In addition to spectral information, the present invention also collects images of the plastics to be classified and analyzes their quality. This multi-dimensional evaluation method not only considers the spectral information of the plastics but also takes into account the quality analysis of the plastics, making the classification results more comprehensive and reliable, and contributing to more targeted processing and utilization of the plastics in the future. The present invention has good adaptability to different types of plastics. Whether it is common polyethylene, polypropylene, or other special plastics, accurate classification can be achieved through the establishment and comparison of standard spectral curves, greatly improving the sorting efficiency and accuracy, reducing labor costs, and having significant economic benefits and application values. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0050] Figure 1 It is a schematic flowchart of the method of the present invention;

[0051] Figure 2 It is a schematic flowchart of the method for obtaining the standard infrared spectral curves of various types of plastics of the present invention;

[0052] Figure 3 It is a schematic flowchart of the method for determining the types of plastics to be classified of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0054] Please refer to Figure 1 , the first aspect embodiment of the present invention provides a method for sorting mixed plastics based on infrared spectroscopy, including:

[0055] Obtain the standard infrared spectral curves of various types of plastics;

[0056] Please refer to Figure 2 , specifically, extract several samples of various types of plastics and obtain the infrared spectral curves of the various types of plastic samples;

[0057] Divide the infrared spectral curves into several segments according to the changing trend, and extract several coordinate points from each segment of the curve; among them, the abscissas of the coordinate points extracted from the infrared spectral curves of the same type are the same;

[0058] Extract the ordinate values corresponding to the same abscissa from the infrared spectral curves of the same type, and the median of the ordinate values is marked as the standard ordinate value; the abscissa and the standard ordinate value form the standard coordinate point; among them, the infrared spectral curves of the same type are the infrared spectral curves of the same type of plastic;

[0059] Fit several standard coordinate points to obtain the standard infrared spectral curves of various types of plastics.

[0060] For example: Suppose to obtain the standard infrared spectral curve of PE type plastic; collect the infrared spectral curves of several PE plastics, such as supermarket shopping bags, mineral water bottles, food wraps, PE films, and PE packaging materials, and use a Fourier transform infrared spectrometer to scan each sample to obtain 5 infrared spectral curves of PE plastics; among them, the abscissa: wave number cm-1, the ordinate: absorbance;

[0061] Divide the infrared spectral curves into several segments according to the changing trend, and traverse the changing trend from (0, 0) in sequence. If the infrared spectral curve of a certain plastic sample is a smooth trend from (0, 0) to (x1, y1) and an upward trend from (x1, y1) to (x2, y2), then (0, 0) to (x1, y1) is one segment, and (x1, y1) to (x2, y2) is one segment. Traverse all the coordinate points in sequence, and the infrared spectral curve is divided into several segments;

[0062] Extract several coordinate points on each segment of the curve. If the coordinate points extracted from the infrared spectral curve of a certain PE plastic sample in the segment from (0, 0) to (x1, y1) are (x10, y10), (x11, y11),..., (xn, yn) for a total of n points, where n is a positive integer; the coordinate points with abscissas of x10, x11,..., xn are extracted from the other plastic samples of the same type respectively; there are several ordinate values corresponding to the x10 point of several infrared spectral curves. Extract the median of the several ordinate values and mark it as the standard ordinate value; (x10, standard ordinate value) is the standard coordinate point; the corresponding standard coordinate points for the remaining x11,..., xn are obtained in the same way, and several standard coordinate points of this segment of the curve are obtained;

[0063] Obtain several standard coordinate points of the remaining curve segments in this way, and fit the several standard coordinate points of the several curve segments to obtain the standard infrared spectrum curve of the PE type plastic.

[0064] Based on the standard infrared spectrum curve, analyze the standard spectral information of various types of plastics; among them, the standard spectral information includes the standard peak value, standard area, and standard position information of the characteristic absorption peak;

[0065] Specifically, based on the standard infrared spectrum curve, obtain the standard peak value and standard position information of the characteristic absorption peak;

[0066] Among them, the standard position information of the characteristic absorption peak includes the peak position, starting position, ending position, and full width at half maximum; the starting position is the position where the characteristic absorption peak starts, and the ending position is the position where the characteristic absorption peak ends;

[0067] The area calculation of the characteristic absorption peak is as follows:

[0068] Extract several coordinate points from the characteristic absorption peak, and construct the curve equation of the characteristic absorption peak based on polynomial equation fitting; based on the starting position and ending position of the absorption characteristic peak, integrate the curve equation to obtain the standard area of the characteristic absorption peak.

[0069] For example: Take a certain PE plastic as an example, extract the peak point at 2920 cm-1 of the standard infrared curve, and determine the starting / ending position. Starting position: Scan left from 2920 cm-1 to find the wave number (assumed to be 2950 cm-1) where the absorbance drops to the baseline (such as 0.05); Ending position: Scan right from 2920 cm-1 to find the wave number where the absorbance drops to the baseline (assumed to be 2850 cm-1).

[0070] Calculate the full width at half maximum: Half height = peak absorbance × 0.5 = 0.85 × 0.5 = 0.425; Find the wave numbers corresponding to the absorbance = 0.425 on both sides of the peak (such as 2940 cm-1 and 2900 cm-1), full width at half maximum = 2940 – 2900 = 40 cm-1; Uniformly select 10 wave number points and their absorbances (from the standard infrared spectrum curve) in the range of 2850 – 2950 cm-1: Construct the curve equation of the characteristic absorption peak at 2920 cm-1 of this PE plastic according to polynomial equation fitting, marked as A(x); Through Calculate to obtain the area of the characteristic absorption peak at 2920 cm-1; among them, B is the initial position of this characteristic absorption peak, and C is the ending position of this characteristic absorption peak.

[0071] Identify the absorption characteristic peaks of the plastic to be classified, and obtain the spectral information of the plastic to be classified;

[0072] Based on the standard spectral information, extract the peak values of the characteristic absorption peaks of various types of plastics to obtain a peak value sequence; among them, the peak values in the peak value sequence are different;

[0073] Extract the peak to be recognized from the infrared spectrum curve of the plastic to be classified, calculate the difference between the peak value of the peak to be recognized and each peak value in the peak value sequence, and determine whether the difference is less than the difference threshold; if so, mark the peak to be recognized as a characteristic absorption peak; among them, the peak to be recognized is the maximum point in the infrared spectrum curve of the plastic to be classified.

[0074] For example, based on the standard infrared spectral information, assume that the peak values of the characteristic absorption peaks of PE (polyethylene), PP, and PVC (polyvinyl chloride) plastics are extracted to form a peak value sequence; among them, only one of the same peak values is retained;

[0075] Taking PVC (polyvinyl chloride) as an example, Table 1 shows the matching relationship between the plastic to be classified and the standard peak values of the PVC type;

[0076] Table 1 shows the matching relationship between the plastic to be classified and the standard peak values of the PVC type

[0077]

[0078]

[0079] Compare the spectral information of the plastic to be classified with the standard spectral information to determine the type of the plastic to be classified;

[0080] Please refer to Figure 3 , specifically, count the number of the same peak values between the peak values of the plastic to be classified and the standard peak values of each type of plastic, and the plastic type with the number of the same peak values exceeding the quantity threshold is the candidate type of the plastic to be classified;

[0081] Calculate the absolute value of the area difference between the area of the characteristic absorption peak of the plastic to be classified and the standard area of each same absorption characteristic peak in the candidate type, and calculate the ratio of the absolute value of the area difference to the standard area of the same absorption characteristic peak to obtain the area difference rate;

[0082] Calculate the absolute value of the difference between the position information of the absorption characteristic peak of the plastic to be classified and the standard position information of each same absorption characteristic peak in the candidate type, and sum the ratios with the corresponding standard position information of the same absorption characteristic peak to obtain the position difference rate; among them, the same absorption characteristic peak value is that the difference between the peak value of the peak to be recognized and the standard peak value is less than the difference threshold;

[0083] Calculate the weighted sum between the difference rate and the position difference rate to obtain the similarity index; determine whether the similarity index is greater than a preset similarity threshold; if so, the absorption characteristic peaks of the plastic to be classified match the absorption characteristic peaks of the candidate type; if not, the absorption characteristic peaks of the plastic to be classified do not match the absorption characteristic peaks of the candidate type;

[0084] Count the number of matching absorption characteristic peaks between the plastic to be classified and each candidate type; determine whether the number of matching absorption characteristic peaks is greater than the matching number threshold; if so, the candidate type is the type of the plastic to be classified; if not, the candidate type is not the type of the plastic to be classified.

[0085] Among them, the weight coefficients of the area and position information of the characteristic absorption peaks are obtained through the following methods, including:

[0086] Extract several plastic samples of each type, and calculate the mean and variance of the spectral information of each type of plastic sample;

[0087] Through the formula Calculate the importance degree FDR of the plastic spectral information; where, i is the plastic type, k is the area or position information of the absorption characteristic peak, uik is the mean of the spectral information k of the i-type plastic, sik is the standard spectral information k of the i-type plastic, and σi k is the variance of the spectral information k of the i-type plastic;

[0088] Based on the importance degree, determine the weight coefficients of the area and position information of the characteristic absorption peaks.

[0089] For example: Assume that the number of the same peaks (cm -1 ) between the peak of a plastic to be classified and the standard peaks of PE, PP, and PVC type plastics is shown in Table 2: If the difference threshold: ±10 cm -1 , and the quantity threshold: ≥3 matching peaks;

[0090] Table 2 The number of the same peaks between the peak of a plastic to be classified and the standard peaks of PE, PP, and PVC type plastics

[0091]

[0092] Result: PE and PVC are the candidate types of the plastic to be classified.

[0093] Calculate the area difference rate between each pair of matching characteristic peaks: For example, the area difference rate of the matching peaks between the plastic to be classified and PE = ∣the area of the peak to be identified at 2918 - the area of the absorption characteristic peak at 2920 of PE∣ / the area of the absorption characteristic peak at 2920 of PE; the rest are calculated in the same way;

[0094] It should be noted that the matching peaks between the plastic to be classified and PE are the absorption characteristic peaks with the same peak value.

[0095] Calculate the position difference rate: The position information includes the peak position and the full width at half maximum. Calculate the ratio of the sum of the absolute differences to the standard value. For example, the position difference rate of the matching peak between the plastic to be classified and PE = |the peak position of the peak to be identified at 2918 - the peak position of the absorption characteristic peak of PE at 2920| / the peak position of the absorption characteristic peak of PE at 2920 + |the full width at half maximum of the peak to be identified at 2918 - the full width at half maximum of the absorption characteristic peak of PE at 2920| / the full width at half maximum of the absorption characteristic peak of PE at 2920 + |the initial position of the peak to be identified at 2918 - the initial position of the absorption characteristic peak of PE at 2920| / the initial position of the absorption characteristic peak of PE at 2920 + |the termination position of the peak to be identified at 2918 - the termination position of the absorption characteristic peak of PE at 2920| / the termination position of the absorption characteristic peak of PE at 2920;

[0096] Calculate the weight coefficients of the area of the absorption characteristic peak and the position information. If the FDR of the area is greater than the FDR of the position information, then the weight coefficient of the position is greater than the weight coefficient of the position information; otherwise, the weight coefficient of the position is less than or equal to the weight coefficient of the position information;

[0097] Similarity index = w1 × area difference rate + w2 × position difference rate; where w1 and w2 are the weight coefficients of the area difference rate and the position difference rate respectively.

[0098] Assume that the similarity index between the plastic to be classified and PE is less than the similarity index threshold, then the type of the plastic to be classified is the PE material.

[0099] Collect the image of the plastic to be classified and analyze the quality of the plastic to be classified;

[0100] Input the image of the plastic to be classified into the quality assessment model, and the quality assessment model outputs the quality label of the plastic to be classified; where the quality assessment model is constructed by an artificial intelligence model, and the quality label includes a good label and a defect label, usually represented by "0" and "1" respectively.

[0101] Among them, the quality assessment model is constructed by an artificial intelligence model, including:

[0102] Obtain a number of plastic images of various types and their corresponding quality labels, and mark the defects in the plastic images to obtain marked images;

[0103] Integrate the marked images and quality labels into several groups of training data and test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model according to the test results; finally obtain a quality evaluation model with the marked image as the input and the quality label as the output; wherein, the artificial intelligence model is a BP neural network model or an RBF neural network model.

[0104] Classify the plastics to be classified according to the type and quality of the plastics to be classified;

[0105] Specifically, classify plastics of the same type, and further divide the plastics of the same type into plastics with good quality and plastics with defects.

[0106] The second aspect of the present invention provides a sorting system for mixed plastics based on infrared spectroscopy, including an analysis module and a classification module;

[0107] The analysis module obtains the standard infrared spectral curves of various types of plastics; based on the standard infrared spectral curves, analyzes the standard spectral information of various types of plastics; wherein, the standard spectral information includes the standard peak value, standard area and standard position information of the characteristic absorption peak;

[0108] Identify the absorption characteristic peaks of the plastics to be classified, and obtain the spectral information of the plastics to be classified; compare the spectral information of the plastics to be classified with the standard spectral information to determine the type of the plastics to be classified; and,

[0109] Collect the images of the plastics to be classified and analyze the quality of the plastics to be classified;

[0110] The classification module classifies the plastics to be classified according to the type and quality of the plastics to be classified.

[0111] Some of the data in the above formula are calculated by removing the dimension and taking its numerical value. The formula is obtained by software simulation of a large amount of collected data to get a formula closest to the actual situation; the preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained by simulation of a large amount of data.

[0112] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A mixed plastic sorting method based on infrared spectroscopy, characterized in that: include: Obtaining standard infrared spectrum curves of various types of plastics; analyzing standard spectrum information of various types of plastics based on the standard infrared spectrum curves; wherein the standard spectrum information includes standard peak value, standard area and standard position information of characteristic absorption peaks; Identify the absorption characteristic peaks of the plastic to be classified and obtain the spectrum information of the plastic to be classified; compare the spectrum information of the plastic to be classified with the standard spectrum information to determine the type of the plastic to be classified; and, Collect images of plastics to be classified and analyze the quality of the plastics to be classified; The plastics to be sorted are sorted according to their type and quality.

2. The mixed plastic separation method based on infrared spectroscopy according to claim 1, characterized in that: The method of obtaining standard infrared spectrum curves of various types of plastics includes: Extract a number of plastic samples of various types and obtain infrared spectrum curves of the plastic samples of various types; The infrared spectrum curve is divided into several sections according to the variation trend, and several coordinate points are extracted from each section of the curve; wherein the coordinate points extracted from the same type of infrared spectrum curve have the same horizontal coordinates; Extract the ordinate value corresponding to the same abscissa from the same type of infrared spectrum curve, and mark the median of the ordinate value as the standard ordinate value; the abscissa and the standard ordinate value constitute the standard coordinate point; wherein the same type of infrared spectrum curve is the infrared spectrum curve of the same type of plastic; Several standard coordinate points are fitted to obtain the standard infrared spectrum curves of various types of plastics.

3. The mixed plastic separation method based on infrared spectroscopy according to claim 1, characterized in that: The standard spectral information for analyzing various types of plastics includes: Based on the standard infrared spectrum curve, the peak value, area and position information of the characteristic absorption peak are obtained; wherein the position information of the characteristic absorption peak includes the peak position, the starting position, the ending position and the half-height width; the starting position is the starting position of the characteristic absorption peak, and the ending position is the ending position of the characteristic absorption peak; The area of ​​the characteristic absorption peak is calculated as follows: A number of coordinate points are extracted from the characteristic absorption peak, and the curve equation of the characteristic absorption peak is constructed based on the curve equation fitting; based on the starting position and the ending position of the absorption characteristic peak, the curve equation is integrated to obtain the standard area of ​​the characteristic absorption peak.

4. The mixed plastic separation method based on infrared spectroscopy according to claim 1, characterized in that: The step of identifying the absorption characteristic peaks of the plastics to be classified comprises: Based on the standard spectrum information, the peak values ​​of characteristic absorption peaks of various types of plastics are extracted to obtain a peak sequence; wherein the peak values ​​in the peak sequence are different; Extract the peak to be identified from the infrared spectrum curve of the plastic to be classified, calculate the difference between the peak value of the peak to be identified and each peak value in the peak sequence, and judge whether the difference is less than the difference threshold; if yes, mark the peak to be identified as a characteristic absorption peak; if not, do not mark it; wherein, the peak to be identified is the maximum point in the infrared spectrum curve of the plastic to be classified.

5. The mixed plastic separation method based on infrared spectroscopy according to claim 4 is characterized in that: The method of determining the type of plastic to be classified includes: The number of peaks that are identical between the peak of the plastic to be classified and the standard peak of each type of plastic is counted, and the plastic type whose number of identical peaks exceeds the quantity threshold is the candidate type of the plastic to be classified; Calculate the absolute value of the area difference between the area of ​​the characteristic absorption peak of the plastic to be classified and the standard area of ​​each identical absorption characteristic peak in the candidate type, and calculate the ratio of the absolute value of the area difference to the standard area of ​​the identical absorption characteristic peak to obtain the area difference rate; Calculate the absolute value of the difference between the position information of the absorption characteristic peak of the plastic to be classified and the standard position information of each same absorption characteristic peak in the candidate type, and sum the ratio with the corresponding standard position information of the same absorption characteristic peak to obtain the position difference rate; The weighted sum of the difference rate and the position difference rate is calculated to obtain a similarity index; and the type of the plastic to be classified is determined based on the similarity index.

6. The mixed plastic separation method based on infrared spectroscopy according to claim 5, characterized in that: The same absorption characteristic peak is a peak to be identified, and the difference between the peak and the standard peak is less than a difference threshold.

7. The mixed plastic separation method based on infrared spectroscopy according to claim 5, characterized in that: The weight coefficients of the area and position information of the characteristic absorption peak are obtained by: Extract a number of plastic samples of each type, and calculate the mean and variance of the spectral information of each type of plastic sample; By formula The importance degree FDR of plastic spectral information is calculated; where i is the plastic type, k is the area or position information of the absorption characteristic peak, uik is the mean of the spectral information k of type i plastic, sik is the standard spectral information k of type i plastic, σi k is the variance of the spectral information k of type i plastic; Based on the importance, the weight coefficients of the area and position information of the characteristic absorption peak are determined.

8. The mixed plastic separation method based on infrared spectroscopy according to claim 1, characterized in that: The analysis of the quality of the plastics to be sorted includes: The image of the plastic to be classified is input into the quality assessment model, and the quality assessment model outputs the quality label of the plastic to be classified; wherein the quality label includes a good label and a defective label, and the quality assessment model is constructed by an artificial intelligence model.

9. The mixed plastic separation method based on infrared spectroscopy according to claim 8, characterized in that: The quality assessment model is constructed by an artificial intelligence model, including: Acquire a number of plastic images of various types and corresponding quality labels, and mark defects in the plastic images to obtain marked images; Integrate the labeled images and quality labels into several groups of training data and test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model according to the test results; finally obtain a quality assessment model with the labeled image as input and the quality label as output; wherein the artificial intelligence model is a BP neural network model or a RBF neural network model.

10. A mixed plastic sorting system based on infrared spectroscopy, operated based on the mixed plastic sorting method based on infrared spectroscopy according to any one of claims 1 to 9, characterized in that: Includes analysis module and classification module; Analysis module: used to obtain standard infrared spectrum curves of various types of plastics; based on the standard infrared spectrum curves, analyze the standard spectrum information of various types of plastics; wherein the standard spectrum information includes the standard peak value, standard area and standard position information of the characteristic absorption peak; Identify the absorption characteristic peaks of the plastic to be classified and obtain the spectrum information of the plastic to be classified; compare the spectrum information of the plastic to be classified with the standard spectrum information to determine the type of the plastic to be classified; and, Collect images of plastics to be classified and analyze the quality of the plastics to be classified; Classification module: used to classify the plastics to be classified according to their type and quality.

Images