PREDICTION OF CUTTING LOAD OF DRUM SHEARER BASED ON DEEP BELIEF NETWORK

A prediction model based on Deep Belief Network( DBN) was proposed to accurately predict the cutting load of the shearer’s spiral drum. The DBN model uses 7 characteristic parameters which include 2 guiding boots,2 smooth boots,rocker arm vibration,idler shaft,and cutting motor current as visual inp...

Full description

Saved in:
Bibliographic Details
Main Authors: MAO Jun, GUO Hao, CHEN HongYue
Format: Article
Language:zho
Published: Editorial Office of Journal of Mechanical Strength 2020-01-01
Series:Jixie qiangdu
Subjects:
Online Access:http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2020.02.003
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841535777524154368
author MAO Jun
GUO Hao
CHEN HongYue
author_facet MAO Jun
GUO Hao
CHEN HongYue
author_sort MAO Jun
collection DOAJ
description A prediction model based on Deep Belief Network( DBN) was proposed to accurately predict the cutting load of the shearer’s spiral drum. The DBN model uses 7 characteristic parameters which include 2 guiding boots,2 smooth boots,rocker arm vibration,idler shaft,and cutting motor current as visual input. By means of unsupervised level greedy learning,the higher level features are represented,the intelligence of the identification process is enhanced,and the complexity and imprecision of artificial features extraction are avoided. The test results show that the proposed method is suitable for predicting the load of the spiral drum of coal miner,which has strong characteristic extraction ability and better performance than BP neural network.
format Article
id doaj-art-5d4e6b1b687d4e8fa72b38f5c14b530f
institution Kabale University
issn 1001-9669
language zho
publishDate 2020-01-01
publisher Editorial Office of Journal of Mechanical Strength
record_format Article
series Jixie qiangdu
spelling doaj-art-5d4e6b1b687d4e8fa72b38f5c14b530f2025-01-15T02:28:05ZzhoEditorial Office of Journal of Mechanical StrengthJixie qiangdu1001-96692020-01-014227027530607287PREDICTION OF CUTTING LOAD OF DRUM SHEARER BASED ON DEEP BELIEF NETWORKMAO JunGUO HaoCHEN HongYueA prediction model based on Deep Belief Network( DBN) was proposed to accurately predict the cutting load of the shearer’s spiral drum. The DBN model uses 7 characteristic parameters which include 2 guiding boots,2 smooth boots,rocker arm vibration,idler shaft,and cutting motor current as visual input. By means of unsupervised level greedy learning,the higher level features are represented,the intelligence of the identification process is enhanced,and the complexity and imprecision of artificial features extraction are avoided. The test results show that the proposed method is suitable for predicting the load of the spiral drum of coal miner,which has strong characteristic extraction ability and better performance than BP neural network.http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2020.02.003ShearerSpiral drumCutting loadDeep belief network
spellingShingle MAO Jun
GUO Hao
CHEN HongYue
PREDICTION OF CUTTING LOAD OF DRUM SHEARER BASED ON DEEP BELIEF NETWORK
Jixie qiangdu
Shearer
Spiral drum
Cutting load
Deep belief network
title PREDICTION OF CUTTING LOAD OF DRUM SHEARER BASED ON DEEP BELIEF NETWORK
title_full PREDICTION OF CUTTING LOAD OF DRUM SHEARER BASED ON DEEP BELIEF NETWORK
title_fullStr PREDICTION OF CUTTING LOAD OF DRUM SHEARER BASED ON DEEP BELIEF NETWORK
title_full_unstemmed PREDICTION OF CUTTING LOAD OF DRUM SHEARER BASED ON DEEP BELIEF NETWORK
title_short PREDICTION OF CUTTING LOAD OF DRUM SHEARER BASED ON DEEP BELIEF NETWORK
title_sort prediction of cutting load of drum shearer based on deep belief network
topic Shearer
Spiral drum
Cutting load
Deep belief network
url http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2020.02.003
work_keys_str_mv AT maojun predictionofcuttingloadofdrumshearerbasedondeepbeliefnetwork
AT guohao predictionofcuttingloadofdrumshearerbasedondeepbeliefnetwork
AT chenhongyue predictionofcuttingloadofdrumshearerbasedondeepbeliefnetwork