Article(id=1241769334666756503, tenantId=1146029695717560320, journalId=1240670690148397066, issueId=1241769329201578292, articleNumber=null, orderNo=null, doi=10.3963/j.issn.1001-487X.2024.01.026, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1633968000000, receivedDateStr=2021-10-12, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1773990480342, onlineDateStr=2026-03-20, pubDate=1709222400000, pubDateStr=2024-03-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1773990480342, onlineIssueDateStr=2026-03-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773990480342, creator=13701087609, updateTime=1773990480342, updator=13701087609, issue=Issue{id=1241769329201578292, tenantId=1146029695717560320, journalId=1240670690148397066, year='2024', volume='41', issue='1', pageStart='1', pageEnd='220', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1773990479040, creator=13701087609, updateTime=1773992264087, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241776816298459159, tenantId=1146029695717560320, journalId=1240670690148397066, issueId=1241769329201578292, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241776816298459160, tenantId=1146029695717560320, journalId=1240670690148397066, issueId=1241769329201578292, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=196, endPage=201, ext={EN=ArticleExt(id=1241769335157490091, articleId=1241769334666756503, tenantId=1146029695717560320, journalId=1240670690148397066, language=EN, title=Research on Fragment Size Identification Method of Blasting Pile based on Deep Learning Technology, columnId=1240702076553065119, journalTitle=Blasting, columnName=BLASTING SAFETY, runingTitle=null, highlight=null, articleAbstract=

Boulder yield is an important index to evaluate the blasting quality in the blasting process of an open pit mine. Since a high boulder yield will not only greatly reduce the mining efficiency, but also increase the cost of secondary rock breaking, so fragments size statistics is an important work in open pit mining. Aiming at the problem that the statistics of fragment size is complex and not accurate enough, a statistical model of boulder yield was built by deep learning based on the takes the image data of blasting piles collected in the Unugetushan copper and molybdenum mine. Firstly, the annotated data set was initially segmented into an initial effect diagram of the mine rock contour based on the U-net image segmentation model. And then, the annotated data for training was optimized and the Resu-net model was improved on the basis of the residual learning module, which resulted in the final segmentation effect map of mine rock contour. Finally, the fragment size information of the blasting pile was obtained through the minimum external rectangle method combined with OpenCV image processing technology. The results show that the segmentation accuracy of U-net+Resu-net fragment size optimization model proposed in this study is 97.84% with an accurate image data segmentation. The statistics of fragment size in an inclined blasting pile is realized by OpenCV technology combined with the camera monocular imaging principle. In addition, the developed interactive interface is simple to operate and can quickly calculate the boulder yield.

, 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, authorCompany=null, fund=null, authors=null, authorsList=Li-jun CHEN, Guo-qiang CAI, Wen-bin ZHANG), CN=ArticleExt(id=1241769352157003960, articleId=1241769334666756503, tenantId=1146029695717560320, journalId=1240670690148397066, language=CN, title=基于深度学习技术的爆堆块度识别方法研究, columnId=1240702076704060068, journalTitle=爆破, columnName=安全与管理, runingTitle=null, highlight=null, articleAbstract=

在露天矿爆破开采过程中,大块率是评价爆破质量的一个重要指标。较高的大块率不仅会大大降低采装效率,同时也增加二次破岩的费用,因此大块率统计是露天矿开采中一项重要工作。针对目前矿山存在的矿岩大块率统计复杂且准确性不高的问题,以乌努格吐山铜钼矿为研究对象,收集了矿区内台阶爆破爆堆图像数据,构建了基于深度学习的爆堆大块率统计模型。首先基于U-net矿岩图像分割模型,初步分割标注处理的数据集,建立了矿岩轮廓初次分割效果图。在残差学习模块基础上,改进Resu-net模型,优化训练标注数据,获得了最终矿岩轮廓分割效果图。最后,采用OpenCV图像处理技术,通过最小外接矩形法确定了爆堆块度尺度信息。结果表明,本研究提出的U-net+Resu-net爆堆块度优化分割模型准确率达到97.84%,爆堆矿岩图像分割数据较准确。通过OpenCV技术与相机单目成像原理相结合的方法,实现了倾斜爆堆矿岩图像的爆堆块度统计。此外,所开发的交互式界面操作简单,可快速统计大块尺寸。满洲里乌努格吐山铜钼矿的应用表明,该方法可高效、准确统计爆堆块度,具有一定的推广价值。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=m18ALomB2c6c7ihqhj3viw==, magXml=MGxVEtNIZ7d9BhaDfT16eQ==, pdfUrl=null, pdf=ht5TT5AtseNJMk/s0frlSg==, pdfFileSize=7530337, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=vAHdkSlCqVSvcqbjXcTYAQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=bNirl2yGyGX42JpQaWeNrw==, mapNumber=null, authorCompany=null, fund=null, authors=

陈立军(1976-),男,项目经理、学士,主要从事矿山生产管理,(E-mail)

CHEN Li-jun (1976-), male, project manager, bachelor′s degree, mainly engaged in mining production management, (E-mail) .

, authorsList=陈立军, 蔡国强, 张文斌)}, authors=[Author(id=1241769352601600205, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=632545110@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241769352723235028, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, authorId=1241769352601600205, language=EN, stringName=Li-jun CHEN, firstName=Li-jun, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=China Railway 19 Bureau Group Mining Investment Co, LTD, Manzhouli 021400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241769352832286934, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, authorId=1241769352601600205, language=CN, stringName=陈立军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中铁十九局集团 矿业投资有限公司 新巴尔虎右旗分公司,满洲里 021400, bio={"content":"

陈立军(1976-),男,项目经理、学士,主要从事矿山生产管理,(E-mail)

CHEN Li-jun (1976-), male, project manager, bachelor′s degree, mainly engaged in mining production management, (E-mail) .

"}, bioImg=null, bioContent=

陈立军(1976-),男,项目经理、学士,主要从事矿山生产管理,(E-mail)

CHEN Li-jun (1976-), male, project manager, bachelor′s degree, mainly engaged in mining production management, (E-mail) .

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241769352442216642, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, xref=null, ext=[AuthorCompanyExt(id=1241769352467382469, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, companyId=1241769352442216642, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=China Railway 19 Bureau Group Mining Investment Co, LTD, Manzhouli 021400, China), AuthorCompanyExt(id=1241769352479965382, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, companyId=1241769352442216642, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中铁十九局集团 矿业投资有限公司 新巴尔虎右旗分公司,满洲里 021400)])]), Author(id=1241769352974893278, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, 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=1241769353100722407, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, authorId=1241769352974893278, language=EN, stringName=Guo-qiang CAI, firstName=Guo-qiang, middleName=null, lastName=CAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=China Railway 19 Bureau Group Mining Investment Co, LTD, Manzhouli 021400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241769353188802797, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, authorId=1241769352974893278, language=CN, stringName=蔡国强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中铁十九局集团 矿业投资有限公司 新巴尔虎右旗分公司,满洲里 021400, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241769352442216642, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, xref=null, ext=[AuthorCompanyExt(id=1241769352467382469, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, companyId=1241769352442216642, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=China Railway 19 Bureau Group Mining Investment Co, LTD, Manzhouli 021400, China), AuthorCompanyExt(id=1241769352479965382, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, companyId=1241769352442216642, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中铁十九局集团 矿业投资有限公司 新巴尔虎右旗分公司,满洲里 021400)])]), Author(id=1241769353352380658, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, 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=1241769353448849658, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, authorId=1241769353352380658, language=EN, stringName=Wen-bin ZHANG, firstName=Wen-bin, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=China Railway 19 Bureau Group Mining Investment Co, LTD, Manzhouli 021400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241769353566290173, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, authorId=1241769353352380658, language=CN, stringName=张文斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中铁十九局集团 矿业投资有限公司 新巴尔虎右旗分公司,满洲里 021400, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241769352442216642, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, xref=null, ext=[AuthorCompanyExt(id=1241769352467382469, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, companyId=1241769352442216642, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=China Railway 19 Bureau Group Mining Investment Co, LTD, Manzhouli 021400, China), AuthorCompanyExt(id=1241769352479965382, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, companyId=1241769352442216642, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中铁十九局集团 矿业投资有限公司 新巴尔虎右旗分公司,满洲里 021400)])])], keywords=[Keyword(id=1241769353729868036, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, orderNo=1, keyword=blasting fragment size), Keyword(id=1241769353843114251, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, orderNo=2, keyword=deep learning), Keyword(id=1241769353939583246, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, orderNo=3, keyword=monocular imaging), Keyword(id=1241769354094772500, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, orderNo=4, keyword=ore segmentation), Keyword(id=1241769354182852888, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, orderNo=1, keyword=爆堆块度), Keyword(id=1241769354300293401, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, orderNo=2, keyword=深度学习), Keyword(id=1241769354367402270, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, orderNo=3, keyword=单目成像), Keyword(id=1241769354430316834, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, orderNo=4, keyword=矿石分割)], refs=[Reference(id=1241769358238744944, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2011, volume=18, issue=4, pageStart=385, pageEnd=389, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=ZHANG Guo-ying, LIU Guan-zhou, ZHU Hong, journalName=International Journal of Minerals Metallurgy and Materials, refType=null, unstructuredReference=ZHANG Guo-ying, LIU Guan-zhou, ZHU Hong, et al. Segmentation algorithm of complex ore images based on templates transformation and reconstruction[J]. International Journal of Minerals Metallurgy and Materials, 2011, 18(4): 385-389., articleTitle=Segmentation algorithm of complex ore images based on templates transformation and reconstruction, refAbstract=null), Reference(id=1241769358335213938, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2014, volume=238 LNEE, issue=null, pageStart=1125, pageEnd=1131, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=KE Dong, JIANG Da-lin, journalName=Lecture Notes in Electrical Engineering, refType=null, unstructuredReference=KE Dong, JIANG Da-lin. Automated estimation of ore size distributions based on machine vision[J]. Lecture Notes in Electrical Engineering, 2014, 238 LNEE(null): 1125-1131., articleTitle=Automated estimation of ore size distributions based on machine vision, refAbstract=null), Reference(id=1241769358427488628, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=10.1016/J.ESWA.2022.116511, pmid=null, pmcid=null, year=2022, volume=null, issue=May, pageStart=194, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=CHEN Yi, WANG Ming-jing, AA Heidari, journalName=Expert Systems with Application, refType=null, unstructuredReference=CHEN Yi, WANG Ming-jing, AA Heidari, et al. Multithreshold image segmentation using a multi-strategy shuffled frog leaping algorithm[J]. Expert Systems with Application, 2022(May): 194., articleTitle=Multithreshold image segmentation using a multi-strategy shuffled frog leaping algorithm, refAbstract=null), Reference(id=1241769358494597493, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2019, volume=36, issue=3, pageStart=43, pageEnd=49, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=谢博, 施富强, 赵建才, journalName=爆破, refType=null, unstructuredReference=谢博, 施富强, 赵建才, . 爆破岩块自动识别与块度特征提取方法[J]. 爆破, 2019, 36(3): 43-49., articleTitle=爆破岩块自动识别与块度特征提取方法, refAbstract=null), Reference(id=1241769358570094967, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2019, volume=36, issue=3, pageStart=43, pageEnd=49, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=XIE Bo, SHI Fu-qiang, ZHAO Jian-cai, journalName=Blasting, refType=null, unstructuredReference=XIE Bo, SHI Fu-qiang, ZHAO Jian-cai, et al. Method for automatic identification and block size feature extraction of blasting rock blocks[J]. Blasting, 2019, 36(3): 43-49. (in Chinese), articleTitle=Method for automatic identification and block size feature extraction of blasting rock blocks, refAbstract=null), Reference(id=1241769358683341178, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=234, pageEnd=241, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=OLAF Ronneberger, PHILIPP Fischer, THOMAS Brox, journalName=null, refType=null, unstructuredReference=OLAF Ronneberger, PHILIPP Fischer, THOMAS Brox. U-Net: Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention, 2015, 9351: 234-241., articleTitle=U-Net: Convolutional networks for biomedical image segmentation, refAbstract=null), Reference(id=1241769358775615869, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=10.3390/s20174979, pmid=null, pmcid=null, year=2020, volume=20, issue=17, pageStart=49, pageEnd=79, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=XIAO Dong, LIU Xi-wen, LE Ba-tuan, journalName=Sensors, refType=null, unstructuredReference=XIAO Dong, LIU Xi-wen, LE Ba-tuan, et al. An ore image segmentation method based on RDU-Net model[J]. Sensors, 2020, 20(17): 49-79., articleTitle=An ore image segmentation method based on RDU-Net model, refAbstract=null), Reference(id=1241769358884667774, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=10, pageStart=11469, pageEnd=11475, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=YANG Hao, HUANG Chao, WANG Long, journalName=IEEE sensors journal, refType=null, unstructuredReference=YANG Hao, HUANG Chao, WANG Long, et al. An improved encoder-decoder network for ore image segmentation[J]. IEEE sensors journal, 2021, 21(10): 11469-11475., articleTitle=An improved encoder-decoder network for ore image segmentation, refAbstract=null), Reference(id=1241769358997913985, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2021, volume=32, issue=10, pageStart=3885, pageEnd=3903, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=LIU Yang, ZHANG Ze-lin, LIU Xiang, journalName=Advanced Powder Technology, refType=null, unstructuredReference=LIU Yang, ZHANG Ze-lin, LIU Xiang, et al. Efficient image segmentation based on deep learning for mineral image classification[J]. Advanced Powder Technology, 2021, 32(10): 3885-3903., articleTitle=Efficient image segmentation based on deep learning for mineral image classification, refAbstract=null), Reference(id=1241769359115354501, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2021, volume=170, issue=null, pageStart=100, pageEnd=107, url=null, language=null, rfNumber=[9], rfOrder=9, authorNames=FILIPPO Michel Pedro, DA Fonseca Martins Gomes Otvio, DA Costa Gilson Alexandre Ostwald Pedro, journalName=Minerals Engineering, refType=null, unstructuredReference=FILIPPO Michel Pedro, DA Fonseca Martins Gomes Otvio, DA Costa Gilson Alexandre Ostwald Pedro, et al. Deep learning semantic segmentation of opaque and nonopaque minerals from epoxy resin in reflected light microscopy images[J]. Minerals Engineering, 2021, 170: 100-107., articleTitle=Deep learning semantic segmentation of opaque and nonopaque minerals from epoxy resin in reflected light microscopy images, refAbstract=null), Reference(id=1241769359216017799, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=null, pageStart=59048, pageEnd=59058, url=null, language=null, rfNumber=[10], rfOrder=10, authorNames=YANG Z, DING H, GUO L, journalName=IEEE Access, refType=null, unstructuredReference=YANG Z, DING H, GUO L, et al. Superpixel image segmentation-based particle size distribution analysis of fragmented rock[J]. IEEE Access, 2021, 9: 59048-59058., articleTitle=Superpixel image segmentation-based particle size distribution analysis of fragmented rock, refAbstract=null), Reference(id=1241769360700801417, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=10.1016/J.MINENG.2021.107-230, pmid=null, pmcid=null, year=2021, volume=173, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=11, authorNames=KOH Edwin J Y, AMINI Eiman, McLACHLAN Geoffrey J, journalName=Minerals Engineering, refType=null, unstructuredReference=KOH Edwin J Y, AMINI Eiman, McLACHLAN Geoffrey J, et al. Utilising convolutional neural networks to perform fast automated modal mineralogy analysis for thinsection optical microscopy[J]. Minerals Engineering, 2021, 173: 107230., articleTitle=Utilising convolutional neural networks to perform fast automated modal mineralogy analysis for thinsection optical microscopy, refAbstract=null), Reference(id=1241769360822436234, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=10.1016/J.AUTCON.2021.103-685, pmid=null, pmcid=null, year=2021, volume=126, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=12, authorNames=ZHOU Xiao-xiong, GONG Qiu-ming, LIU Yong-qiang, journalName=Automation in Construction, refType=null, unstructuredReference=ZHOU Xiao-xiong, GONG Qiu-ming, LIU Yong-qiang, et al. Automatic segmentation of tbm muck images via a deep-learning approach to estimate the size and shape of rock chips[J], Automation in Construction, 2021, 126: 103685., articleTitle=Automatic segmentation of tbm muck images via a deep-learning approach to estimate the size and shape of rock chips, refAbstract=null), Reference(id=1241769360960848266, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2021, volume=104, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=13, authorNames=WANG Ying-da, SHABANINEJAD Mehdi, ARMSTRONG Ryan T, journalName=Applied Soft Computing, refType=null, unstructuredReference=WANG Ying-da, SHABANINEJAD Mehdi, ARMSTRONG Ryan T, et al. Deep neural networks for improving physical accuracy of 2d and 3d multi-mineral segmentation of rock micro-ct images[J]. Applied Soft Computing, 2021, 104: 107185., articleTitle=Deep neural networks for improving physical accuracy of 2d and 3d multi-mineral segmentation of rock micro-ct images, refAbstract=null), Reference(id=1241769361065705867, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=10.1088/1742-6596/1611/1/012062, pmid=null, pmcid=null, year=2020, volume=10, issue=16, pageStart=9396, pageEnd=9406, url=null, language=null, rfNumber=[14], rfOrder=14, authorNames=LIU Xiao-bo, ZHANG Yu-wei, JING Hong-di, journalName=RSCAdvances, refType=null, unstructuredReference=LIU Xiao-bo, ZHANG Yu-wei, JING Hong-di, et al. Ore image segmentation method using U-Net and Res_Unet convolutional networks[J]. RSCAdvances, 2020, 10(16): 9396-9406., articleTitle=Ore image segmentation method using U-Net and Res_Unet convolutional networks, refAbstract=null), Reference(id=1241769361166369163, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2017, volume=16, issue=10, pageStart=129, pageEnd=131, url=null, language=null, rfNumber=[15], rfOrder=15, authorNames=张永付, 张鹏, journalName=软件导刊, refType=null, unstructuredReference=张永付, 张鹏. 基于Python的硬币识别系统设计与实现[J]. 软件导刊, 2017, 16(10): 129-131., articleTitle=基于Python的硬币识别系统设计与实现, refAbstract=null), Reference(id=1241769361237672333, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, doi=null, pmid=null, pmcid=null, year=2017, volume=16, issue=10, pageStart=129, pageEnd=131, url=null, language=null, rfNumber=[15], rfOrder=16, authorNames=ZHANG Yongfu, ZHANG Peng, journalName=Software Guide, refType=null, unstructuredReference=ZHANG Yongfu, ZHANG Peng. Design and Implementation of a Coin Recognition System Based on Python[J]. Software Guide, 2017, 16(10): 129-131. (in Chinese), articleTitle=Design and Implementation of a Coin Recognition System Based on Python, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1241769352442216642, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, xref=null, ext=[AuthorCompanyExt(id=1241769352467382469, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, companyId=1241769352442216642, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=China Railway 19 Bureau Group Mining Investment Co, LTD, Manzhouli 021400, China), AuthorCompanyExt(id=1241769352479965382, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, companyId=1241769352442216642, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中铁十九局集团 矿业投资有限公司 新巴尔虎右旗分公司,满洲里 021400)])], figs=[ArticleFig(id=1241769354589700389, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, label=Fig. 1, caption=Wunugetushan copper molybdenum mine, figureFileSmall=N+/qIfCz1R1j/nRL1iqpcg==, figureFileBig=vAHdkSlCqVSvcqbjXcTYAQ==, tableContent=null), ArticleFig(id=1241769354681975082, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, label=图1, caption=乌努格吐山铜钼矿, figureFileSmall=N+/qIfCz1R1j/nRL1iqpcg==, figureFileBig=vAHdkSlCqVSvcqbjXcTYAQ==, tableContent=null), ArticleFig(id=1241769356300976432, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, label=Fig. 2, caption=Boulder after blast, figureFileSmall=b9Mt4QyZSv6305ocnMYYVg==, figureFileBig=huDNi27JHQx7ejGPag9meA==, tableContent=null), ArticleFig(id=1241769356414222642, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, label=图2, caption=现场爆堆大块图, figureFileSmall=b9Mt4QyZSv6305ocnMYYVg==, figureFileBig=huDNi27JHQx7ejGPag9meA==, tableContent=null), ArticleFig(id=1241769356548440374, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, label=Fig. 3, caption=Training flow chart, figureFileSmall=YYAYWjnGU6PsZ9Dk9KKS9A==, figureFileBig=SaBCeabxYJXGId6Z7buWXw==, tableContent=null), ArticleFig(id=1241769356661686585, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, label=图3, caption=训练流程图, figureFileSmall=YYAYWjnGU6PsZ9Dk9KKS9A==, figureFileBig=SaBCeabxYJXGId6Z7buWXw==, tableContent=null), ArticleFig(id=1241769356774932797, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, label=Fig. 4, caption=Structure of U-Net network, figureFileSmall=Zzd377TVHwrmQUbZUn4V/A==, figureFileBig=C7i5f2khd4BKV8Sxeq4kWA==, tableContent=null), ArticleFig(id=1241769356858818879, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, label=图4, caption=U-net网络结构图, figureFileSmall=Zzd377TVHwrmQUbZUn4V/A==, figureFileBig=C7i5f2khd4BKV8Sxeq4kWA==, tableContent=null), ArticleFig(id=1241769356925927746, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, label=Fig. 5, caption=Monocular imaging principle, figureFileSmall=umESbgZQUKw/nGJNM1+Osg==, figureFileBig=SZHJc58JkhIpXsSBipO1hg==, tableContent=null), ArticleFig(id=1241769357005619527, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, label=图5, caption=单目成像原理, figureFileSmall=umESbgZQUKw/nGJNM1+Osg==, figureFileBig=SZHJc58JkhIpXsSBipO1hg==, tableContent=null), ArticleFig(id=1241769357127254347, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, label=Fig. 6, caption=Explosion pile picture, figureFileSmall=zRIWXrWWMhdKcbuff8jPSA==, figureFileBig=pX3/MalFClvpT7MqUk/uTw==, tableContent=null), ArticleFig(id=1241769357240500559, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, label=图6, caption=爆堆图片, figureFileSmall=zRIWXrWWMhdKcbuff8jPSA==, figureFileBig=pX3/MalFClvpT7MqUk/uTw==, tableContent=null), ArticleFig(id=1241769357349552469, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, label=Fig. 7, caption=Optimization process, figureFileSmall=7l+1C8N7j0h8ZmWW6llSjA==, figureFileBig=fA8JKVEjH3UhYUtJWRyf+A==, tableContent=null), ArticleFig(id=1241769357441827160, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, label=图7, caption=优化过程, figureFileSmall=7l+1C8N7j0h8ZmWW6llSjA==, figureFileBig=fA8JKVEjH3UhYUtJWRyf+A==, tableContent=null), ArticleFig(id=1241769357555073367, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, label=Fig. 8, caption=Segmentation effect, figureFileSmall=ggkZGgrpNS0nQWUuo8QoPQ==, figureFileBig=6/pLKXMtAQywDU3HwtIrVw==, tableContent=null), ArticleFig(id=1241769357617987929, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, label=图8, caption=分割效果, figureFileSmall=ggkZGgrpNS0nQWUuo8QoPQ==, figureFileBig=6/pLKXMtAQywDU3HwtIrVw==, tableContent=null), ArticleFig(id=1241769357689291100, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, label=Fig. 9, caption=Fragment size identification, figureFileSmall=WpJ8EOAYBuEtdro23aDASA==, figureFileBig=eNcL40WGaYRf47JmvwiQsg==, tableContent=null), ArticleFig(id=1241769357785760097, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, label=图9, caption=块度识别, figureFileSmall=WpJ8EOAYBuEtdro23aDASA==, figureFileBig=eNcL40WGaYRf47JmvwiQsg==, tableContent=null), ArticleFig(id=1241769357861257572, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, label=Fig. 10, caption=Operation interface, figureFileSmall=bBP/Fdk8hH65H/E84EZ4kQ==, figureFileBig=UrUjDrNX1C1BHJN22CjG0A==, tableContent=null), ArticleFig(id=1241769357940949352, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, label=图10, caption=操作界面, figureFileSmall=bBP/Fdk8hH65H/E84EZ4kQ==, figureFileBig=UrUjDrNX1C1BHJN22CjG0A==, tableContent=null), ArticleFig(id=1241769358020641130, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=EN, label=Table 1, caption=

Comparison of the effects of deep learning and manual calculations

, figureFileSmall=null, figureFileBig=null, tableContent=
原始图像预测图像块度识别预测/人工(大块个数)
12/12
11/10
10/10
14/13
10/12
5/5
7/6
8/6
7/6
8/9
), ArticleFig(id=1241769358108721517, tenantId=1146029695717560320, journalId=1240670690148397066, articleId=1241769334666756503, language=CN, label=表1, caption=

深度学习法与人工计算法效果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
原始图像预测图像块度识别预测/人工(大块个数)
12/12
11/10
10/10
14/13
10/12
5/5
7/6
8/6
7/6
8/9
)], attaches=null, journal=Journal(id=1240670582996512777, delFlag=0, nameCn=爆破, nameEn=Blasting, nameHistory1=null, nameHistory2=null, issn=1001-487X, eissn=null, cn=42-1164/TJ, coden=null, periodic=2, 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=WY0TpbOLkpEy0LB1gxLRkA==, journalPrice=null, startedYear=null, abbrevIsoEn=Blasting, journalRemark=null, publicationField=null, createdTime=1773728517534, updatedTime=1773729027907, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=B, firstLetterEn=B, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=WY0TpbOLkpEy0LB1gxLRkA==, picEn=WihllgjTVpaoKPVK01wkxA==, jcr=null, cjcr=null, exts=[JournalExt(id=1240672723748311401, language=CN, name=爆破, 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=1773729027926, updatedTime=1773729027926, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://bopo.cbpt.cnki.net/EditorDN/index.aspx?t=1, submissionEditorUrl=https://bopo.cbpt.cnki.net/EditorDN/index.aspx?t=3, submissionReviewUrl=https://bopo.cbpt.cnki.net/EditorDN/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1240672723802837354, language=EN, name=Blasting, 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=1773729027939, updatedTime=1773729027939, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://bopo.cbpt.cnki.net/EditorDN/index.aspx?t=1, submissionEditorUrl=https://bopo.cbpt.cnki.net/EditorDN/index.aspx?t=3, submissionReviewUrl=https://bopo.cbpt.cnki.net/EditorDN/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1240670690148397066, websiteList=[Website(id=1240673414420156779, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1240670690148397066, 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/bp/CN, language=CN, createTime=1773729192595, createBy=18614031015, updateTime=1773729402692, updateBy=18614031015, name=爆破-中文, tplId=1146099689490845704, title=爆破, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1240674340283404702, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414420156779, code=articleTextType, value=kx, createTime=1773729413338, updateTime=1773729413338, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674340258238875, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414420156779, code=banner, value=null, createTime=1773729413332, updateTime=1773729413332, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674340304376225, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414420156779, code=grayFlag, value=0, createTime=1773729413343, updateTime=1773729413343, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674340249850266, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414420156779, code=logo, value=https://castjournals.cast.org.cn/joweb/bp/CN/file/pic?fileId=6aWE5pjR/O5nMmPAr6vERA==, createTime=1773729413330, updateTime=1773729413330, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674340316959139, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414420156779, code=minRunFlag, value=0, createTime=1773729413346, updateTime=1773729413346, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674340275016093, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414420156779, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/bp/CN/file/pic, createTime=1773729413336, updateTime=1773729413336, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674340312764834, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414420156779, code=silenceFlag, value=0, createTime=1773729413345, updateTime=1773729413345, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674340266627484, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414420156779, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1773729413334, updateTime=1773729413334, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674340287599007, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414420156779, code=themeColor, value=null, createTime=1773729413340, updateTime=1773729413340, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674340295987616, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414420156779, code=themeStyle, value=null, createTime=1773729413341, updateTime=1773729413341, creator=18614031015, updator=18614031015)]), Website(id=1240673414491459949, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1240670690148397066, 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/bp/EN, language=EN, createTime=1773729192612, createBy=18614031015, updateTime=1773729407178, updateBy=18614031015, name=爆破-英文, tplId=1146101810881728533, title=Blasting, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1240674360592224680, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414491459949, code=articleTextType, value=kx, createTime=1773729418180, updateTime=1773729418180, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674360571253157, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414491459949, code=banner, value=null, createTime=1773729418175, updateTime=1773729418175, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674360609001899, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414491459949, code=grayFlag, value=0, createTime=1773729418184, updateTime=1773729418184, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674360562864548, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414491459949, code=logo, value=https://castjournals.cast.org.cn/joweb/bp/EN/file/pic?fileId=6aWE5pjR/O5nMmPAr6vERA==, createTime=1773729418173, updateTime=1773729418173, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674360621584813, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414491459949, code=minRunFlag, value=0, createTime=1773729418187, updateTime=1773729418187, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674360583836071, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414491459949, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/bp/EN/file/pic, createTime=1773729418178, updateTime=1773729418178, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674360617390508, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414491459949, code=silenceFlag, value=0, createTime=1773729418186, updateTime=1773729418186, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674360579641766, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414491459949, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1773729418177, updateTime=1773729418177, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674360596418985, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414491459949, code=themeColor, value=null, createTime=1773729418182, updateTime=1773729418182, creator=18614031015, updator=18614031015), WebsiteProps(id=1240674360604807594, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240673414491459949, code=themeStyle, value=null, createTime=1773729418183, updateTime=1773729418183, creator=18614031015, updator=18614031015)])], journalTitle=爆破, weixinUrl=null, journalUrl=https://bopo.cbpt.cnki.net/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Blasting, journalPhotoCn=WY0TpbOLkpEy0LB1gxLRkA==, journalPhotoEn=WihllgjTVpaoKPVK01wkxA==, journalFirstLetter=B, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/bp/CN/10.3963/j.issn.1001-487X.2024.01.026, detailUrlEn=https://castjournals.cast.org.cn/joweb/bp/EN/10.3963/j.issn.1001-487X.2024.01.026, pdfUrlCn=https://castjournals.cast.org.cn/joweb/bp/CN/PDF/10.3963/j.issn.1001-487X.2024.01.026, pdfUrlEn=https://castjournals.cast.org.cn/joweb/bp/EN/PDF/10.3963/j.issn.1001-487X.2024.01.026, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于深度学习技术的爆堆块度识别方法研究
收藏切换
PDF下载
陈立军 , 蔡国强 , 张文斌
爆破 | 安全与管理 2024,41(1): 196-201
收起
收藏切换
爆破 | 安全与管理 2024, 41(1): 196-201
基于深度学习技术的爆堆块度识别方法研究
全屏
陈立军 , 蔡国强, 张文斌
作者信息
  • 中铁十九局集团 矿业投资有限公司 新巴尔虎右旗分公司,满洲里 021400
  • 陈立军(1976-),男,项目经理、学士,主要从事矿山生产管理,(E-mail)

    CHEN Li-jun (1976-), male, project manager, bachelor′s degree, mainly engaged in mining production management, (E-mail) .

Research on Fragment Size Identification Method of Blasting Pile based on Deep Learning Technology
Li-jun CHEN , Guo-qiang CAI, Wen-bin ZHANG
Affiliations
  • China Railway 19 Bureau Group Mining Investment Co, LTD, Manzhouli 021400, China
出版时间: 2024-03-01 doi: 10.3963/j.issn.1001-487X.2024.01.026
文章导航
收藏切换

在露天矿爆破开采过程中,大块率是评价爆破质量的一个重要指标。较高的大块率不仅会大大降低采装效率,同时也增加二次破岩的费用,因此大块率统计是露天矿开采中一项重要工作。针对目前矿山存在的矿岩大块率统计复杂且准确性不高的问题,以乌努格吐山铜钼矿为研究对象,收集了矿区内台阶爆破爆堆图像数据,构建了基于深度学习的爆堆大块率统计模型。首先基于U-net矿岩图像分割模型,初步分割标注处理的数据集,建立了矿岩轮廓初次分割效果图。在残差学习模块基础上,改进Resu-net模型,优化训练标注数据,获得了最终矿岩轮廓分割效果图。最后,采用OpenCV图像处理技术,通过最小外接矩形法确定了爆堆块度尺度信息。结果表明,本研究提出的U-net+Resu-net爆堆块度优化分割模型准确率达到97.84%,爆堆矿岩图像分割数据较准确。通过OpenCV技术与相机单目成像原理相结合的方法,实现了倾斜爆堆矿岩图像的爆堆块度统计。此外,所开发的交互式界面操作简单,可快速统计大块尺寸。满洲里乌努格吐山铜钼矿的应用表明,该方法可高效、准确统计爆堆块度,具有一定的推广价值。

爆堆块度  /  深度学习  /  单目成像  /  矿石分割

Boulder yield is an important index to evaluate the blasting quality in the blasting process of an open pit mine. Since a high boulder yield will not only greatly reduce the mining efficiency, but also increase the cost of secondary rock breaking, so fragments size statistics is an important work in open pit mining. Aiming at the problem that the statistics of fragment size is complex and not accurate enough, a statistical model of boulder yield was built by deep learning based on the takes the image data of blasting piles collected in the Unugetushan copper and molybdenum mine. Firstly, the annotated data set was initially segmented into an initial effect diagram of the mine rock contour based on the U-net image segmentation model. And then, the annotated data for training was optimized and the Resu-net model was improved on the basis of the residual learning module, which resulted in the final segmentation effect map of mine rock contour. Finally, the fragment size information of the blasting pile was obtained through the minimum external rectangle method combined with OpenCV image processing technology. The results show that the segmentation accuracy of U-net+Resu-net fragment size optimization model proposed in this study is 97.84% with an accurate image data segmentation. The statistics of fragment size in an inclined blasting pile is realized by OpenCV technology combined with the camera monocular imaging principle. In addition, the developed interactive interface is simple to operate and can quickly calculate the boulder yield.

blasting fragment size  /  deep learning  /  monocular imaging  /  ore segmentation
陈立军, 蔡国强, 张文斌. 基于深度学习技术的爆堆块度识别方法研究. 爆破, 2024 , 41 (1) : 196 -201 . DOI: 10.3963/j.issn.1001-487X.2024.01.026
Li-jun CHEN, Guo-qiang CAI, Wen-bin ZHANG. Research on Fragment Size Identification Method of Blasting Pile based on Deep Learning Technology[J]. Blasting, 2024 , 41 (1) : 196 -201 . DOI: 10.3963/j.issn.1001-487X.2024.01.026
矿岩爆破块度是衡量露天矿台阶爆破效果最重要的指标之一,矿岩爆后的大块情况直接影响后续生产中的装载、运输及二次破碎作业等过程。大块矿岩的存在一直是制约矿山安全、效率、成本控制的重要影响因素。因此如何高效、低成本的获得矿岩块度信息对于矿山生产效率起着决定性作用。传统的矿石尺寸测量方式是通过手工测量实现的,此法不仅需要大量的人力和时间,而且精度和效率往往很低,也隐伏巨大的安全风险。随着计算机技术的发展,基于图像处理的智能图像分割方法被提出,其中在矿石图像的分割方法研究中,许多专家取得了巨大突破,其中以分水岭法及其改进方法[1,2],阈值分割方法[3],基于特定理论的分割方法等作为传统的计算机图像处理方法存在参数过多和调参困难的问题,同时针对每张图片的分割都需要进行大量的参数调节以获得最终分割图像,效率较低。近年来随着深度学习技术的发展,因其具有从大量训练数据中学习具体特征的强大学习能力,推动了该技术在许多领域的应用研究。谢博等人获得爆堆三维点云数据,利用区域生长法进行岩块点云分割,取得了较好的分割效果[4]。Ronneberger O等人首次提出了一种(Encoder-Decoder)形式的新型网络结构(即U-Net),并利用该网络模型进行了细胞图像分割,实现在较少细胞数据情况下高精度目标分割。由于器官分割(尤其是细胞分割)与岩土工程中矿石图像分割近似,因此推动了矿岩图像分割与识别领域的研究[5]。基于此,Xiao D等人提出的RDU-Net模型,对比U-Net和DUNet模型,获得了更好的矿石图像分割效果[6]。Yang H等人提出了一种改进的采用VGG-16作为编码器的U-Net网络对矿岩图像进行研究[7]。Liu Y等人针对矿物颗粒之间的粘附和重叠问题,对比分析了五种改进的深度学习分割模型效果。而针对显微图像中的矿物边界分割也开始了拓展研究[8]。Filippo M P等人使用DeepLabv3+模型对反射光显微镜图像中从环氧树脂中不透明和非透明矿物边界分割进行了研究[9]。Yang Z等人采用超像素图像分割技术,对爆堆粒径统计展开了研究[10]。Koh E J Y等人研究了Mask R-CNN和SOLO v2的辨识晶粒边界并对矿物进行分类的识别能力[11]。由于在室外环境采集获得矿石图像数据,不但存在着矿石表面信息复杂,尺寸形状多变和堆积密集等问题,还存在背景环境复杂,噪声影响严重,而以上的方法对于这些情况的解决效果和分割准确率都不高,而且存在参数设计复杂等问题。这些现象为利用机器视觉手段分离矿石颗粒带来了很大的困难。
由于满洲里乌努格吐山铜钼矿西部采区矿岩特殊的物理性质,爆破后极易形成大块,现场统计大块率的工作量十分繁重,为此基于深度卷积神经模型与单目成像原理,提出使用U-net+Resu-net模型分割爆堆矿岩轮廓,结合图像处理手段对爆堆斜面块体图像进行块度统计,获得爆堆大块岩石信息,进而为现场统计爆堆大块率研究提供技术支持。通过乌努格吐山铜钼矿的实际应用,验证了该方法的可行性与便捷性。
乌努格吐山铜钼矿位于内蒙古自治区满洲里市西南22 km,矿区面积约9.8 km2,行政区划属新巴尔虎右旗(参见图1)。设计采矿采用单台阶缓帮开采,岩石剥离采用组合台阶陡帮开采;为降低矿石的损失、贫化指标,根据矿体的赋存条件,设计开段沟采用纵向布置在矿体上盘,垂直矿体走向由矿体上盘向下盘推进。
矿区内节理发育明显,西部边帮台阶爆破大块率问题严重,影响铲运机装矿运输,需要二次破碎,并且现场每天进行多次爆破作业,人工块度统计耗时费力,直接影响生产效率。因此有必要对爆堆大块率信息进行快速统计。现场爆堆大块情况如下图2
深度学习技术是由多伦多大学的Hinton等人于2006年提出的,其特点为多层神经网络。在深度学习中,卷积神经网络算法(Convolutional Neural Networks,CNN)作为一种高效的识别算法,常被应用在图像识别领域,尤其是在计算机视觉、自然语言处理和语音识别技术等领域得到广泛应用,是当前大数据处理、人工智能研发以及在应用统计学的研究中的热点[12,13]。随着计算机图像处理技术的发展,应用深度卷积神经网络实现图像识别的研究技术发展迅速。深度学习在图像识别领域的突出表现,尤其是在医学图像细胞分割问题研究中,证明了其技术可以做到对粘连物体进行轮廓分割,因此采用深度学习技术可以解决矿石图像分割问题。并且,近年来,已有相关学者使用U-net,RestNet及其改进的语义分割算法对矿石图像进行研究,取得了相应的研究成果[14]
本文使用的深度学习识别方法分为三个步骤。第一步,采集图像信息制作训练集,对图像进行处理,将图像通过U-Net模型进行训练,输出预测图像。第二步,将上一阶段预测获得的轮廓图像通过Resunet模型进行训练获得最终的爆堆矿岩图像特证集合。第三步,通过爆堆矿岩图像特征集预测爆堆矿岩轮廓,并利用python-OpenCV模块统计矿石尺寸分布[15],实现矿石图像分割,具体流程参见图3
U-Net网络模型是一种语义分割网络模型[5],是基于全卷积网络拓展和修改而来区别于一般的卷积神经网络,网络由两部分组成:一个收缩路径(contracting path)来获取上下文信息(即下采样)以及一个对称的扩张路径(expanding path)用以精确定位(即上采样)。见图4
Resunet是基于U型网络结构结合残差模块(Residual)的语义分割模型,网络构造与U-Net网络结构相似,Resunet网络将Residual模块(残差模块)加入到U-Net网络中,这种网络通过使用一种预激活的模块进行归一化处理和relu函数优化后再进行卷积操作,其中卷积层通过convolutional_block和identity_block残差函数模块替代正常卷积进行下采样操作,通过Concatenate函数在上采样过程中,相同尺寸特征图进行拼接,达到最终重建输出效果,可以有效的克服由于网络层数加深造成特征信息丢失问题以及梯度弥散问题,增强信息传输能力。
有学者对于矿岩图片的研究都是基于通过垂直物体表面拍摄得图的方法来获得研究数据识别尺寸。由于现场台阶爆破崩落矿岩会生成与水平面构成一定角度的爆堆并且台阶高度高达15 m,因此想要获得一整个爆堆都存在在一张图片上,并且是垂直爆堆面的图片,只有通过无人机获得。但是有些矿山企业没有无人机设备,并且没有专人进行飞行,因此为了更加方便的获得爆堆图片信息,本文提出基于手机拍照获得斜面爆堆图片,再通过单目相机成像原理,划分比例区间并结合标记物尺寸,进而获得爆堆矿岩的真实尺寸。如图5为单目成像原理图。
通过单目成像原理,进行斜面成像计算,将现场获得的爆堆图像,人为横向划分几个区域(如图6),分别计算各个分割区域的成像比例系数AA1A2A3A4A5等),通过python编程语言结合OpenCV技术计算实际矿岩尺寸。
将现场获得爆堆图像进行尺寸归一,获得标准256×256尺寸图片作为U-Net语义分割模型的训练输入图片数据,利用U-Net模型基本可以识别出矿石的轮廓情况,但仍存在部分区域过分割等问题。解决图像过分割问题的算法有很多,但是传统的基于阈值等处理的方法往往存在参数调整复杂并且解决效果一般的问题。为进一步获得更精确的分割效果,本文将训练集的预测结果图作为Resunet语义分割模型的训练集进行训练,实现轮廓优化作用。具体流程如下图7所示。
因在采集图片时存在其他台阶(主要上一阶段边坡)和天空等不相关信息,并且为了更好的在深度网络中训练,最好选择标准图像尺寸进行训练。因此,需要对矿岩图片进行修剪等处理,本文使用处理后的1000张矿岩图像为训练集,其中样本大小均为256×256,由于现场存在灰尘和不同光照等影响因素,因此需先对图像进行图像去噪,直方图均值化和灰度处理等图像预处理操作,获得更清晰,轮廓更明显的图像信息。
通过labelme对训练集数据进行人工标定。对两个网络均采用0.0001的学习率,每次迭代的图片数量选择2,对整个样本进行10次循环训练,损失函数选择binary_crossentropy函数配合sigmoid激活函数使用并使用Adam梯度下降法进行网络训练,并通过accuracy_score函数对分类问题准确率进行判定。最终获得分类准确率达到97.84%,基本满足对于矿石尺寸的识别需求。见图8
利用python-OpenCV模块中的算法获取识别轮廓图片中的参数:首先,利用findContours算法,搜索矿岩预测轮廓图片中的所有轮廓;再利用drawContour算法将轮廓画在原图上,利用boundingRect算法得到每一个轮廓的最小外接矩形,生成红色边框;利用rectLength算法得到每个岩块的最小外接矩形的尺寸,利用contourArea算法求得面积A。如图9所示。
使用Qt Designer进行操作界面设计。Qt Designer是一种直观可见的全方位GUI构造器,它所设计出来的用户界面能够在多种平台上使用,并且使用designer来设计界面,可以大大减少程序代码量,设计起来也更加方便清晰。
通过PyInstaller将训练数据和编程代码文件打包生成exe文件,结合操作界面打包封装生成安装包,可以下载到电脑进行操作,解决了不需要懂编程技术也可使用的问题。结果如图10
为了验证该方法的处理速度和有效性,选取未训练的样本数据作为测试集对模型语义分割进行对比测试,采用人为计算的大块数作为正确值进行对比,具体对比见表1
表1可知,采用深度学习的方法对大块矿石的识别与人工测量的效果相近,且一组10张图片的预测时间在14秒左右,模型预测耗时大大低于人工计算时间,因此该模型可以使用与矿山爆堆大块的识别,进而为后续的大块率计算提供了可能。
为了应对台阶爆破现场出现的大量大块问题,依据深度学习图像分割手段研究了爆堆块体的分割和块度统计。
(1)针对U-net模型分割效果无法满足实际应用的情况,搭建了U-net+Resu-net形式的爆堆矿岩图像优化分割模型,优化后的爆堆矿岩图像分割准确率达到97.84%,优化分割效果满足了实际应用。
(2)提出结合单目成像原理的斜面爆堆图像尺寸计算方法,为现场数据采集只能竖直角度获得,提供了可以现场手机拍摄斜面爆堆获得数据的新方法。
(3)在矿山原本块度统计使用人工或经验估计的背景下,提出了更加智能和高效的块度统计方法。对现场大块统计研究提供了新方法,对矿岩爆破块度尤其是大块的研究有指导作用。
参考文献 引证文献
排序方式:
[1]
ZHANG Guo-ying, LIU Guan-zhou, ZHU Hong, et al. Segmentation algorithm of complex ore images based on templates transformation and reconstruction[J]. International Journal of Minerals Metallurgy and Materials, 2011, 18(4): 385-389.
[2]
KE Dong, JIANG Da-lin. Automated estimation of ore size distributions based on machine vision[J]. Lecture Notes in Electrical Engineering, 2014, 238 LNEE(null): 1125-1131.
[3]
CHEN Yi, WANG Ming-jing, AA Heidari, et al. Multithreshold image segmentation using a multi-strategy shuffled frog leaping algorithm[J]. Expert Systems with Application, 2022(May): 194.
[4]
谢博, 施富强, 赵建才, . 爆破岩块自动识别与块度特征提取方法[J]. 爆破, 2019, 36(3): 43-49.
XIE Bo, SHI Fu-qiang, ZHAO Jian-cai, et al. Method for automatic identification and block size feature extraction of blasting rock blocks[J]. Blasting, 2019, 36(3): 43-49. (in Chinese)
[5]
OLAF Ronneberger, PHILIPP Fischer, THOMAS Brox. U-Net: Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention, 2015, 9351: 234-241.
[6]
XIAO Dong, LIU Xi-wen, LE Ba-tuan, et al. An ore image segmentation method based on RDU-Net model[J]. Sensors, 2020, 20(17): 49-79.
[7]
YANG Hao, HUANG Chao, WANG Long, et al. An improved encoder-decoder network for ore image segmentation[J]. IEEE sensors journal, 2021, 21(10): 11469-11475.
[8]
LIU Yang, ZHANG Ze-lin, LIU Xiang, et al. Efficient image segmentation based on deep learning for mineral image classification[J]. Advanced Powder Technology, 2021, 32(10): 3885-3903.
[9]
FILIPPO Michel Pedro, DA Fonseca Martins Gomes Otvio, DA Costa Gilson Alexandre Ostwald Pedro, et al. Deep learning semantic segmentation of opaque and nonopaque minerals from epoxy resin in reflected light microscopy images[J]. Minerals Engineering, 2021, 170: 100-107.
[10]
YANG Z, DING H, GUO L, et al. Superpixel image segmentation-based particle size distribution analysis of fragmented rock[J]. IEEE Access, 2021, 9: 59048-59058.
[11]
KOH Edwin J Y, AMINI Eiman, McLACHLAN Geoffrey J, et al. Utilising convolutional neural networks to perform fast automated modal mineralogy analysis for thinsection optical microscopy[J]. Minerals Engineering, 2021, 173: 107230.
[12]
ZHOU Xiao-xiong, GONG Qiu-ming, LIU Yong-qiang, et al. Automatic segmentation of tbm muck images via a deep-learning approach to estimate the size and shape of rock chips[J], Automation in Construction, 2021, 126: 103685.
[13]
WANG Ying-da, SHABANINEJAD Mehdi, ARMSTRONG Ryan T, et al. Deep neural networks for improving physical accuracy of 2d and 3d multi-mineral segmentation of rock micro-ct images[J]. Applied Soft Computing, 2021, 104: 107185.
[14]
LIU Xiao-bo, ZHANG Yu-wei, JING Hong-di, et al. Ore image segmentation method using U-Net and Res_Unet convolutional networks[J]. RSCAdvances, 2020, 10(16): 9396-9406.
[15]
张永付, 张鹏. 基于Python的硬币识别系统设计与实现[J]. 软件导刊, 2017, 16(10): 129-131.
ZHANG Yongfu, ZHANG Peng. Design and Implementation of a Coin Recognition System Based on Python[J]. Software Guide, 2017, 16(10): 129-131. (in Chinese)
2024年第41卷第1期
PDF下载
114
55
引用本文
BibTeX
文章信息
doi: 10.3963/j.issn.1001-487X.2024.01.026
  • 接收时间:2021-10-12
  • 首发时间:2026-03-20
  • 出版时间:2024-03-01
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2021-10-12
基金
作者信息
    中铁十九局集团 矿业投资有限公司 新巴尔虎右旗分公司,满洲里 021400
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/bp/CN/10.3963/j.issn.1001-487X.2024.01.026
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

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

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