基于改进YOLOv5的矿用输送带纵向撕裂检测方法

TD67%TP751; 带式输送机输送带纵向撕裂可能引发重大安全事故.针对现有输送带撕裂检测方法精度低、抗干扰能力差的问题,提出了一种基于多尺度特征融合的纵向撕裂检测系统.该系统通过线性激光和高速相机实时捕获输送机胶带表面图像,使用LoG算法对图像进行预处理,提取图像关键区域、减少数据冗余,并通过多尺度特征融合神经网络进行撕裂检测.在检测算法方面,在神经网络主干网络中引入ConvNeXt特征增强模块,提高模型对细小撕裂纹理的特征提取能力,在Neck 部分使用双向特征金字塔网络(BiFPN)融合浅层细节纹理特征,减少下采样过程中深层网络细节信息的丢失.实验结果表明,改进后的算法对输送带纵向撕裂故...

Full description

Saved in:
Bibliographic Details
Published in矿业安全与环保 Vol. 51; no. 4; pp. 1 - 8
Main Authors 于庆, 罗明华, 向亮, 游磊, 朱兴林
Format Journal Article
LanguageChinese
Published 煤矿灾害防控全国重点实验室,重庆 400037 01.08.2024
中煤科工集团重庆研究院有限公司,重庆 400039
Subjects
conveying belt
特征融合
feature fusion
输送带
YOLOv5
目标检测
带式输送机
纵向撕裂
belt conveyor
object detection
longitudinal tear
Online AccessGet full text
ISSN1008-4495
DOI10.19835/j.issn.1008-4495.20240577

Cover

Abstract TD67%TP751; 带式输送机输送带纵向撕裂可能引发重大安全事故.针对现有输送带撕裂检测方法精度低、抗干扰能力差的问题,提出了一种基于多尺度特征融合的纵向撕裂检测系统.该系统通过线性激光和高速相机实时捕获输送机胶带表面图像,使用LoG算法对图像进行预处理,提取图像关键区域、减少数据冗余,并通过多尺度特征融合神经网络进行撕裂检测.在检测算法方面,在神经网络主干网络中引入ConvNeXt特征增强模块,提高模型对细小撕裂纹理的特征提取能力,在Neck 部分使用双向特征金字塔网络(BiFPN)融合浅层细节纹理特征,减少下采样过程中深层网络细节信息的丢失.实验结果表明,改进后的算法对输送带纵向撕裂故障的检测精度 P 和平均精度均值(mAP)分别达到了96.34%、94.36%,优于其他主流的检测方法.
AbstractList TD67%TP751; 带式输送机输送带纵向撕裂可能引发重大安全事故.针对现有输送带撕裂检测方法精度低、抗干扰能力差的问题,提出了一种基于多尺度特征融合的纵向撕裂检测系统.该系统通过线性激光和高速相机实时捕获输送机胶带表面图像,使用LoG算法对图像进行预处理,提取图像关键区域、减少数据冗余,并通过多尺度特征融合神经网络进行撕裂检测.在检测算法方面,在神经网络主干网络中引入ConvNeXt特征增强模块,提高模型对细小撕裂纹理的特征提取能力,在Neck 部分使用双向特征金字塔网络(BiFPN)融合浅层细节纹理特征,减少下采样过程中深层网络细节信息的丢失.实验结果表明,改进后的算法对输送带纵向撕裂故障的检测精度 P 和平均精度均值(mAP)分别达到了96.34%、94.36%,优于其他主流的检测方法.
Abstract_FL Longitudinal tearing of belt conveyor may lead to significant safety accidents.However,existing algorithms suffer from low detection accuracy and poor anti-interference capability.This study proposes a longitudinal tear detection system based on multi-scale feature fusion.The system captures belt images in real-time using linear lasers and high-speed cameras,pre-processes the images using the LoG algorithm to extract key regions,thereby reducing data redundancy,and finally detects tears using the multi-scale feature fusion neural network.In terms of the detection algorithm,the ConvNeXt feature enhancement module is introduced into neural network backbone network to improve the feature extraction ability of the model for minor tear texture.Additionally,a Bidirectional Feature Pyramid Network(BiFPN)is employed in the Neck part to fuse shallow detail texture features,reducing the loss of detail information in deep layers during down-sampling.The experimental results show that the detection accuracy P and mean average precision(mAP)for longitudinal tear fault detection of the improved algorithm reach 96.34%and 94.36%,respectively,which is superior to other mainstream detection methods.
Author 于庆
朱兴林
罗明华
向亮
游磊
AuthorAffiliation 煤矿灾害防控全国重点实验室,重庆 400037;中煤科工集团重庆研究院有限公司,重庆 400039
AuthorAffiliation_xml – name: 煤矿灾害防控全国重点实验室,重庆 400037;中煤科工集团重庆研究院有限公司,重庆 400039
Author_FL YOU Lei
ZHU Xinglin
YU Qing
LUO Minghua
XIANG Liang
Author_FL_xml – sequence: 1
  fullname: YU Qing
– sequence: 2
  fullname: LUO Minghua
– sequence: 3
  fullname: XIANG Liang
– sequence: 4
  fullname: YOU Lei
– sequence: 5
  fullname: ZHU Xinglin
Author_xml – sequence: 1
  fullname: 于庆
– sequence: 2
  fullname: 罗明华
– sequence: 3
  fullname: 向亮
– sequence: 4
  fullname: 游磊
– sequence: 5
  fullname: 朱兴林
BookMark eNo9jz1Lw0Ach2-oYK39Ek4uif_L3SU5cJHiGwSy6OBU7iXRVknRoNKtiltBfGkddOhQEHcp2Az2y5hL_BaKitMPnuF5-C2gStJJIoSWMNiY-4SttO1WmiY2BvAtSjmzHXAoMM-roOo_nEf1NG1JAJe5lDGvilbzUfaRXZvBtJw97YVBeMaKx6tiNCsGL-X7_WfvIn97LrJJfnNr7obl-NKMe2bSNw9T8zpcRHOxOEqj-t_W0O7G-k5jywrCze3GWmClGAi2NMcaXCkxlz7xPRYxT8dEKBVRgkEJH0tH04grDUJh7biuUCzSUnoYuAOc1NDyr_dcJLFI9pvtzulJ8l1sHnbFcfdA_nylAJh8AYShYgQ
ClassificationCodes TD67%TP751
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.19835/j.issn.1008-4495.20240577
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
DocumentTitle_FL Longitudinal tear detection method of mine conveyor belt based on improved YOLOv5
EndPage 8
ExternalDocumentID kyaqyhb202404001
GrantInformation_xml – fundername: 中煤科工集团重庆研究院自立重点研发科研项目
  funderid: (2023ZDYF01)
GroupedDBID 2B.
4A8
92I
93N
ALMA_UNASSIGNED_HOLDINGS
GROUPED_DOAJ
PSX
TCJ
ID FETCH-LOGICAL-s1031-d91d06bb19b83875e57df3acce4310ca81b2d4e9cd0ac1d266ac5edbb71092093
ISSN 1008-4495
IngestDate Thu May 29 04:06:59 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 4
Keywords conveying belt
特征融合
feature fusion
输送带
YOLOv5
目标检测
带式输送机
纵向撕裂
belt conveyor
object detection
longitudinal tear
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1031-d91d06bb19b83875e57df3acce4310ca81b2d4e9cd0ac1d266ac5edbb71092093
PageCount 8
ParticipantIDs wanfang_journals_kyaqyhb202404001
PublicationCentury 2000
PublicationDate 2024-08-01
PublicationDateYYYYMMDD 2024-08-01
PublicationDate_xml – month: 08
  year: 2024
  text: 2024-08-01
  day: 01
PublicationDecade 2020
PublicationTitle 矿业安全与环保
PublicationTitle_FL Mining Safety & Environmental Protection
PublicationYear 2024
Publisher 煤矿灾害防控全国重点实验室,重庆 400037
中煤科工集团重庆研究院有限公司,重庆 400039
Publisher_xml – name: 煤矿灾害防控全国重点实验室,重庆 400037
– name: 中煤科工集团重庆研究院有限公司,重庆 400039
SSID ssib006564557
ssj0002925396
ssib036434754
ssib001105362
ssib000270141
ssib051374764
Score 2.3916364
Snippet TD67%TP751; 带式输送机输送带纵向撕裂可能引发重大安全事故.针对现有输送带撕裂检测方法精度低、抗干扰能力差的问题,提出了一种基于多尺度特征融合的纵向撕裂检测系统.该...
SourceID wanfang
SourceType Aggregation Database
StartPage 1
Title 基于改进YOLOv5的矿用输送带纵向撕裂检测方法
URI https://d.wanfangdata.com.cn/periodical/kyaqyhb202404001
Volume 51
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  issn: 1008-4495
  databaseCode: DOA
  dateStart: 20230101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.doaj.org/
  omitProxy: true
  ssIdentifier: ssj0002925396
  providerName: Directory of Open Access Journals
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NaxQxFB_aevEiiorfVDAnmXVmkswk4GVmm6WI2EsL9VTma60UVrSr0B6kijdB_Gg96KGHgniXgt2D_Wfc2fpf-F42zkSpUIUlPJI3L-9jZ_LLzEviONco7RYspblLeR66TKShm4acudwXgMYLjg9IzLa4E84usFuLfHFi8qm9uqSftfL1Q9eV_E9UoQ7iiqtk_yGytVCoABriCyVEGMojxZgoTmSHJDFRDEuhiAqJBFoSJUjSITK5O3d77gknKiISGJgmOtiEBCOx0JyKSEqUxLwH4aPYRJA4RB4Qm3DdkUekr-UHRHK8KqZEBFiDhIcEcIpE84RaBygpGR9v-QsBWwow7AW0AuGxIkIiIbhWSTehORGW8ZgZzKnzky2LuSbCpgWUniEy0noIwyJmgGhYanO0lNhqCbFn-IEUNCu2X4sErE7KG_-RtX6g8e9uBQ8myliVaLeCGon2FBoTWXaCHglqi66PUEm8PNC-05dLhU0x2Nc2NdBX0Lb4jfXXmd7kxxpjMOOEMeN8MwiZXXfv229Y9Iji29Dk0DFPAojWgx5Kb9XSW-gVQONRM9LX-Zcra-nDteVMc4B6_qRzLIBR0bNeSZiv0pgH3MBrAOPU2l4yxK2Imq_mFNAtixp4yn0Kk1UzHUdkFMiAU31kXq2l2QcYbbjxVwv0grpeN-3ds7Df_EnnhJm0TcfjO_CUM7G-fNq5OdwefB-8qjb3DvY_ju-y0YcXo-390ebng2_vfmw8G379NBrsDl-_qd5uHew8r3Y2qt2X1fu96svWGWeho-bbs645i8RdxYNQ3EL6hRdmmS8zQWGOX_Ko6NI0z0tA4F6ewuwvKFgp88JLc78A2JvmvCyyDHOdA0_Ss85U70GvPOdMywwaI5CF38AjwIMgCIFklBY574beeeeqsXbJPGtWl_4M2IUj8Fx0jjc3xiVnqv_ocXkZEHQ_u6LD_BOoEJGO
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E6%94%B9%E8%BF%9BYOLOv5%E7%9A%84%E7%9F%BF%E7%94%A8%E8%BE%93%E9%80%81%E5%B8%A6%E7%BA%B5%E5%90%91%E6%92%95%E8%A3%82%E6%A3%80%E6%B5%8B%E6%96%B9%E6%B3%95&rft.jtitle=%E7%9F%BF%E4%B8%9A%E5%AE%89%E5%85%A8%E4%B8%8E%E7%8E%AF%E4%BF%9D&rft.au=%E4%BA%8E%E5%BA%86&rft.au=%E7%BD%97%E6%98%8E%E5%8D%8E&rft.au=%E5%90%91%E4%BA%AE&rft.au=%E6%B8%B8%E7%A3%8A&rft.date=2024-08-01&rft.pub=%E7%85%A4%E7%9F%BF%E7%81%BE%E5%AE%B3%E9%98%B2%E6%8E%A7%E5%85%A8%E5%9B%BD%E9%87%8D%E7%82%B9%E5%AE%9E%E9%AA%8C%E5%AE%A4%2C%E9%87%8D%E5%BA%86+400037&rft.issn=1008-4495&rft.volume=51&rft.issue=4&rft.spage=1&rft.epage=8&rft_id=info:doi/10.19835%2Fj.issn.1008-4495.20240577&rft.externalDocID=kyaqyhb202404001
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fkyaqyhb%2Fkyaqyhb.jpg