Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Dry garbage deep sorting method and device based on spectrum recognition technology

A spectrum recognition and garbage technology, applied in character and pattern recognition, sorting, solid waste removal and other directions, can solve the problems of deep sorting technology of dry garbage that have not been publicly reported, and achieve the improvement of resource yield and effective utilization. and processing, to achieve the effect of regular updates

Pending Publication Date: 2022-03-01
NORTH CHINA ELECTRIC POWER UNIV (BAODING)
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At this stage, there is no public report on the deep separation technology of dry waste based on spectral recognition

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
  • Dry garbage deep sorting method and device based on spectrum recognition technology
  • Dry garbage deep sorting method and device based on spectrum recognition technology
  • Dry garbage deep sorting method and device based on spectrum recognition technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Embodiment 1: as figure 1 Shown, a kind of dry rubbish depth sorting method based on spectral recognition technology, described method comprises:

[0043] S1: Establish deep sorting categories for dry waste after source separation. The specific process is: according to the composition characteristics of dry waste and the direction of high-value utilization, the dry waste after source classification is divided into: cellulose, vinyl polymer, and low-value.

[0044] S2: Obtain a large amount of infrared spectrum data of different depth sorting categories of dry waste, and establish a dry waste infrared spectrum database. The specific process is: collect a large amount of dry waste after source classification, and use infrared spectrometer to collect dry waste samples at 650-4000cm -1 The spectral data of the band, get the infrared spectral data matrix X m×n , where m=72 represents the total amount of dry garbage, and n=3351 represents the infrared spectrum data of the ...

Embodiment 2

[0047] Example 2: Using the preprocessed dry garbage infrared spectrum data in Example 1, a random forest classification model containing 500 decision trees was constructed, each decision tree including 5 randomly extracted variables in the dry garbage infrared spectrum data. According to the formula Obtain the discriminant results of the random forest, and then use the leave-one-out cross-validation formula Calculate the final accuracy of the model, and the calculation shows that the accuracy of classification and identification of the model is 81.6%.

Embodiment 3

[0048] Example 3: Using the preprocessed dry garbage infrared spectrum data in Example 1, a random forest classification model containing 500 decision trees was constructed, each decision tree including 15 randomly selected variables in the dry garbage infrared spectrum data. According to the formula Obtain the discriminant results of the random forest, and then use the leave-one-out cross-validation formula Calculate the final accuracy of the model, and the calculation shows that the accuracy of classification and identification of the model is 83.1%.

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 discloses a dry garbage deep sorting method and device based on a spectrum recognition technology. The method comprises the following steps: establishing a deep sorting category of the dry garbage after source classification; acquiring infrared spectrum data of dry garbage of different depth sorting categories, and establishing a dry garbage infrared spectrum database; preprocessing the infrared spectrum data, constructing a random forest classification model, and carrying out cross validation by adopting a leave-one-out method; and detecting infrared spectrum data of the dry garbage of unknown types by utilizing a spectrum identification technology and combining with the trained random forest classification model, and obtaining the attribution types of the dry garbage so as to realize deep sorting. The invention further discloses a deep sorting device for the dry garbage. The deep sorting device comprises a conveying device, a sorting device, a collecting device and a central control device. According to the method, through the difference of infrared spectrums of different types of dry garbage, deep sorting is conducted on the dry garbage subjected to source classification by means of the spectrum recognition technology, and the recycling efficiency of the dry garbage in the municipal solid waste is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of deep sorting of garbage, and in particular relates to a method and device for deep sorting of dry garbage based on spectrum recognition technology. Background technique [0002] With the rapid advancement of my country's urbanization process, the dilemma of garbage siege is becoming more and more serious. As a by-product of the transformation of urban ecosystems, municipal solid waste has the characteristics of many types and a large amount. The traditional waste disposal methods are generally relatively rough incineration power generation and sanitary landfill, which has secondary pollution and low resource recovery rate. and other shortcomings. In order to improve the resource output rate of domestic waste, in 2018, the Ministry of Housing and Urban-Rural Development of my country proposed to gradually build a "four-point method" for the source classification of domestic waste, and divide domestic wast...

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): G06F30/27G06K9/62B07C5/342B07C5/36B07C5/38B09B3/00G06F119/02
CPCG06F30/27B09B3/00B07C5/342B07C5/361B07C5/38G06F2119/02G06F18/24323
Inventor 胡斌付浩王文斌刘吉张兵马善为陆强
Owner NORTH CHINA ELECTRIC POWER UNIV (BAODING)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com