Method for discriminating multiple waste plastic kinds by adopting near infrared spectrum characteristic wavelength

A near-infrared spectroscopy and waste plastic technology, which is applied in the direction of material analysis, analysis materials, and measurement devices by optical means, can solve the problems of complex operation process, cumbersome spectral processing process, and increased calculation time, and achieves simple analysis process. The effect of saving calculation time and reducing the amount of calculation

Inactive Publication Date: 2015-04-08
TIANJIN UNIV
View PDF3 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (1) Secondary pollution and corrosion of equipment will occur in the process of burning heat, and a large amount of harmful gas and black smoke will be produced.
At present, the technology of combustion heat extraction in our country is still immature, and a large amount of funds are needed to support incineration equipment.
[0006] (2) The failure of the catalyst in the catalytic cracking process. Due to the poor thermal conductivity of waste plastics and the mixed non-pyrolyzable substances, the surface of the catalyst is coked and deactivated during the cracking to produce fuel oil. In addition, the hydrogen chloride produced during the pyrolysis of PVC catalyst poisoning
[0007] (3) Recycling of chemical products, sorting of waste plastics before simple regeneration
[0010] In Liu Hongsha's master's thesis "Recognition of Waste Mixed Plastics Based on Near-infrared Spectroscopy" published in 2013, she introduced the method of using near-infrared spectroscopy to identify and classify six kinds of waste plastics. Denoising preprocessing, but the spectral processing process is cumbersome, and the extracted characteristic wavelengths are also many, which greatly increases the calculation amount of the entire process, and also increases the calculation time of the entire process, making it difficult to operate in practical applications. become complicated

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for discriminating multiple waste plastic kinds by adopting near infrared spectrum characteristic wavelength

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Clean the surface of the waste plastic and polish it with 360# sandpaper, then cut it into small pieces with a size of 2mm*2mm, and finally number them and measure them by diffuse reflectance at room temperature of 20-25°C.

[0040] The present invention adopts the FT S6000 Fourier transform infrared spectrometer produced by American Bio-rad Company to collect the near-infrared spectrum of the sample. .

[0041] MATLAB was used to conduct principal component analysis on the near-infrared spectra of 86 waste plastic samples as a standard sample set after K-M transformation, and the principal component scores and loading coefficients were obtained. The cumulative contribution rate of the first four principal components reached 96.62%, which can represent the original For most of the characteristic information of the spectrum, the contribution rate of the first principal component is 75.68%, so the loading coefficient of the first principal component is the main factor, an...

Embodiment 2

[0044] With reference to the method of embodiment 1, 18 characteristic wavelength data of the plastics of 86 standard sample sets extracted are used as the input of BP neural network model, and BP neural network model is trained, and the BP neural network model input layer that training draws The number of neurons is 18, the number of neurons in the hidden layer is 20, the number of neurons in the output layer is 6, and the target error is 0.01. The transfer function of the hidden layer adopts the double tangent S-type transfer function tansig, the output layer adopts the purelin function, and the learning function trainlm is selected. The training times are 100. Then use the trained BP neural network model to predict and classify the unknown sample set. The BP neural network model has a discrimination accuracy rate of 98.84% for the standard sample set, and a prediction accuracy rate of 73.33% for the unknown sample set, which can basically meet the requirements for the class...

Embodiment 3

[0046] With reference to the method of embodiment 1, the 18 characteristic wavelength data of the plastics of 86 standard sample sets that extract are used as the input of PNN neural network model, the PNN neural network model is trained, and the dispersion constant of the PNN neural network model that training obtains is 0.1, and the maximum number of neurons in the middle layer is 86. Then use the trained PNN network model to predict and classify the unknown sample set. The PNN network training model has a classification accuracy rate of 100% for the training set and 97.67% for the prediction set, meeting the requirements for the classification of waste plastics.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a method for discriminating a plastic article and provides a method for discriminating multiple waste plastic kinds. The subsequent treatment calculated amount is reduced, the calculating time is saved, a sample can be directly discriminated and analyzed without being pretreated, and the operation and implementation in the industry are facilitated. Thus, according to the technical scheme adopted by the invention, the method for discriminating multiple waste plastic kinds by adopting a near infrared spectrum characteristic wavelength comprises the following steps: 1, acquiring original spectrums of multiple waste plastic standard samples by adopting a Fourier near-infrared spectroscopy; 2, performing K-M transformation on the acquired original spectrums; 3, performing principal component analysis on the spectrum data subjected to the K-M transformation, and extracting characteristic spectrums; 4, performing Fisher discrimination and establishing a discrimination model; and 5, discriminating and classifying unknown kinds of plastic by adopting the discrimination model established in the step 4, namely, a discriminant. The method is mainly applied to discrimination of the plastic article.

Description

technical field [0001] The invention relates to a method for identifying plastic items, in particular to a method for identifying several types of waste plastics by using near-infrared spectrum characteristic wavelengths technical background [0002] At present, the total output of plastic products in the world exceeds 1 million tons. As a result, a global environmental problem has been caused, that is, the pollution caused by waste plastics to the environment. Waste plastics are difficult to degrade naturally and have no affinity for the natural environment. Therefore, governments of various countries are actively promoting the recycling of waste plastics. [0003] Today, there are roughly three ways to solve the problem of waste plastic pollution: recycling, landfill treatment and the development of degradable plastics. From the perspective of environmental protection, the recycling and reuse of waste plastics can not only eliminate environmental pollution, but also obta...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01N21/359G01N21/3563
CPCG16C20/20
Inventor 张毅民白家瑞刘红莎王鹏王娜马冬雅
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap