Article(id=1322164751325581813, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1322164546295410919, articleNumber=null, orderNo=null, doi=null, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1741881600000, receivedDateStr=2025-03-14, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793158241349, onlineDateStr=2026-10-28, pubDate=1764000000000, pubDateStr=2025-11-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793158241349, onlineIssueDateStr=2026-10-28, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793158241349, creator=13701087609, updateTime=1793158241349, updator=13701087609, issue=Issue{id=1322164546295410919, tenantId=1146029695717560320, journalId=1225396423026438145, year='2025', volume='45', issue='11', pageStart='1', pageEnd='284', issueExtLink='null', onlineDate='null', pubDate='1764000000000', pubDateStr='2025-11-25', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793158192465, creator='13701087609', updateTime=1793158905697, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1322167537857573862, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1322164546295410919, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1322167537861768167, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1322164546295410919, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=258, endPage=265, ext={EN=ArticleExt(id=1322164751606600182, articleId=1322164751325581813, tenantId=1146029695717560320, journalId=1225396423026438145, language=EN, title=Research on Foreign Object Detection Algorithm for Coal Mine Conveyor Belt Based on Linear Deformable Convolution, columnId=null, journalTitle=Mining Research and Development, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Aiming at the problem that the existing machine vision methods cannot effectively detect foreign objects due to the special shape and unobvious characteristics of foreign objects on coal mine conveyor belts, an improved YOLOv11 model was proposed. Firstly, the C3k2-LDC feature extraction module was constructed using linear deformable convolution, so that the model has the ability to extract features of irregular shaped foreign objects. Then, the edge enhancement module was introduced, and the multi-scale feature fusion strategy was adopted to effectively strengthen the edge information of the weak feature foreign object. Finally, a loss function optimization scheme based on WIoU was proposed to reduce the impact of low-quality data samples on training. The effectiveness and robustness of the improved YOLOv11 model were verified by ablation test, comparative test, thermal map and visual analysis. The results show that the mAP50 of the improved YOLOv11 model is 90.2%, which is 4.0, 9.1, 7.4 and 5.7 percentage points higher than that of RT-DETR, EfficientDet-D2, YOLOv8n and YOLOv11s models, respectively. In terms of lightweight, the floating-point calculation amount and parameter amount of the improved YOLOv11 model are 6.8×109 and 2.6×106 respectively, and the detection speed is 127 frames/s, which can realize the real-time foreign object detection task on the basis of ensuring the detection accuracy. Compared with the original model, the improved model pays more attention to the characteristics of complex foreign objects and has good robustness. The research results can provide technical support for mine safety management.

, authors=Rui WANG1, Rui SI2, Chaoyu HAO2, Yongguo YUAN1, authorsList=Rui WANG, Rui SI, Chaoyu HAO, Yongguo YUAN, authorCompany=null, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1322164756975309337, articleId=1322164751325581813, tenantId=1146029695717560320, journalId=1225396423026438145, language=CN, title=基于线性可变形卷积的煤矿输送带异物检测算法研究, columnId=1226462295946085268, journalTitle=矿业研究与开发, columnName=矿山机电与矿业智能化, runingTitle=null, highlight=null, articleAbstract=

针对煤矿输送带上的异物因形状特殊、特征不明显,导致现有机器视觉方法无法有效检测出异物的问题,提出了改进YOLOv11模型。首先,采用线性可变形卷积构建C3k2-LDC特征提取模块,使模型具备对不规则形状异物的特征提取能力;然后,引入边缘增强模块,采用多尺度特征融合策略,有效强化了弱特征异物的边缘信息;最后,提出基于WIoU的损失函数优化方案,减少低质量数据样本对训练的影响。通过消融试验、对比试验、热力图及可视化分析,验证改进YOLOv11模型的有效性及鲁棒性。结果表明:改进YOLOv11模型的mAP50为90.2%,相比RT-DETR、EfficientDet-D2、YOLOv8n、YOLOv11s模型分别提升了4.0,9.1,7.4,5.7个百分点;轻量化方面,改进YOLOv11模型的浮点计算量和参数量分别为6.8×109、2.6×106,检测速度为127帧/s,可在保证检测精度的基础上实现实时异物检测任务;相比原模型,改进模型对复杂异物特征的关注度更高,具有良好的鲁棒性。研究结果可为矿山安全管理提供技术支撑。

, authors=王瑞1, 司蕊2, 郝朝瑜2, 元永国1, authorsList=王瑞, 司蕊, 郝朝瑜, 元永国, authorCompany=null, correspAuthors=null, authorNote=

王瑞(1983—),女,吉林辽源人,硕士,副教授,主要从事企业安全生产数学建模方面的教学与研究工作。E-mail:

, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=zQpB56cbMHfOBjn8ciwyow==, magXml=AyY7CR+7h2y2EsRqB4nnMQ==, pdfUrl=null, pdf=0evMvCDDLrEy5ejh1mGZGw==, pdfFileSize=4201726, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=S0VX9K3hbiMA+44rHNkSJA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=qeFVUUJYP4NMGog722NZ5Q==, mapNumber=null, fund=null)}, authors=[Author(id=1322164759366062625, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=502176104@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322164759449948707, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759366062625, language=EN, stringName=Rui WANG, firstName=Rui, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Public Teaching Department, Liaoyuan Vocational Technical College, Liaoyuan, Jilin 136200, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322164759517057572, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759366062625, language=CN, stringName=王瑞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.辽源职业技术学院 公共教学部,吉林 辽源市 136200, bio={"content":"

王瑞(1983—),女,吉林辽源人,硕士,副教授,主要从事企业安全生产数学建模方面的教学与研究工作。E-mail:

"}, bioImg=null, bioContent=

王瑞(1983—),女,吉林辽源人,硕士,副教授,主要从事企业安全生产数学建模方面的教学与研究工作。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322164757327630874, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, xref=1., ext=[AuthorCompanyExt(id=1322164757336019483, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757327630874, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Public Teaching Department, Liaoyuan Vocational Technical College, Liaoyuan, Jilin 136200, China), AuthorCompanyExt(id=1322164757344408092, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757327630874, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.辽源职业技术学院 公共教学部,吉林 辽源市 136200)])]), Author(id=1322164759592555046, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322164759672246824, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759592555046, language=EN, stringName=Rui SI, firstName=Rui, middleName=null, lastName=SI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Safety and Emergency Management and Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322164759730967081, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759592555046, language=CN, stringName=司蕊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.太原理工大学 安全与应急管理工程学院,山西 太原市 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322164757461848605, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, xref=2., ext=[AuthorCompanyExt(id=1322164757604454942, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757461848605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Safety and Emergency Management and Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322164757625426463, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757461848605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.太原理工大学 安全与应急管理工程学院,山西 太原市 030024)])]), Author(id=1322164759819047467, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322164759915516461, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759819047467, language=EN, stringName=Chaoyu HAO, firstName=Chaoyu, middleName=null, lastName=HAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Safety and Emergency Management and Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322164759991013934, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759819047467, language=CN, stringName=郝朝瑜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.太原理工大学 安全与应急管理工程学院,山西 太原市 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322164757461848605, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, xref=2., ext=[AuthorCompanyExt(id=1322164757604454942, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757461848605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Safety and Emergency Management and Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322164757625426463, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757461848605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.太原理工大学 安全与应急管理工程学院,山西 太原市 030024)])]), Author(id=1322164760062317104, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322164760142008882, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164760062317104, language=EN, stringName=Yongguo YUAN, firstName=Yongguo, middleName=null, lastName=YUAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Public Teaching Department, Liaoyuan Vocational Technical College, Liaoyuan, Jilin 136200, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322164760230089267, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164760062317104, language=CN, stringName=元永国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.辽源职业技术学院 公共教学部,吉林 辽源市 136200, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322164757327630874, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, xref=1., ext=[AuthorCompanyExt(id=1322164757336019483, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757327630874, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Public Teaching Department, Liaoyuan Vocational Technical College, Liaoyuan, Jilin 136200, China), AuthorCompanyExt(id=1322164757344408092, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757327630874, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.辽源职业技术学院 公共教学部,吉林 辽源市 136200)])])], keywords=[Keyword(id=1322164760334946868, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, orderNo=1, keyword=Conveyor belt), Keyword(id=1322164760410444341, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, orderNo=2, keyword=Foreignobject detection), Keyword(id=1322164760481747510, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, orderNo=3, keyword=Deep learning), Keyword(id=1322164760565633591, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, orderNo=4, keyword=Linear deformable convolution), Keyword(id=1322164760641131064, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, orderNo=5, keyword=Improved YOLOv11 model), Keyword(id=1322164760708239929, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, orderNo=1, keyword=输送带), Keyword(id=1322164760800514618, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, orderNo=2, keyword=异物检测), Keyword(id=1322164760876012091, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, orderNo=3, keyword=深度学习), Keyword(id=1322164760955703868, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, orderNo=4, keyword=线性可变形卷积), Keyword(id=1322164761047978557, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, orderNo=5, keyword=改进YOLOv11模型)], refs=[Reference(id=1322164764214678095, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=49, issue=1, pageStart=181, pageEnd=202, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=王国法, 庞义辉, 任怀伟, journalName=煤炭学报, refType=null, unstructuredReference=王国法,庞义辉,任怀伟,等. 智慧矿山系统工程及关键技术研究与实践[J]. 煤炭学报,2024, 49 (1): 181-202., articleTitle=智慧矿山系统工程及关键技术研究与实践, refAbstract=null), Reference(id=1322164764281786960, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=49, issue=1, pageStart=181, pageEnd=202, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=WANG Guofa, PANG Yihui, REN Huaiwei, journalName=Journal of China Coal Society, refType=null, unstructuredReference=WANG Guofa, PANG Yihui, REN Huaiwei, et al. System engineering and key technologies research and practice of smart mine[J]. Journal of China Coal Society, 2024, 49 (1): 181-202., articleTitle=System engineering and key technologies research and practice of smart mine, refAbstract=null), Reference(id=1322164764361478737, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=5, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=王国法, 巩师鑫, 申凯, journalName=矿业安全与环保, refType=null, unstructuredReference=王国法,巩师鑫,申凯. 煤矿智能安控技术体系与高质量发展对策[J]. 矿业安全与环保,2023, 50 (5): 1-8., articleTitle=煤矿智能安控技术体系与高质量发展对策, refAbstract=null), Reference(id=1322164764449559122, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=5, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=WANG Guofa, GONG Shixin, SHEN Kai, journalName=Mining Safety & Environmental Protection, refType=null, unstructuredReference=WANG Guofa, GONG Shixin, SHEN Kai. Intelligent security control technology system and high-quality development countermeasures for coal mines [J]. Mining Safety & Environmental Protection, 2023, 50 (5): 1-8., articleTitle=Intelligent security control technology system and high-quality development countermeasures for coal mines, refAbstract=null), Reference(id=1322164764512473683, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2022, volume=47, issue=3, pageStart=1361, pageEnd=1369, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=程德强, 徐进洋, 寇旗旗, journalName=煤炭学报, refType=null, unstructuredReference=程德强,徐进洋,寇旗旗,等. 融合残差信息轻量级网络的运煤皮带异物分类[J]. 煤炭学报,2022, 47 (3): 1361-1369., articleTitle=融合残差信息轻量级网络的运煤皮带异物分类, refAbstract=null), Reference(id=1322164764583776852, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2022, volume=47, issue=3, pageStart=1361, pageEnd=1369, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=CHENG Deqiang, XU Jinyang, KOU Qiqi, journalName=Journal of China Coal Society, refType=null, unstructuredReference=CHENG Deqiang, XU Jinyang, KOU Qiqi, et al. Lightweight network based on residual information for foreign body classification on coal conveyor belt[J]. Journal of China Coal Society, 2022, 47 (3): 1361-1369., articleTitle=Lightweight network based on residual information for foreign body classification on coal conveyor belt, refAbstract=null), Reference(id=1322164764655080021, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=14, pageStart=6276, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=LUO B X, KOU Z M, HAN C, journalName=Sensors (Basel, Switzerland), refType=null, unstructuredReference=LUO B X, KOU Z M, HAN C, et al. A faster and lighter detection method for foreign objects in coal mine belt conveyors [J]. Sensors (Basel, Switzerland), 2023, 23 (14): 6276., articleTitle=A faster and lighter detection method for foreign objects in coal mine belt conveyors, refAbstract=null), Reference(id=1322164764730577494, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2023, volume=11, issue=5, pageStart=114, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=YAO R B, QI P, HUA D Z, journalName=Technologies, refType=null, unstructuredReference=YAO R B, QI P, HUA D Z, et al. A foreign object detection method for belt conveyors based on an improved YOLOX model[J]. Technologies, 2023, 11 (5): 114., articleTitle=A foreign object detection method for belt conveyors based on an improved YOLOX model, refAbstract=null), Reference(id=1322164764797686359, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2023, volume=9, issue=5, pageStart=5221, pageEnd=5234, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=DAI L L, ZHANG X, GARDONI P, journalName=Complex & Intelligent Systems, refType=null, unstructuredReference=DAI L L, ZHANG X, GARDONI P, et al. A new machine vision detection method for identifying and screening out various large foreign objects on coal belt conveyor lines[J]. Complex & Intelligent Systems, 2023, 9 (5): 5221-5234., articleTitle=A new machine vision detection method for identifying and screening out various large foreign objects on coal belt conveyor lines, refAbstract=null), Reference(id=1322164764868989528, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2023, volume=11, issue=null, pageStart=23046, pageEnd=23052, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=MIAO D, WANG Y M, YANG L, journalName=IEEE Access, refType=null, unstructuredReference=MIAO D, WANG Y M, YANG L, et al. Foreign object detection method of conveyor belt based on improved nanodet[J]. IEEE Access, 2023, 11: 23046-23052., articleTitle=Foreign object detection method of conveyor belt based on improved nanodet, refAbstract=null), Reference(id=1322164764936098393, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=9, pageStart=175, pageEnd=178, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=陈瑞, 张鹏, 施海馨, journalName=煤矿机械, refType=null, unstructuredReference=陈瑞,张鹏,施海馨,等. 基于改进YOLOv8的输送带异物检测研究[J]. 煤矿机械,2024, 45 (9): 175-178., articleTitle=基于改进YOLOv8的输送带异物检测研究, refAbstract=null), Reference(id=1322164765015790170, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=9, pageStart=175, pageEnd=178, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=CHEN Rui, ZHANG Peng, SHI Haixin, journalName=Coal Mine Machinery, refType=null, unstructuredReference=CHEN Rui, ZHANG Peng, SHI Haixin, et al. Research on foreign body detection in conveyor belt based on improved YOLOv8[J]. Coal Mine Machinery, 2024, 45 (9): 175-178., articleTitle=Research on foreign body detection in conveyor belt based on improved YOLOv8, refAbstract=null), Reference(id=1322164765108064859, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=47, issue=21, pageStart=188, pageEnd=196, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=郭志聪, 张雷, journalName=电子测量技术, refType=null, unstructuredReference=郭志聪,张雷. 基于改进YOLOv8的低照度煤矿传送带异物识别算法[J]. 电子测量技术,2024, 47 (21): 188-196., articleTitle=基于改进YOLOv8的低照度煤矿传送带异物识别算法, refAbstract=null), Reference(id=1322164765175173724, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=47, issue=21, pageStart=188, pageEnd=196, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=GUO Zhicong, ZHANG Lei, journalName=Electronic Measurement Technology, refType=null, unstructuredReference=GUO Zhicong, ZHANG Lei. Foreign object recognition algorithm of low-light coal mine conveyor belt based on improved YOLOv8 [J]. Electronic Measurement Technology, 2024, 47 (21): 188-196., articleTitle=Foreign object recognition algorithm of low-light coal mine conveyor belt based on improved YOLOv8, refAbstract=null), Reference(id=1322164765275837021, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=12, pageStart=4617, pageEnd=4629, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=马恒, 刘利灿, 高科, journalName=安全与环境学报, refType=null, unstructuredReference=马恒,刘利灿,高科. 融合多尺度特征的轻量化煤炭输送带异物检测方法[J]. 安全与环境学报,2024, 24 (12): 4617-4629., articleTitle=融合多尺度特征的轻量化煤炭输送带异物检测方法, refAbstract=null), Reference(id=1322164765342945886, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=12, pageStart=4617, pageEnd=4629, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=MA Heng, LIU Lican, GAO Ke, journalName=Journal of Safety and Environment, refType=null, unstructuredReference=MA Heng, LIU Lican, GAO Ke. Multi-scale feature fusion method for detecting foreign objects on lightweight coal conveyor belts[J]. Journal of Safety and Environment, 2024, 24 (12): 4617-4629., articleTitle=Multi-scale feature fusion method for detecting foreign objects on lightweight coal conveyor belts, refAbstract=null), Reference(id=1322164765418443359, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2025, volume=8, issue=1, pageStart=17, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=ALKHAMMASH E H, journalName=Fire, refType=null, unstructuredReference=ALKHAMMASH E H. Multi-classification using YOLOV11 and hybrid YOLO11 n-mobilenet models: a fire classes case study[J]. Fire, 2025, 8 (1): 17., articleTitle=Multi-classification using YOLOV11 and hybrid YOLO11 n-mobilenet models: a fire classes case study, refAbstract=null), Reference(id=1322164765485552224, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=149, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=ZHANG X, SONG Y Z, SONG T T, journalName=Image and Vision Computing, refType=null, unstructuredReference=ZHANG X, SONG Y Z, SONG T T, et al. LDConv: linear deformable convolution for improving convolutional neural networks [J]. Image and Vision Computing, 2024, 149: 105190., articleTitle=LDConv: linear deformable convolution for improving convolutional neural networks, refAbstract=null), Reference(id=1322164765586215521, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=9894, pageEnd=9903, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=GAO S X, ZHANG P P, YAN T Y, journalName=null, refType=null, unstructuredReference=GAO S X, ZHANG P P, YAN T Y, et al. Multi-scale and detail-enhanced segment anything model for salient object detection[C]//Proceedings of the 32nd ACM International Conference on Multimedia. New York: ACM, 2024: 9894-9903., articleTitle=Multi-scale and detail-enhanced segment anything model for salient object detection, refAbstract=null), Reference(id=1322164765657518690, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=23, issue=1, pageStart=335, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=LIU Zhigang, SUN Baoshan, BI Kaiyu, journalName=International Journal of Computational Intelligence and Applications, refType=null, unstructuredReference=LIU Zhigang, SUN Baoshan, BI Kaiyu. Optimization of YOLOv7 based on PConv, SE Attention and Wise-IoU[J]. International Journal of Computational Intelligence and Applications, 2024, 23 (1): 335., articleTitle=Optimization of YOLOv7 based on PConv, SE Attention and Wise-IoU, refAbstract=null), Reference(id=1322164765728821859, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=2, pageStart=178, pageEnd=182, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=邓田, 余翼, journalName=矿业研究与开发, refType=null, unstructuredReference=邓田,余翼. 基于PSO-Faster R-CNN改进算法的矿石识别分类研究[J]. 矿业研究与开发,2021, 41 (2): 178-182., articleTitle=基于PSO-Faster R-CNN改进算法的矿石识别分类研究, refAbstract=null), Reference(id=1322164765804319332, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=2, pageStart=178, pageEnd=182, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=DENG Tian, YU Yi, journalName=Mining Research and Development, refType=null, unstructuredReference=DENG Tian, YU Yi. Research on ore identification and separation based on improved PSO-Faster R-CNN algorithm[J]. Mining Research and Development, 2021, 41 (2): 178-182., articleTitle=Research on ore identification and separation based on improved PSO-Faster R-CNN algorithm, refAbstract=null), Reference(id=1322164765875622501, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2025, volume=61, issue=4, pageStart=272, pageEnd=281, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=刘思元, 高凯, 雍龙泉, journalName=计算机工程与应用, refType=null, unstructuredReference=刘思元,高凯,雍龙泉. 改进RT-DETR的航拍小目标检测算法[J]. 计算机工程与应用,2025, 61 (4): 272-281., articleTitle=改进RT-DETR的航拍小目标检测算法, refAbstract=null), Reference(id=1322164765946925670, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2025, volume=61, issue=4, pageStart=272, pageEnd=281, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=LIU Siyuan, GAO Kai, YONG Longquan, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=LIU Siyuan, GAO Kai, YONG Longquan. Improved RT-DETR algorithm for aerial small object detection [J]. Computer Engineering and Applications, 2025, 61 (4): 272-281., articleTitle=Improved RT-DETR algorithm for aerial small object detection, refAbstract=null), Reference(id=1322164766014034535, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2022, volume=38, issue=13, pageStart=158, pageEnd=166, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=陈锋军, 张新伟, 朱学岩, journalName=农业工程学报, refType=null, unstructuredReference=陈锋军,张新伟,朱学岩,等. 基于改进EfficientDet的油橄榄果实成熟度检测[J]. 农业工程学报,2022, 38 (13): 158-166., articleTitle=基于改进EfficientDet的油橄榄果实成熟度检测, refAbstract=null), Reference(id=1322164766089532008, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2022, volume=38, issue=13, pageStart=158, pageEnd=166, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=CHEN Fengjun, ZHANG Xinwei, ZHU Xueyan, journalName=Transactions of the Chinese Society of Agricultural Engineering, refType=null, unstructuredReference=CHEN Fengjun, ZHANG Xinwei, ZHU Xueyan, et al. Detection of the olive fruit maturity based on improved EfficientDet [J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38 (13): 158-166., articleTitle=Detection of the olive fruit maturity based on improved EfficientDet, refAbstract=null), Reference(id=1322164766181806697, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=10, pageStart=67, pageEnd=73, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=鲁杰, 王劭琛, 魏征, journalName=实验技术与管理, refType=null, unstructuredReference=鲁杰,王劭琛,魏征. 基于YOLOv8-ER的带式输送机煤矸目标检测[J]. 实验技术与管理,2024, 41 (10): 67-73., articleTitle=基于YOLOv8-ER的带式输送机煤矸目标检测, refAbstract=null), Reference(id=1322164766278275690, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=10, pageStart=67, pageEnd=73, url=null, language=null, rfNumber=[18], rfOrder=27, authorNames=LU Jie, WANG Shaochen, WEI Zheng, journalName=Experimental Technology and Management, refType=null, unstructuredReference=LU Jie, WANG Shaochen, WEI Zheng. YOLOv8-ER belt conveyor coal gangue target monitoring [J]. Experimental Technology and Management, 2024, 41 (10): 67-73., articleTitle=YOLOv8-ER belt conveyor coal gangue target monitoring, refAbstract=null), Reference(id=1322164766353773163, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, doi=null, pmid=null, pmcid=null, year=2025, volume=37, issue=null, pageStart=107984, pageEnd=108011, url=null, language=null, rfNumber=[19], rfOrder=28, authorNames=WANG A, CHEN H, LIU L H, journalName=Advances in Neural Information Processing Systems, refType=null, unstructuredReference=WANG A, CHEN H, LIU L H, et al. YOLOv10: real-time end-to-end object detection [J]. Advances in Neural Information Processing Systems, 2025, 37: 107984-108011., articleTitle=YOLOv10: real-time end-to-end object detection, refAbstract=null)], funds=[Fund(id=1322164764126597710, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, awardId=52434007, language=CN, fundingSource=国家自然科学基金项目(52434007), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322164757327630874, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, xref=1., ext=[AuthorCompanyExt(id=1322164757336019483, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757327630874, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Public Teaching Department, Liaoyuan Vocational Technical College, Liaoyuan, Jilin 136200, China), AuthorCompanyExt(id=1322164757344408092, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757327630874, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.辽源职业技术学院 公共教学部,吉林 辽源市 136200)]), AuthorCompany(id=1322164757461848605, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, xref=2., ext=[AuthorCompanyExt(id=1322164757604454942, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757461848605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Safety and Emergency Management and Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322164757625426463, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757461848605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.太原理工大学 安全与应急管理工程学院,山西 太原市 030024)])], figs=[ArticleFig(id=1322164761182196286, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, label=Fig.1, caption=Improved YOLOv11 network model, figureFileSmall=M6tyL1RvbacOEf2hT01kCg==, figureFileBig=S0VX9K3hbiMA+44rHNkSJA==, tableContent=null), ArticleFig(id=1322164761249305151, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, label=图1, caption=改进YOLOv11网络模型, figureFileSmall=M6tyL1RvbacOEf2hT01kCg==, figureFileBig=S0VX9K3hbiMA+44rHNkSJA==, tableContent=null), ArticleFig(id=1322164761412883008, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, label=Fig.2, caption=Calculation flowchart of LDConv, figureFileSmall=H0A5DcfmlmdPiyVrTs6tyg==, figureFileBig=hSebycCVsfSQxX/7u4yw+g==, tableContent=null), ArticleFig(id=1322164761479991873, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, label=图2, caption=LDConv计算流程, figureFileSmall=H0A5DcfmlmdPiyVrTs6tyg==, figureFileBig=hSebycCVsfSQxX/7u4yw+g==, tableContent=null), ArticleFig(id=1322164761593238082, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, label=Fig.3, caption=Structural of edge enhancement module, figureFileSmall=XydkrEkTqPfxhhOJWlEjcg==, figureFileBig=sT7soEbpVe9izGr9YvlfNw==, tableContent=null), ArticleFig(id=1322164761647764035, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, label=图3, caption=边缘增强模块结构, figureFileSmall=XydkrEkTqPfxhhOJWlEjcg==, figureFileBig=sT7soEbpVe9izGr9YvlfNw==, tableContent=null), ArticleFig(id=1322164761706484292, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, label=Fig.4, caption=Decline curves of loss value of model, figureFileSmall=w7XKFMolAMqq14KrxMQTDw==, figureFileBig=wfzj1oOQqQvx9YvKBSCFdw==, tableContent=null), ArticleFig(id=1322164761773593157, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, label=图4, caption=模型损失值下降曲线, figureFileSmall=w7XKFMolAMqq14KrxMQTDw==, figureFileBig=wfzj1oOQqQvx9YvKBSCFdw==, tableContent=null), ArticleFig(id=1322164761836507718, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, label=Fig.5, caption=Thermal maps of foreign object detection results, figureFileSmall=ddcWpGOqNiia1mxT1QR0Hw==, figureFileBig=eBoRlaAEiMy8wua8AZEC+Q==, tableContent=null), ArticleFig(id=1322164761903616583, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, label=图5, caption=异物检测结果热力图, figureFileSmall=ddcWpGOqNiia1mxT1QR0Hw==, figureFileBig=eBoRlaAEiMy8wua8AZEC+Q==, tableContent=null), ArticleFig(id=1322164761983308360, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, label=Fig.6, caption=Visualization results of foreign object detection, figureFileSmall=8UWYnkFcqbpwBT+jT195gg==, figureFileBig=jH5H/bhE5w5gdSqtOxbgAw==, tableContent=null), ArticleFig(id=1322164762063000137, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, label=图6, caption=异物检测可视化结果, figureFileSmall=8UWYnkFcqbpwBT+jT195gg==, figureFileBig=jH5H/bhE5w5gdSqtOxbgAw==, tableContent=null), ArticleFig(id=1322164763774276170, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, label=Table 1, caption=

Comparison of ablation test results

, figureFileSmall=null, figureFileBig=null, tableContent=
模型LDConvEEMWIoUP/%R/%mAP50/%浮点计算量/(×109)参数量/(×106)
186.880.583.36.52.6
2√88.478.384.16.32.5
3√89.677.985.37.02.7
4√√92.584.187.76.82.6
5√√√94.386.190.26.82.6
), ArticleFig(id=1322164763841385035, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, label=表1, caption=

消融试验结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型LDConvEEMWIoUP/%R/%mAP50/%浮点计算量/(×109)参数量/(×106)
186.880.583.36.52.6
2√88.478.384.16.32.5
3√89.677.985.37.02.7
4√√92.584.187.76.82.6
5√√√94.386.190.26.82.6
), ArticleFig(id=1322164763942048332, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=EN, label=Table 2, caption=

Comparison of different object detection models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型P/%R/%mAP50/%浮点计算量/(×109)参数量/(×106)FPS/(帧•s-1)
Faster R-CNN84.975.380.6118.5136.938
RT-DETR90.684.886.256.919.978
EfficientDet-D283.579.181.110.48.086
YOLOv8n81.682.782.88.23.1120
YOLOv10n87.274.980.46.72.2144
YOLOv11s88.082.784.521.19.4113
本文模型94.386.190.26.82.6127
), ArticleFig(id=1322164764021740109, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, language=CN, label=表2, caption=

不同目标检测模型对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型P/%R/%mAP50/%浮点计算量/(×109)参数量/(×106)FPS/(帧•s-1)
Faster R-CNN84.975.380.6118.5136.938
RT-DETR90.684.886.256.919.978
EfficientDet-D283.579.181.110.48.086
YOLOv8n81.682.782.88.23.1120
YOLOv10n87.274.980.46.72.2144
YOLOv11s88.082.784.521.19.4113
本文模型94.386.190.26.82.6127
)], attaches=null, journal=Journal(id=1225396331729022976, delFlag=0, nameCn=矿业研究与开发, nameEn=Mining Research and Development, nameHistory1=null, nameHistory2=null, issn=1005-2763, eissn=null, cn=43-1215/TD, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=BLic9JllTIKtYRYod5zIVQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Mining Research and Development, journalRemark=null, publicationField=null, createdTime=1770086852251, updatedTime=1784018193958, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=K, firstLetterEn=K, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=BLic9JllTIKtYRYod5zIVQ==, picEn=Bqi6ei4JhI5hinJcqiOo2A==, jcr=null, cjcr=null, exts=[JournalExt(id=1283828614093321209, language=CN, name=矿业研究与开发, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1784018193982, updatedTime=1784018193982, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.chinamine.org.cn/kyyjykf/author/login, submissionEditorUrl=http://www.chinamine.org.cn/kyyjykf/editor/login, submissionReviewUrl=http://www.chinamine.org.cn/kyyjykf/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1283828614143652858, language=EN, name=Mining Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1784018193994, updatedTime=1784018193994, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.chinamine.org.cn/kyyjykfen/author/login, submissionEditorUrl=http://www.chinamine.org.cn/kyyjykfen/editor/login, submissionReviewUrl=http://www.chinamine.org.cn/kyyjykfen/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1225396423026438145, websiteList=[Website(id=1225409554104627231, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225396423026438145, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kyyjykf/CN, language=CN, createTime=1770090004708, createBy=18614031015, updateTime=1770090031995, updateBy=18614031015, name=矿业研究与开发-中文, tplId=1146099689490845704, title=矿业研究与开发, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1228001470277153440, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=articleTextType, value=kx, createTime=1770707965678, updateTime=1770707965678, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470256181917, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=banner, value=null, createTime=1770707965673, updateTime=1770707965673, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470293930659, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=grayFlag, value=0, createTime=1770707965682, updateTime=1770707965682, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470251987612, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=logo, value=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/file/pic?fileId=++etCLRiS7F8czudkkUdPA==, createTime=1770707965672, updateTime=1770707965672, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470302319269, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=minRunFlag, value=0, createTime=1770707965684, updateTime=1770707965684, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470268764831, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/file/pic, createTime=1770707965676, updateTime=1770707965676, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470298124964, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=silenceFlag, value=0, createTime=1770707965683, updateTime=1770707965683, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470264570526, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770707965675, updateTime=1770707965675, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470281347745, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=themeColor, value=null, createTime=1770707965679, updateTime=1770707965679, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470285542050, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=themeStyle, value=null, createTime=1770707965680, updateTime=1770707965680, creator=18614031015, updator=18614031015)]), Website(id=1225409554180124705, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225396423026438145, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kyyjykf/EN, language=EN, createTime=1770090004726, createBy=18614031015, updateTime=1770090069284, updateBy=18614031015, name=矿业研究与开发英文, tplId=1146101810881728533, title=Mining Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1225410562574696778, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=articleTextType, value=kx, createTime=1770090245145, updateTime=1770090245145, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562553725255, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=banner, value=null, createTime=1770090245140, updateTime=1770090245140, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562612445517, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=grayFlag, value=0, createTime=1770090245154, updateTime=1770090245154, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562536948038, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=logo, value=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/file/pic?fileId=++etCLRiS7F8czudkkUdPA==, createTime=1770090245136, updateTime=1770090245136, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562629222735, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=minRunFlag, value=0, createTime=1770090245158, updateTime=1770090245158, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562566308169, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/file/pic, createTime=1770090245143, updateTime=1770090245143, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562620834126, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=silenceFlag, value=0, createTime=1770090245156, updateTime=1770090245156, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562562113864, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770090245142, updateTime=1770090245142, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562583085387, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=themeColor, value=null, createTime=1770090245147, updateTime=1770090245147, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562604056908, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=themeStyle, value=null, createTime=1770090245152, updateTime=1770090245152, creator=18614031015, updator=18614031015)])], journalTitle=矿业研究与开发, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Mining Research and Development, journalPhotoCn=BLic9JllTIKtYRYod5zIVQ==, journalPhotoEn=Bqi6ei4JhI5hinJcqiOo2A==, journalFirstLetter=K, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/Y2025/V45/I11/258, detailUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/Y2025/V45/I11/258, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/PDF/Y2025/V45/I11/258, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/PDF/Y2025/V45/I11/258, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1764000000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于线性可变形卷积的煤矿输送带异物检测算法研究
收藏切换
PDF下载
王瑞 1 , 司蕊 2 , 郝朝瑜 2 , 元永国 1
矿业研究与开发 | 矿山机电与矿业智能化 2025,45(11): 258-265
收起
收藏切换
矿业研究与开发 |矿山机电与矿业智能化 2025 , 45 (11) : 258 -265
基于线性可变形卷积的煤矿输送带异物检测算法研究
全屏
[Author(id=1322164759366062625, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=502176104@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322164759449948707, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759366062625, language=EN, stringName=Rui WANG, firstName=Rui, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Public Teaching Department, Liaoyuan Vocational Technical College, Liaoyuan, Jilin 136200, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322164759517057572, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759366062625, language=CN, stringName=王瑞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.辽源职业技术学院 公共教学部,吉林 辽源市 136200, bio={"content":"

王瑞(1983—),女,吉林辽源人,硕士,副教授,主要从事企业安全生产数学建模方面的教学与研究工作。E-mail:

"}, bioImg=null, bioContent=

王瑞(1983—),女,吉林辽源人,硕士,副教授,主要从事企业安全生产数学建模方面的教学与研究工作。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322164757327630874, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, xref=1., ext=[AuthorCompanyExt(id=1322164757336019483, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757327630874, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Public Teaching Department, Liaoyuan Vocational Technical College, Liaoyuan, Jilin 136200, China), AuthorCompanyExt(id=1322164757344408092, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757327630874, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.辽源职业技术学院 公共教学部,吉林 辽源市 136200)])]), Author(id=1322164759592555046, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322164759672246824, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759592555046, language=EN, stringName=Rui SI, firstName=Rui, middleName=null, lastName=SI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Safety and Emergency Management and Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322164759730967081, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759592555046, language=CN, stringName=司蕊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.太原理工大学 安全与应急管理工程学院,山西 太原市 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322164757461848605, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, xref=2., ext=[AuthorCompanyExt(id=1322164757604454942, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757461848605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Safety and Emergency Management and Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322164757625426463, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757461848605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.太原理工大学 安全与应急管理工程学院,山西 太原市 030024)])]), Author(id=1322164759819047467, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322164759915516461, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759819047467, language=EN, stringName=Chaoyu HAO, firstName=Chaoyu, middleName=null, lastName=HAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Safety and Emergency Management and Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322164759991013934, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164759819047467, language=CN, stringName=郝朝瑜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.太原理工大学 安全与应急管理工程学院,山西 太原市 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322164757461848605, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, xref=2., ext=[AuthorCompanyExt(id=1322164757604454942, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757461848605, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Safety and Emergency Management and Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322164757625426463, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757461848605, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.太原理工大学 安全与应急管理工程学院,山西 太原市 030024)])]), Author(id=1322164760062317104, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322164760142008882, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164760062317104, language=EN, stringName=Yongguo YUAN, firstName=Yongguo, middleName=null, lastName=YUAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Public Teaching Department, Liaoyuan Vocational Technical College, Liaoyuan, Jilin 136200, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322164760230089267, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, authorId=1322164760062317104, language=CN, stringName=元永国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.辽源职业技术学院 公共教学部,吉林 辽源市 136200, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322164757327630874, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, xref=1., ext=[AuthorCompanyExt(id=1322164757336019483, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757327630874, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Public Teaching Department, Liaoyuan Vocational Technical College, Liaoyuan, Jilin 136200, China), AuthorCompanyExt(id=1322164757344408092, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322164751325581813, companyId=1322164757327630874, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.辽源职业技术学院 公共教学部,吉林 辽源市 136200)])])]
王瑞1 , 司蕊2, 郝朝瑜2, 元永国1
作者信息
  • 1.辽源职业技术学院 公共教学部,吉林 辽源市 136200
  • 2.太原理工大学 安全与应急管理工程学院,山西 太原市 030024
作者简介:

王瑞(1983—),女,吉林辽源人,硕士,副教授,主要从事企业安全生产数学建模方面的教学与研究工作。E-mail:

Research on Foreign Object Detection Algorithm for Coal Mine Conveyor Belt Based on Linear Deformable Convolution
Rui WANG1 , Rui SI2, Chaoyu HAO2, Yongguo YUAN1
Affiliations
  • 1.Public Teaching Department, Liaoyuan Vocational Technical College, Liaoyuan, Jilin 136200, China
  • 2.College of Safety and Emergency Management and Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China
出版时间: 2025-11-25
文章导航
收藏切换

针对煤矿输送带上的异物因形状特殊、特征不明显,导致现有机器视觉方法无法有效检测出异物的问题,提出了改进YOLOv11模型。首先,采用线性可变形卷积构建C3k2-LDC特征提取模块,使模型具备对不规则形状异物的特征提取能力;然后,引入边缘增强模块,采用多尺度特征融合策略,有效强化了弱特征异物的边缘信息;最后,提出基于WIoU的损失函数优化方案,减少低质量数据样本对训练的影响。通过消融试验、对比试验、热力图及可视化分析,验证改进YOLOv11模型的有效性及鲁棒性。结果表明:改进YOLOv11模型的mAP50为90.2%,相比RT-DETR、EfficientDet-D2、YOLOv8n、YOLOv11s模型分别提升了4.0,9.1,7.4,5.7个百分点;轻量化方面,改进YOLOv11模型的浮点计算量和参数量分别为6.8×109、2.6×106,检测速度为127帧/s,可在保证检测精度的基础上实现实时异物检测任务;相比原模型,改进模型对复杂异物特征的关注度更高,具有良好的鲁棒性。研究结果可为矿山安全管理提供技术支撑。

输送带  /  异物检测  /  深度学习  /  线性可变形卷积  /  改进YOLOv11模型

Aiming at the problem that the existing machine vision methods cannot effectively detect foreign objects due to the special shape and unobvious characteristics of foreign objects on coal mine conveyor belts, an improved YOLOv11 model was proposed. Firstly, the C3k2-LDC feature extraction module was constructed using linear deformable convolution, so that the model has the ability to extract features of irregular shaped foreign objects. Then, the edge enhancement module was introduced, and the multi-scale feature fusion strategy was adopted to effectively strengthen the edge information of the weak feature foreign object. Finally, a loss function optimization scheme based on WIoU was proposed to reduce the impact of low-quality data samples on training. The effectiveness and robustness of the improved YOLOv11 model were verified by ablation test, comparative test, thermal map and visual analysis. The results show that the mAP50 of the improved YOLOv11 model is 90.2%, which is 4.0, 9.1, 7.4 and 5.7 percentage points higher than that of RT-DETR, EfficientDet-D2, YOLOv8n and YOLOv11s models, respectively. In terms of lightweight, the floating-point calculation amount and parameter amount of the improved YOLOv11 model are 6.8×109 and 2.6×106 respectively, and the detection speed is 127 frames/s, which can realize the real-time foreign object detection task on the basis of ensuring the detection accuracy. Compared with the original model, the improved model pays more attention to the characteristics of complex foreign objects and has good robustness. The research results can provide technical support for mine safety management.

Conveyor belt  /  Foreignobject detection  /  Deep learning  /  Linear deformable convolution  /  Improved YOLOv11 model
王瑞, 司蕊, 郝朝瑜, 元永国. 基于线性可变形卷积的煤矿输送带异物检测算法研究. 矿业研究与开发, 2025 , 45 (11) : 258 -265 .
Rui WANG, Rui SI, Chaoyu HAO, Yongguo YUAN. Research on Foreign Object Detection Algorithm for Coal Mine Conveyor Belt Based on Linear Deformable Convolution[J]. Mining Research and Development, 2025 , 45 (11) : 258 -265 .
矿产资源作为人类社会赖以生存的关键物质基础,不仅是国家安全与经济繁荣的战略支撑,还是矿业持续发展的重要保障[1]。在煤炭开采这一关键环节中,确保开采过程的安全性与稳定性,提高开采效率与质量,是推动矿业高质量发展的核心要素[2]。为实现这一目标,煤矿在运输环节普遍采用了带式输送机,其凭借长距离运输、大运量等诸多优势,在煤炭、金属及建筑行业发挥着重要作用。然而,在实际运行过程中,正常煤流传输皮带上可能会遭遇大块煤矸石、锚杆等异物的侵扰,这些异物可能在落煤口引发堆煤、堵煤等问题,严重影响运输效率,且对整个工作系统中的其他设备构成安全隐患,威胁整体生产安全[3]。因此,通过视频目标检测技术,对异物进行检测并提前预警,对保障煤炭开采的顺利进行和推动矿业高质量发展具有重要意义。
针对矿石输送带异物检测问题,国内外学者开展了大量的研究。LUO等[4]针对煤矿环境复杂问题,提出用暗通道去噪方法提高图像清晰度,再通过改进YOLOv5网络,在所提出的异物数据集中实现了94.9%的均值平均精度。YAO等[5]为提高带式输送机中大纵横比异物的检测率,通过CBAM注意力和IAT图像增强模块,丰富输入信息,设计了一种旋转解耦头,并构建了YOLOX网络,最终在异物检测试验中实现了93.87%的均值平均精度。DAI等[6]提出了基于机器视觉的检测方法,通过加权多尺度Retinex图像增强算法提高捕获图像质量,利用多尺度模板匹配算法和多层感知器网络来识别和筛选煤炭带式传送机上的大型异物。MIAO等[7]针对异物检测算法在硬件中实时性差的问题,提出了改进Nanodet方法,通过改进IoU损失提高网络检测效率,最终在ARM上实现了94.3%的均值平均精度和30帧/s的检测速度。陈瑞等[8]提出一种基于改进YOLOv8的输送带异物检测方法,利用Ghost模块和网络剪枝技术减少冗余参数,在嵌入式平台NVIDIA Jetson Xavier NX上进行试验,结果表明,改进模型的均值平均精度为90.5%,运算速度达到30帧/s。郭志聪等[9]针对输送带异物检测模型在低光照环境下出现性能下降的问题,提出利用图像增强算法进行预处理,然后采用动态蛇形卷积提升对细长异物的检测精度,最终达到了86.6%的均值平均精度。马恒等[10]针对煤炭输送带异物检测问题,基于带有压缩激励模块的残差视觉网络与高效注意力,构建出轻量化结构,实现了88.20%的均值平均精度。
现有研究针对矿业输送带视频中的异物检测问题,已从图像质量优化、异物特征提取及模型参数调整等多个角度提出了相应的解决方案,但均未考虑输送带场景下对特征不显著异物和多尺度特征异物的检测难题。针对该问题,本文从特征提取、边缘增强及损失函数优化3个方面,提出了改进YOLOv11模型。通过模块间的协同优化,克服单一方法在复杂形状识别、边缘特征提取和低质量样本处理上的局限性,实现对异物的精确识别与实时定位。研究结果可为煤炭开采工作中的安全预警系统提供更高效的技术支持。
YOLOv11网络结构[11]在YOLOv8网络结构的基础上进行了改进,进一步提升了实时目标检测的性能。YOLOv11网络由输入端、主干网络和颈部网络及检测头4部分组成。输入端继续使用YOLOv4提出的Mosaic数据增强方法,增强模型泛化能力。主干网络部分,YOLOv11提出C3k2和C2PSA特征提取模块,C3k2内部由C3k模块堆叠构成,当其输入参数C3k为False时,C3k2与YOLOv8中的C2f模块相同;C2PSA是具有注意力机制的模块,具备多尺度特征提取能力。颈部网络部分,采用PAN-FPN(特征金与塔网络路径聚合网络)结构,通过在FPN上增加自底向上的路径增强多尺度信息的融合。检测头部分,采用解耦头设计,在YOLOv8的基础上引入深度可分离卷积,减少检测头的计算复杂度。
原始YOLOv11模型采用传统二维卷积提取特征,具有局部感受视野的特点,但无法有效检测煤矿输送带上的复杂形状异物。针对该问题,本文提出改进YOLOv11模型,如图1所示。
首先,在线性可变形卷积(Linear Deformable Convolution,LDConv)中引入C3k2模块,构造C3k2-LDC模块,提高网络对各种复杂特征异物的检测能力;然后,采用边缘增强模块(Edge Enhancement Module,EEM)替换SPPF模块,丰富异物的边缘特征,使网络对其位置进行快速定位;最后,利用WIoU替换CIoU损失,减少低质量数据样本对训练的影响。
卷积神经网络中,标准卷积的采样位置是固定的,具有局部感受野的特点,无法感知其他位置的信息,难以有效检测出煤矿输送带中如锚杆等形状特殊的异物。针对该问题,本文提出利用线性可变形卷积(LDConv)[12]替换标准卷积,实现不规则特征提取过程。
LDConv提供可变形卷积机制,其计算原理见公式(1)。
式中:Y表示可变形卷积函数操作;P0为卷积采样原点,在可变形卷积中代表区域最左上角的点;R为生成的采样网格;B为网格位置偏移量;x(P0+B)为对应网格位置的像素值;wB为对应网格权重。
与传统可变形卷积不同的是,LDConv允许卷积具有任意的采样形状和大小。且卷积参数量随尺寸增加的方式被优化为线性增加,这为硬件实现提供了更高的灵活性。LDConv整体计算流程如图2所示。首先,确定可变形卷积的尺寸和初始形状,并定义为变量N,依据初始采样形状生成初始采样位置信息;然后,针对尺寸为C×W×H的输入图像,通过二维卷积提取采样位置的偏移信息,得到尺寸为2N×W×H的偏移量,将偏移量与各自对应的采样位置信息相加,得到最终的采样形状;最后,通过重采样调整相应位置的特征,再应用卷积、归一化、激活运算来提取特征。
LDConv为模型提供了针对特殊形状目标特征的提取能力。但在矿井环境中,煤矿输送带上异物的特征并不明显,锚杆和大块煤矸石在煤矿流中只具有少量的边缘特征,不易被检测。因此,为增强模型对异物位置信息的关注度,本文提出将边缘增强模块[13]融入模型的主干网络。
边缘增强模块的结构如图3所示,其利用传统图像差分处理思想,用3×3平均池化来平滑图像,扩展感受野,降低图像细节。再用原图像减去平滑细节后的图像,得到的结果则为突出细节信息的图像。
边缘增强模块的处理过程如下。
(1)对输入图像进行特征提取,通过多次平均池化获得不同尺度的平滑图像,其计算过程见公式(2)和公式(3)。
式中:Fin为输入图像;F0为初始特征图;f1表示带有归一化和Sigmoid激活的1×1卷积计算操作;fa表示平均池化操作;Ft+1表示下一个尺度的特征图。
(2)通过作差的方式,增强图像边缘特征的表达,再利用残差结构防止特征丢失,计算过程见公式(4)。
式中:Fx表示边缘增强模块的输入;Feex代表输出。
(3)将所有特征图通过fc操作进行通道维度拼接,再用1×1卷积进行通道缩减,得到输出结果Fout,计算过程见公式(5)。
在模型训练阶段,边界框回归损失函数对模型性能提升具有较显著的影响。具体来说,损失函数计算的是网络推理结果与人工标注数据之间的差异度量值。但现有很多工作未考虑到样本质量对模型性能的影响,例如煤矿输送带的异物可能因光照强度、位置的不同,使其图像质量有差异。针对该问题,本文提出利用WIoU[14]作为模型边界框回归损失。计算WIoUv1损失(记为LWIoUv1),见公式(6)。
式中:x、y表示预测边界框的中心点横坐标和纵坐标;xgt、ygt表示真实边界框的中心点横坐标与纵坐标;Wg和Hg为预测框和真实框的最小外接矩形的宽和高;LIoU为交并比损失;∗表示将最小外接矩形的Wg和Hg与梯度计算分离。
为避免低质量样本对训练产生影响,引入离群度参数β,并构建梯度增益系数r,降低高质量边界框竞争力和低质量边界框所产生的有害梯度,具体见公式(7)和公式(8)。
式中:为LIoU的滑动平均值;为单调聚焦系数,其值随着LIoU的减小而减少;α和δ为超参数。
利用增益系数r构建WIoU损失(记为LWIoU),并作为最终的边界框回归损失,见公式(9)。
试验平台采用的GPU为GeForce RTX 3090,显存24 GB。CPU主频为2.50 GHz,核心数为24,运行内存为32 GB。深度学习框架使用PyTorch 1.9.0,CUDA版本为11.1。超参数方面,训练轮数为200轮,初始学习率为0.01,权重衰减系数为0.000 5,Batch size为16,优化器采用SGD,优化器动量为0.937。
试验所用的数据集来自中国矿业大学公开的煤矿井下异物数据集CUMT-BeLT。数据集中的样本皆从煤矿输送带现场拍摄,内部包含正常煤流、大石块、锚杆共3个类别。数据集共4 800个图像样本,每个类别各包含1 300张训练集图片和300张测试集图片。
试验采用的模型精度评价指标包括精确率(Precision,P)、召回率(Recall,R)、均值平均精度(mean Average Precision,mAP)。采用的模型复杂度评价指标包括参数量、浮点运算次数、每秒帧数(Frames Per Second,FPS)。
为验证WIoU损失对模型改进的有效性,在模型训练的前100轮,记录每轮训练后的WIoU与CIoU损失值,绘制损失值曲线如图4所示。由图4可知,在训练轮数达到60轮时,损失值下降曲线趋于平稳,代表模型收敛。且WIoU损失值下降速度比CIoU更快,最终的损失值也比CIoU更小,验证了WIoU对模型改进的有效性。
为验证不同改进方法对模型性能的影响,在试验环境及其他参数不变的情况下,以YOLOv11n为基准模型进行消融试验。试验结果见表1。表中√代表添加该模块,mAP50表示IoU阈值为0.5时的mAP值。
由表1可知,在原模型1中引入LDConv后,得到模型2,相比于模型1,模型2的mAP50提升了0.8个百分点,浮点计算量减少了0.2×109,表明LDConv能够在有效捕获更丰富特征的同时,降低网络复杂度。在模型2的基础上加入EEM模块,得到模型4,模型4的mAP50达到了87.7%,相比模型1提升了4.4个百分点,浮点计算量增加了0.3×109,精确率提升了5.7个百分点,证明了LDConv和EEM对传送带上异物特征提取的有效性。在模型4的基础上再使用WIoU损失函数,模型精确率、召回率和mAP50分别达到94.3%、86.1%、90.2%,浮点计算量和参数量分别为6.8×109和2.6×106。消融试验结果表明,本文改进的每一个模块对传动带异物目标检测均有优势,综合改进后的模型能够在增加较小计算量的基础上,提升目标检测精度。
为验证本文提出改进算法的有效性,对相同的数据集分别采用Faster R-CNN[15]、RT-DETR[16]、EfficientDet-D2[17]、YOLOv8n[18]、YOLOv10n[19]和YOLOv11s网络进行对比试验,结果见表2。
由表2可知,在检测精度方面,改进模型的P、R、mAP50分别为94.3%、86.1%、90.2%,相比经典的两阶段模型Faster R-CNN,分别提高了9.4,10.8,9.6个百分点;相比实时端到端目标检测器RT-DETR提高了3.7,1.3,4.0个百分点;相比YOLOv11s模型提高了6.3,3.4,5.7个百分点,表明本文模型具有全面的性能优势。在模型复杂度方面,改进模型的浮点计算量、参数量、检测速度分别为6.8×109、2.6×106、127帧/s,相比Faster R-CNN、RT-DETR、EfficientDet-D2等模型具有显著的优势,但检测速度较YOLOv10n模型仍有提升空间。综上,通过引入LDConv、EEM和WIoU模块对YOLOv11进行优化,模型在检测精度方面取得了较为显著的提升,其性能优于现有的经典模型与最新模型,尽管参数量略高于YOLOv10n模型,但本文模型的mAP50比YOLOv10n提升了9.8个百分点,同时保持了127帧/s的实时检测速度,仍然能够有效满足矿井输送带异物检测的实时性要求。
为了能更直观地展示改进模型的有效性,从数据集中选取了具有代表性的4类复杂图像样本进行分析。通过Grad-CAM生成目标检测热力图,以呈现模型对不同区域像素关注度的分布特征(温度越高,代表模型关注度越高)。图像样本具体包括特殊形状异物、多尺度异物、低显著性异物以及小目标异物。试验结果如图5所示。
由图5可以看出,在检测特殊几何形状和小目标异物时,初始YOLOv11模型表现出明显的关注度缺失;相比之下,改进后的模型在目标区域表现出显著的特征响应,权重分布更为合理。在多尺度异物检测时,初始模型仅能识别大尺度石块目标,而对背景中的小尺度石块存在漏检现象,改进模型则实现了多尺度异物的完整检测。在低显著性异物检测方面,改进模型较初始模型的特征强度更高。可知改进后的YOLOv11模型在复杂场景下的适应性和检测性能均得到了提升。
图6展示了模型在煤矿输送带异物检测任务中面对各种极端条件下的实际性能表现。其中水雾干扰和物体遮挡图像截取自其他煤矿任务现场视频。噪声干扰图像中添加了椒盐噪声,以模拟煤尘等环境因素的影响。
从图6可以看出,在水雾干扰的场景下,该模型能够有效抵御雾气的影响,成功识别出石块异物。在物体遮挡的情况下,模型能够将同一物体从遮挡部位分开检测。此外,在面对噪声干扰、光照不足等情况时,模型均能够有效检测出异物,证明模型具有良好的鲁棒性。
针对煤矿输送带上的异物因特征复杂导致机器视觉系统难以检测的问题,本文构建了基于改进YOLOv11模型的新型深度学习框架。主要结论如下。
(1)改进YOLOv11模型首先利用线性可变形卷积,提高对异物复杂特征的提取能力;然后采用边缘增强模块,突出异物的边缘特征信息;最后用WIoU替换CIoU损失,减少低质量样本的影响。
(2)消融试验结果表明,采用线性可变形卷积、边缘增强模块、WIoU对YOLOv11模型进行改进后,模型准确率、召回率、mAP50分别为94.3%、86.1%、90.2%,相比原模型分别提升了7.5,5.6,6.9个百分点,验证了改进YOLOv11模型的有效性。与其他模型进一步对比可知,本文模型在轻量化和精度两方面均具备综合优势。
(3)热力图和可视化检测结果表明,相比原模型,改进后的模型对异物的复杂特征表现出更高的关注度,能够检测出小目标、特殊形状、多尺度和低显著性等复杂特征异物,且不受水雾、噪声、光照和遮挡等环境因素的干扰,证明改进模型具有良好的鲁棒性。
  • 国家自然科学基金项目(52434007)
参考文献 引证文献
排序方式:
[1]
王国法,庞义辉,任怀伟,等. 智慧矿山系统工程及关键技术研究与实践[J]. 煤炭学报,2024, 49 (1): 181-202.
WANG Guofa, PANG Yihui, REN Huaiwei, et al. System engineering and key technologies research and practice of smart mine[J]. Journal of China Coal Society, 2024, 49 (1): 181-202.
[2]
王国法,巩师鑫,申凯. 煤矿智能安控技术体系与高质量发展对策[J]. 矿业安全与环保,2023, 50 (5): 1-8.
WANG Guofa, GONG Shixin, SHEN Kai. Intelligent security control technology system and high-quality development countermeasures for coal mines [J]. Mining Safety & Environmental Protection, 2023, 50 (5): 1-8.
[3]
程德强,徐进洋,寇旗旗,等. 融合残差信息轻量级网络的运煤皮带异物分类[J]. 煤炭学报,2022, 47 (3): 1361-1369.
CHENG Deqiang, XU Jinyang, KOU Qiqi, et al. Lightweight network based on residual information for foreign body classification on coal conveyor belt[J]. Journal of China Coal Society, 2022, 47 (3): 1361-1369.
[4]
LUO B X, KOU Z M, HAN C, et al. A faster and lighter detection method for foreign objects in coal mine belt conveyors [J]. Sensors (Basel, Switzerland), 2023, 23 (14): 6276.
[5]
YAO R B, QI P, HUA D Z, et al. A foreign object detection method for belt conveyors based on an improved YOLOX model[J]. Technologies, 2023, 11 (5): 114.
[6]
DAI L L, ZHANG X, GARDONI P, et al. A new machine vision detection method for identifying and screening out various large foreign objects on coal belt conveyor lines[J]. Complex & Intelligent Systems, 2023, 9 (5): 5221-5234.
[7]
MIAO D, WANG Y M, YANG L, et al. Foreign object detection method of conveyor belt based on improved nanodet[J]. IEEE Access, 2023, 11: 23046-23052.
[8]
陈瑞,张鹏,施海馨,等. 基于改进YOLOv8的输送带异物检测研究[J]. 煤矿机械,2024, 45 (9): 175-178.
CHEN Rui, ZHANG Peng, SHI Haixin, et al. Research on foreign body detection in conveyor belt based on improved YOLOv8[J]. Coal Mine Machinery, 2024, 45 (9): 175-178.
[9]
郭志聪,张雷. 基于改进YOLOv8的低照度煤矿传送带异物识别算法[J]. 电子测量技术,2024, 47 (21): 188-196.
GUO Zhicong, ZHANG Lei. Foreign object recognition algorithm of low-light coal mine conveyor belt based on improved YOLOv8 [J]. Electronic Measurement Technology, 2024, 47 (21): 188-196.
[10]
马恒,刘利灿,高科. 融合多尺度特征的轻量化煤炭输送带异物检测方法[J]. 安全与环境学报,2024, 24 (12): 4617-4629.
MA Heng, LIU Lican, GAO Ke. Multi-scale feature fusion method for detecting foreign objects on lightweight coal conveyor belts[J]. Journal of Safety and Environment, 2024, 24 (12): 4617-4629.
[11]
ALKHAMMASH E H. Multi-classification using YOLOV11 and hybrid YOLO11 n-mobilenet models: a fire classes case study[J]. Fire, 2025, 8 (1): 17.
[12]
ZHANG X, SONG Y Z, SONG T T, et al. LDConv: linear deformable convolution for improving convolutional neural networks [J]. Image and Vision Computing, 2024, 149: 105190.
[13]
GAO S X, ZHANG P P, YAN T Y, et al. Multi-scale and detail-enhanced segment anything model for salient object detection[C]//Proceedings of the 32nd ACM International Conference on Multimedia. New York: ACM, 2024: 9894-9903.
[14]
LIU Zhigang, SUN Baoshan, BI Kaiyu. Optimization of YOLOv7 based on PConv, SE Attention and Wise-IoU[J]. International Journal of Computational Intelligence and Applications, 2024, 23 (1): 335.
[15]
邓田,余翼. 基于PSO-Faster R-CNN改进算法的矿石识别分类研究[J]. 矿业研究与开发,2021, 41 (2): 178-182.
DENG Tian, YU Yi. Research on ore identification and separation based on improved PSO-Faster R-CNN algorithm[J]. Mining Research and Development, 2021, 41 (2): 178-182.
[16]
刘思元,高凯,雍龙泉. 改进RT-DETR的航拍小目标检测算法[J]. 计算机工程与应用,2025, 61 (4): 272-281.
LIU Siyuan, GAO Kai, YONG Longquan. Improved RT-DETR algorithm for aerial small object detection [J]. Computer Engineering and Applications, 2025, 61 (4): 272-281.
[17]
陈锋军,张新伟,朱学岩,等. 基于改进EfficientDet的油橄榄果实成熟度检测[J]. 农业工程学报,2022, 38 (13): 158-166.
CHEN Fengjun, ZHANG Xinwei, ZHU Xueyan, et al. Detection of the olive fruit maturity based on improved EfficientDet [J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38 (13): 158-166.
[18]
鲁杰,王劭琛,魏征. 基于YOLOv8-ER的带式输送机煤矸目标检测[J]. 实验技术与管理,2024, 41 (10): 67-73.
LU Jie, WANG Shaochen, WEI Zheng. YOLOv8-ER belt conveyor coal gangue target monitoring [J]. Experimental Technology and Management, 2024, 41 (10): 67-73.
[19]
WANG A, CHEN H, LIU L H, et al. YOLOv10: real-time end-to-end object detection [J]. Advances in Neural Information Processing Systems, 2025, 37: 107984-108011.
2025年第45卷第11期
PDF下载
43
20
引用本文
BibTeX
文章信息
  • 接收时间:2025-03-14
  • 首发时间:2026-10-28
  • 出版时间:2025-11-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-03-14
基金
国家自然科学基金项目(52434007)
作者信息
    1.辽源职业技术学院 公共教学部,吉林 辽源市 136200
    2.太原理工大学 安全与应急管理工程学院,山西 太原市 030024
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kyyjykf/CN/1322164751325581813
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏