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

Method for predicting pulverized coal covered coal pile safe stacking and storing time by using neural network

A neural network and neural network model technology, applied in the field of coal spontaneous combustion prediction, can solve problems such as uncertainty and prediction lag, and achieve the effect of simple method and wide application range

Active Publication Date: 2020-04-17
CHINA UNIV OF MINING & TECH
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of prediction hysteresis and uncertainty in the current method for preventing coal spontaneous combustion, the present invention provides a method for predicting the safe storage time of pulverized coal covered coal piles by using neural network, so as to prevent spontaneous combustion of coal piles

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 predicting pulverized coal covered coal pile safe stacking and storing time by using neural network
  • Method for predicting pulverized coal covered coal pile safe stacking and storing time by using neural network
  • Method for predicting pulverized coal covered coal pile safe stacking and storing time by using neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] Select Shangwan coal with a diameter of 35m and a thickness of 70cm in the middle and lower part of the pulverized coal. The coal pile is stored in a fresh air flow (0.08cm / s) environment. The average porosity of the coal pile is 0.40, and the measuring point is selected at a distance of 2m from the ground. The coal oxide layer with a height and a depth of 1.5m is used as a measuring point for temperature and heat release intensity. The input data for the existing coal stockpile yields the output temperature and heat release intensity values. Table 1 is a comparison table of BP neural network prediction value and literature value of exothermic intensity. figure 2 It is a comparison chart of the predicted value of the BP neural network model of temperature and the measured value of the actual coal pile temperature. It can be seen from Table 1 that the value of the exothermic intensity predicted by the BP neural network fluctuates up and down from the average value of t...

Embodiment 2

[0078] Select Yujialiang coal with a diameter of 35m and a thickness of 80cm in the middle and lower part of the pulverized coal. The coal pile is stored in a fresh air flow (0.08cm / s) environment. The average porosity of the coal pile is 0.45. The measuring point is selected at a distance from the ground The coal oxide layer with a height of 2m and a depth of 1.5m is used as a measuring point for temperature and heat release intensity. The input data for the existing coal stockpile yields the output temperature and heat release intensity values. Table 2 is a comparison table of the BP neural network prediction value and the literature value of the exothermic intensity. image 3 It is a comparison chart of the predicted value of the BP neural network model of temperature and the measured value of the actual coal pile temperature. It can be seen from Table 2 that the value of the exothermic intensity predicted by the BP neural network fluctuates up and down from the average va...

Embodiment 3

[0085] Ciyaowan coal with a diameter of 35m and a thickness of 90cm in the middle and lower part is selected. The coal pile is stored in a fresh air flow (0.08cm / s) environment. The average porosity of the coal pile is 0.48. The measuring point is selected at a distance of 2m from the ground. The coal oxide layer with a height and a depth of 1.5m is used as a measuring point for temperature and heat release intensity. The input data for the existing coal stockpile yields the output temperature and heat release intensity values. Table 3 is a comparison table of the BP neural network prediction value and the literature value of the exothermic intensity. Figure 4 It is a comparison chart of the predicted value of the BP neural network model of temperature and the measured value of the actual coal pile temperature. It can be seen from Table 3 that the value of the exothermic intensity predicted by the BP neural network fluctuates up and down from the average value of the exother...

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

PropertyMeasurementUnit
particle diameteraaaaaaaaaa
diameteraaaaaaaaaa
diameteraaaaaaaaaa
Login to View More

Abstract

The invention discloses a method for predicting pulverized coal covered coal pile safe stacking and storing time by using a neural network. The method comprises the steps of firstly, obtaining factorsrelated to the safety dump time through investigation, analysis and identification; setting the pulverized coal covering thickness, the air flow, the stacking and storing time, the coal activation energy and the coal pile void ratio as influence factors of the coal pile safe stacking and storing time; taking the heat release intensity and the temperature as indexes for judging the spontaneous combustion tendency of the coal pile, constructing a neural network model, setting a minimum mean square error for training to obtain a BP neural network model for predicting the temperature and the heatrelease intensity through influence factors such as stacking time, and calculating the shortest spontaneous combustion period of the coal pile according to the BP neural network model. The method hasthe advantages of being simple, accurate, wide in application range and the like.

Description

technical field [0001] The invention relates to a method for predicting the safe storage time of pulverized coal covered coal piles by using a neural network, and belongs to the technical field of coal spontaneous combustion prediction. Background technique [0002] my country is rich in coal resources, and its coal production and consumption rank among the top in the world, accounting for more than 85% of the total domestic primary energy production and consumption. However, coal spontaneous combustion fires are very serious in my country. From large-scale coalfield outcrop fires in Xinjiang, Ningxia, and Inner Mongolia, and coal pile spontaneous combustion fires in ground coal yards in mining areas such as Lingwu, Shenfu, and Datong, and wharfs in Qinhuangdao, to underground coal mining areas in mining areas such as Yanzhou, Yima, Jingyuan, and Fushun Spontaneous coal seam fires can be seen everywhere. Spontaneous combustion of coal is a very serious natural disaster, whi...

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): G06F30/27G06N3/04G06N3/08G01N25/22G01N33/22
CPCG06N3/084G01N25/22G01N33/222G06N3/045
Inventor 孟献梁褚睿智万永周苗真勇吴佳欣杨德光吴国光
Owner CHINA UNIV OF MINING & TECH
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