A recycled plastic data analysis and judgment method based on multi-dimensional detection data

Abstract

The present invention discloses a method for analyzing and determining recycled plastic data based on multi-dimensional detection data, and specifically relates to the technical field of recycled plastic detection. The method performs multi-dimensional detection on recycled plastic samples to obtain recycled plastic data, and divides the recycled plastic data into component dimension data, optical dimension data, physical dimension data, and chemical dimension data. Each dimension data is aggregated within the dimension to obtain a score for each dimension. At the same time, the weight of each dimension is set in combination with the application scenario through the AHP hierarchical analysis method or the principal component analysis method, and the weighted linear summation of each dimension score is performed accordingly to obtain a comprehensive score for the recycled plastic. The comprehensive score of the recycled plastic is compared with a preset recycled plastic score threshold to determine whether the quality of the recycled plastic is high-quality, good, qualified, or unqualified. The method realizes the scientific determination of the quality of recycled plastics through multi-dimensional data aggregation analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of recycled plastic detection, and in particular to a recycled plastic data analysis and determination method based on multi-dimensional detection data. Background Art

[0002] The recycling of recycled plastics is of great significance in resource circulation and environmental protection, and its quality assessment directly affects its application scope and value. Currently, recycled plastic quality testing technology suffers from a single testing dimension, a lack of scientific evaluation system, insufficient coverage of safety indicators, and poor adaptability to application scenarios.

[0003] Therefore, a systematic analysis method based on multi-dimensional detection data is urgently needed to achieve scientific judgment and accurate grading of recycled plastic quality. To this end, a recycled plastic data analysis and judgment method based on multi-dimensional detection data is proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a recycled plastic data analysis and judgment method based on multi-dimensional detection data to solve the problems raised in the above background technology.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] A method for analyzing and determining recycled plastic data based on multi-dimensional detection data comprises the following steps:

[0007] S1. Perform multi-dimensional testing on recycled plastic samples to obtain recycled plastic data;

[0008] S2. Divide the recycled plastic data into component dimension data, optical dimension data, physical dimension data, and chemical dimension data;

[0009] S3. Perform intra-dimensional aggregation on the component dimension data, optical dimension data, physical dimension data, and chemical dimension data to obtain component dimension scores, optical dimension scores, physical dimension scores, and chemical dimension scores. Based on this, perform inter-dimensional aggregation on the component dimension scores, optical dimension scores, physical dimension scores, and chemical dimension scores to obtain a comprehensive score for the recycled plastic;

[0010] S4. The comprehensive score of the recycled plastic is compared with the preset recycled plastic score threshold to obtain the quality of the recycled plastic.

[0011] Preferably, the method for obtaining recycled plastic data is:

[0012] The recycled plastic data includes gray content, density, FTIR spectrum data, tensile strength, elongation at break, bending length, bending modulus, odor level, heavy metal content data, yellowness index, light transmittance and haze, wherein gray content, density and FTIR spectrum data are component dimension data, tensile strength, elongation at break, bending length and bending modulus are physical dimension data, odor level, lead content, cadmium content and mercury content are chemical dimension data, and yellowness index, light transmittance and haze are optical dimension data;

[0013] Place the recycled plastic sample in a crucible in a muffle furnace and heat it to 800±25℃ at a heating rate of 10℃ per minute in an air atmosphere. Burn it for 4 hours until the recycled plastic sample is completely ashed. After cooling it to room temperature, weigh the mass of the sample residue. ,according to Gray content calculated ;

[0014] Using a density balance and Archimedes' principle, the recycled plastic sample was immersed in distilled water to measure the mass of the recycled plastic sample in air and liquid. Calculate the density, where is the mass of recycled plastic sample in air, is the mass of recycled plastic in the sample liquid, is the density of distilled water;

[0015] The recycled plastic sample was mixed with dry KBr at a mass ratio of 1:100, ground and pressed into a transparent sheet at a pressure of 10 MPa. The transparent sheet was scanned cumulatively using a Fourier transform infrared spectrometer to obtain FTIR spectrum data. ;

[0016] The recycled plastic samples were subjected to tensile and bending tests using a universal material testing machine according to GB / T 1040.2 "Determination of tensile properties of plastics" and GB / T 9341 "Determination of flexural properties of plastics" to obtain the tensile strength. , elongation at break , bending length and flexural modulus ;

[0017] Weigh 0.5g of recycled plastic sample and place it in a polytetrafluoroethylene digestion tank. Add 5mL of nitric acid and 2mL of hydrogen peroxide. Digest at 180℃ and 1500W for 30min. After cooling, dilute to 50mL and filter with a 0.45μm filter membrane to obtain the recycled plastic test solution. The recycled plastic test solution is measured by inductively coupled plasma mass spectrometry to obtain the content of lead. , cadmium content and mercury content Heavy metal content data;

[0018] The yellowness index is obtained by using a colorimeter on the recycled plastic sample and measuring the color at three different locations on the surface of the recycled plastic sample according to the ASTM D1925 standard, using a D65 light source and a 10° field of view, and taking the average value. ;

[0019] The transmittance of the recycled plastic sample was measured using a haze meter according to ASTM D1003, using a tungsten halogen lamp as the light source, a wavelength range of 380 to 780 nm and a measurement area of ​​50 mm in diameter. and haze ;

[0020] The recycled plastic sample was placed in a sealed glass container, heated in a 60°C oven for 30 minutes, and then cooled to room temperature. Five odor detectors who were trained and qualified in accordance with ISO 13725 standards smelled the gas on the top of the glass container and scored the odor in turn. The 5-level scoring method was used, where level 1 was no odor, level 2 was slightly noticeable, level 3 was clearly noticeable, level 4 was a strong odor, and level 5 was an unacceptable odor. The final odor level was 1. Take the median of the five ratings.

[0021] Preferably, the method for performing intra-dimensional aggregation on component dimension data is:

[0022] Obtain standard spectral data of the plastic type corresponding to the recycled plastic sample from the target polymer standard spectral library , where plastic types include PP, PE, HDPE, ABS or HIPS, and the standard spectral data and FTIR spectral data The FTIR spectrum similarity is calculated by the FTIR spectrum similarity formula At the same time, the gray content and density The impurity influence coefficient is obtained by calculating the impurity influence formula and density offset formula respectively. and density shift penalty ;

[0023] The FTIR spectrum similarity formula is:

[0024] ;

[0025] The impurity influence formula is:

[0026] ;

[0027] in, is the grayscale attenuation constant, which is obtained by data analysis of a large number of recycled plastic samples with known purity and fitting using the least squares method;

[0028] The density offset formula is:

[0029] ;

[0030] in, The pure standard density of the plastic type corresponding to the recycled plastic sample;

[0031] Based on FTIR spectrum similarity , impurity influence coefficient and density shift penalty , calculated by the component dimension score formula, the component dimension score of the recycled plastic sample is obtained ;

[0032] The component dimension score formula is:

[0033] ;

[0034] in, Score the component dimensions;

[0035] The target polymer standard spectrum library is used to store FTIR data of common plastic types including PP, PE, HDPE, ABS and HIPS, and the standard spectrum data of each plastic type The characteristic absorption peak distribution representing the pure polymer substance can be used to determine the purity of the components of the recycled plastic sample and whether there are impurities.

[0036] Preferably, the method for performing intra-dimensional aggregation on optical dimension data is:

[0037] Based on the optical performance standards of the plastic types corresponding to the recycled plastic samples and combined with the actual use of the recycled plastics, the ideal optical point of the yellow index is artificially set , ideal optical point of light transmittance , ideal optical point of haze , Yellow index weight , transmittance weight and fog weight , based on which the yellow index , light transmittance and haze The optical dimension score of the recycled plastic sample is calculated by the color space distance formula ;

[0038] The color space distance formula is:

[0039] ;

[0040] in, It is the maximum distance between the optical dimension data and the ideal optical point of the optical dimension data.

[0041] Preferably, the method for performing intra-dimensional aggregation on physical dimension data is:

[0042] Based on the physical performance standards of the plastic type corresponding to the recycled plastic sample, set the physical benchmark performance vector , based on which the tensile strength , elongation at break , bending length and flexural modulus Normalization is performed to obtain the physical property vector of recycled plastics ;

[0043] Physical benchmark performance vector and recycled plastic physical properties vector The physical dimension score of the recycled plastic sample is calculated by the projection formula ;

[0044] The projection formula is:

[0045] ;

[0046] in, Score the physical dimension.

[0047] Preferably, the method for performing intra-dimensional aggregation on chemical dimension data is:

[0048] Construct a safe logic gate model to convert odor levels , lead content , cadmium content and mercury content Input into the security logic gate model to get the chemical score , based on which the chemistry score Mapping to a discrete set of values The closest discrete value is taken as the chemical dimension score of the recycled plastic sample ;

[0049] The safety logic gate model is:

[0050] ;

[0051] in, The lead content standard for recycled plastics is The cadmium content standard for recycled plastics is The mercury content standard for recycled plastics is is the proportion of total metal content, is the odor level, and ;

[0052] The calculation formula for the total metal content is:

[0053] .

[0054] Preferably, the method for performing inter-dimensional aggregation on the composition dimension score, the optical dimension score, the physical dimension score and the chemical dimension score is as follows:

[0055] Through AHP or principal component analysis, combined with the application scenarios of recycled plastic samples, the component dimension weights are manually set , optical dimension weight , physical dimension weight and chemical dimension weights , based on which the component dimensions are scored , optical dimension score , physical dimension score and chemistry dimension scores The comprehensive score of recycled plastics is calculated by weighted linear summation formula ;

[0056] The weighted linear summation formula is:

[0057] ;

[0058] Among them, the component dimension weight , optical dimension weight , physical dimension weight And the chemical dimension weights satisfy ;

[0059] The AHP is a multi-criteria decision analysis method that combines qualitative and quantitative methods.

[0060] The principal component analysis method is a data-driven dimensionality reduction technology and multivariate statistical method.

[0061] Preferably, the method of judging the comprehensive score of recycled plastics by comparing it with the preset recycled plastic score threshold is as follows:

[0062] like , then the quality of the recycled plastic is high quality;

[0063] like , the quality of the recycled plastic is good;

[0064] like , then the quality of the recycled plastic is qualified;

[0065] like , the quality of the recycled plastic is unqualified.

[0066] Preferably, the chemical dimension score of the recycled plastic sample When it is zero, the comprehensive score of recycled plastics is directly obtained. The recycled plastic is of unqualified quality.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] The present invention constructs a multidimensional detection system in four dimensions: composition, optics, physics, and chemistry. It combines a scientific intra-dimensional aggregation algorithm with inter-dimensional weighted aggregation based on AHP or principal component analysis to enhance the coverage of safety indicators such as heavy metal content and odor level, and can dynamically adjust weights according to application scenarios. This solves the problems of the existing technology of single detection dimension, unscientific evaluation system, insufficient coverage of safety indicators, and poor adaptability to application scenarios, and realizes scientific judgment and precise grading of the quality of recycled plastics. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0070] Figure 1 The figure is a flow chart of the method steps of the present invention. DETAILED DESCRIPTION

[0071] To make the objectives, technical solutions, and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other implementations obtained by those of ordinary skill in the art without inventive effort are within the scope of protection of the present invention.

[0072] Examples, such as Figure 1 As shown, a method for analyzing and determining recycled plastic data based on multi-dimensional detection data includes the following steps:

[0073] S1. Perform multi-dimensional testing on recycled plastic samples to obtain recycled plastic data;

[0074] S2. Divide the recycled plastic data into component dimension data, optical dimension data, physical dimension data, and chemical dimension data;

[0075] S3. Perform intra-dimensional aggregation on the component dimension data, optical dimension data, physical dimension data, and chemical dimension data to obtain component dimension scores, optical dimension scores, physical dimension scores, and chemical dimension scores. Based on this, perform inter-dimensional aggregation on the component dimension scores, optical dimension scores, physical dimension scores, and chemical dimension scores to obtain a comprehensive score for the recycled plastic;

[0076] S4. The comprehensive score of the recycled plastic is compared with the preset recycled plastic score threshold to obtain the quality of the recycled plastic.

[0077] Furthermore, the working principle of the present invention is described below by way of examples:

[0078] A batch of recycled PP plastic particles was selected. The target application scenario is food packaging film, and special attention should be paid to chemical safety and optical properties.

[0079] The recycled plastic sample was tested in multiple dimensions. 5.00 g of the sample was placed in a muffle furnace and heated to 800 °C at 10 °C / min for 4 h. The residue was 0.05 g and the ash content was calculated. 1.0%; density balance measures the mass of recycled plastic sample in air 2.35g, mass in distilled water is 1.35g, based on which the density is calculated The FTIR spectrum data of the recycled plastic sample was obtained and compared with the PP standard spectrum data. The FTIR spectrum data of the recycled plastic sample was 2950 The characteristic peak intensity at is 90% of the PP standard spectrum data, which is calculated by the FTIR spectrum similarity formula. The tensile strength of the recycled plastic sample was tested by a universal material testing machine. 30MPa, elongation at break 400%, bending length 5mm and flexural modulus The lead content of chemically treated recycled plastic samples was measured by inductively coupled plasma mass spectrometry. The cadmium content is 5ppm Mercury content is 2ppm and The legal standard for mercury content in PP plastics is 2ppm, the legal standard for lead content in PP plastics is 10ppm, and the legal standard for cadmium content in PP plastics is 5ppm. The recycled plastic samples were processed and scored by 5 odorists, with the median score being 2, which is the odor level. The yellow index of the recycled plastic samples was measured by a colorimeter and a transmittance haze meter. 8, light transmittance 90% and haze It is 2%.

[0080] Based on tensile strength 30MPa, elongation at break 400%, bending length 5mm, flexural modulus 1000MPa, gray content 1.0%, density is 2.35g / cm³, and the FTIR spectrum is similar The lead content is 0.92 The cadmium content is 5ppm Mercury content is 2ppm and The odor level is 1ppm. 2, yellow index 8, light transmittance 90% and haze 2%, through the impurity effect formula Calculate the impurity influence coefficient is 0.99; through the density offset formula Calculate the density offset penalty =0, based on which the component dimension score is calculated using the component dimension score formula is 0; through the color space distance formula Calculate the optical dimension score is 0.629; set the physical benchmark performance vector for , and then the physical property vector of recycled plastic is obtained after normalization for , according to which the projection formula , calculate the physical dimension score About 0.0000045; passed Calculate the proportion of total metal is 0.5, based on which the chemical score is obtained through the safe logic gate model is 0.95, mapped to a discrete value set Get the chemistry dimension score is 1.

[0081] Using the AHP method, the weights of the component dimensions are set in combination with the food packaging scenario is 0.2, optical dimension weight is 0.3, the physical dimension weight is 0.2 and the chemical dimension weight is 0.3, based on which the comprehensive score of recycled plastics is obtained through the weighted linear summation formula is 0.4887, because , and the score of the ingredient dimension is abnormally low due to the density. Although the chemical dimension meets the standard, the comprehensive score is insufficient. Therefore, the recycled plastic quality of this batch of recycled PP plastic particles is unqualified.

[0082] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them. Modifications to the technical solutions described in the aforementioned embodiments, or equivalent replacements of some of the technical features therein, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for analyzing and determining recycled plastic data based on multi-dimensional detection data, characterized in that: The following steps are involved: S1. Perform multi-dimensional testing on recycled plastic samples to obtain recycled plastic data; S2. Divide the recycled plastic data into component dimension data, optical dimension data, physical dimension data, and chemical dimension data; S3. Perform intra-dimensional aggregation on the component dimension data, optical dimension data, physical dimension data, and chemical dimension data to obtain a component dimension score, an optical dimension score, a physical dimension score, and a chemical dimension score. Based on this, perform inter-dimensional aggregation on the component dimension score, the optical dimension score, the physical dimension score, and the chemical dimension score to obtain a comprehensive score for the recycled plastic; The method for performing intra-dimensional aggregation on the composition dimension data, optical dimension data, physical dimension data, and chemical dimension data is as follows: (1) Perform intra-dimensional aggregation on component dimension data: Obtain standard spectral data of the plastic type corresponding to the recycled plastic sample from the target polymer standard spectral library , the standard spectrum data and FTIR spectral data The FTIR spectrum similarity is calculated by the FTIR spectrum similarity formula At the same time, the gray content and density The impurity influence coefficient is obtained by calculating the impurity influence formula and density offset formula respectively. and density shift penalty ; Based on FTIR spectrum similarity , impurity influence coefficient and density shift penalty , calculated by the component dimension score formula, the component dimension score of the recycled plastic sample is obtained ; (2) Perform intra-dimensional aggregation on optical dimension data: Based on the optical performance standards of the plastic type corresponding to the recycled plastic sample and combined with the actual use of the recycled plastic, the ideal optical point of the yellow index is manually set. , ideal optical point of light transmittance , ideal optical point of haze , Yellow index weight , transmittance weight and fog weight , based on which the yellow index , light transmittance and haze The optical dimension score of the recycled plastic sample is calculated by the color space distance formula ; (3) Perform intra-dimensional aggregation on physical dimension data: Based on the physical performance standards of the plastic types corresponding to the recycled plastic samples, set the physical benchmark performance vector , based on which the tensile strength , elongation at break , bending length and flexural modulus Normalization is performed to obtain the physical property vector of recycled plastics , the physical benchmark performance vector and recycled plastic physical properties vector The physical dimension score of the recycled plastic sample is calculated by the projection formula ; (4) Perform dimension aggregation on chemical dimension data: Build a safe logic gate model to convert odor levels , lead content , cadmium content and mercury content Input into the security logic gate model to get the chemical score , based on which the chemistry score Mapping to a discrete set of values The closest discrete value is taken as the chemical dimension score of the recycled plastic sample ; S4. The comprehensive score of the recycled plastic is compared with the preset recycled plastic score threshold to obtain the quality of the recycled plastic.

2. The method for analyzing and determining recycled plastic data based on multi-dimensional detection data according to claim 1, characterized in that: The method for obtaining recycled plastic data: The recycled plastic data includes gray content, density, FTIR spectrum data, tensile strength, elongation at break, bending length, bending modulus, odor level, heavy metal content data, yellowness index, light transmittance and haze; The recycled plastic sample is placed in a muffle furnace and burned at high temperature to obtain a sample residue. The gray content is obtained based on the weight of the sample residue and the weight of the recycled plastic sample. The same recycled plastic sample is measured by a density balance, a Fourier transform infrared spectrometer, a universal material testing machine, an inductively coupled plasma mass spectrometer, a colorimeter, and a transmittance haze meter to obtain density, FTIR spectrum data, tensile strength, elongation at break, bending length, bending modulus, heavy metal content data, yellowness index, transmittance, and haze, wherein the heavy metal content data includes lead content, cadmium content, and mercury content; For the odor level, professionally trained odor assessors use sensory evaluation to classify the odor of recycled plastic samples and obtain the odor level.

3. The method for analyzing and determining recycled plastic data based on multi-dimensional detection data according to claim 2, characterized in that: The compositional dimension data include grayscale content, density and FTIR spectrum data, the physical dimension data include tensile strength, elongation at break, bending length and bending modulus, the chemical dimension data include odor level, lead content, cadmium content and mercury content, and the optical dimension data include yellowness index, transmittance and haze.

4. The method for analyzing and determining recycled plastic data based on multi-dimensional detection data according to claim 1, characterized in that: The types of plastics corresponding to the recycled plastic samples include PP, PE, HDPE, ABS or HIPS.

5. The method for analyzing and determining recycled plastic data based on multi-dimensional detection data according to claim 1, characterized in that: The method for performing inter-dimensional aggregation on the composition dimension score, the optical dimension score, the physical dimension score and the chemical dimension score: Through AHP or principal component analysis, combined with the application scenarios of recycled plastic samples, the component dimension weights are manually set , optical dimension weight , physical dimension weight and chemical dimension weights , based on which the component dimensions are scored , optical dimension score , physical dimension score and chemistry dimension scores The comprehensive score of recycled plastics is calculated by weighted linear summation formula .

6. The method for analyzing and determining recycled plastic data based on multi-dimensional detection data according to claim 5, characterized in that: The method for judging the comprehensive score of recycled plastics and the preset recycled plastic score threshold: like , then the quality of the recycled plastic is high quality; like , the quality of the recycled plastic is good; like , then the quality of the recycled plastic is qualified; like , the quality of the recycled plastic is unqualified.

7. The method for analyzing and determining recycled plastic data based on multi-dimensional detection data according to claim 6, characterized in that: Chemical dimension scores of the recycled plastic samples When it is zero, the comprehensive score of recycled plastics is directly obtained. The recycled plastic is of unqualified quality.

Images