基于MRAU视频分割模型的矿井涌(突)水风险识别方法
TD742; 矿井涌(突)水视频识别是智能化矿井建设的关键之一,通过识别涌(突)水从无到有、从小到大的动态演变过程,有助于防止水量超出矿井排水能力并演变为水害.为此提出了一种基于多通道残差注意力机制的U2Net视频分割模型(MRAU),旨在识别涌(突)水的演变过程.首先,基于卷积注意力模块(CBAM)改进U2Net网络模型,以提高特征提取效果.通过多通道残差预处理,区分水流动态特征与静态背景,并将处理结果作为注意力机制输入模型,从而强化水流特征的学习.此外,使用中间帧掩码作为标签进行多帧融合学习,进一步提升网络对水流动态特征的识别能力.最终,通过学习不同场景下的水流特征,实现对未知场景中涌(突...
Saved in:
| Published in | 煤炭科学技术 Vol. 52; no. 11; pp. 17 - 28 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
中国矿业大学(北京)国家煤矿水害防治工程技术研究中心,北京 100083
01.11.2024
矿业大学(北京)内蒙古研究院,内蒙古 鄂尔多斯 017000 矿山水防治与资源化利用国家矿山安全监察局重点实验室,北京 100083%北京石油化工学院信息工程学院,北京 102617 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0253-2336 |
| DOI | 10.12438/cst.2024-1370 |
Cover
| Abstract | TD742; 矿井涌(突)水视频识别是智能化矿井建设的关键之一,通过识别涌(突)水从无到有、从小到大的动态演变过程,有助于防止水量超出矿井排水能力并演变为水害.为此提出了一种基于多通道残差注意力机制的U2Net视频分割模型(MRAU),旨在识别涌(突)水的演变过程.首先,基于卷积注意力模块(CBAM)改进U2Net网络模型,以提高特征提取效果.通过多通道残差预处理,区分水流动态特征与静态背景,并将处理结果作为注意力机制输入模型,从而强化水流特征的学习.此外,使用中间帧掩码作为标签进行多帧融合学习,进一步提升网络对水流动态特征的识别能力.最终,通过学习不同场景下的水流特征,实现对未知场景中涌(突)水动态演变的有效识别.通过与Deeplab、LRASPP、FCN、U2Net网络模型的对比试验,选用Dice和IoU作为评价指标.试验结果表明,MRAU模型的Dice和IoU分别达到 92.88%和 87.51%,相比U2Net基础网络,识别结果分别提高了 4.71%和 7.41%.在未知的涌(突)水场景中测试时,MRAU的 Dice和 IoU得分分别达到了86.75%和 80.23%.与其他模型相比,MRAU的识别精度最高,表明该模型在不同场景下对水流特征具有更强的泛化能力.此外,MRAU能够精准监测涌(突)水流量从小到大的演变过程.最后,通过在井下环境中模拟突水场景,进一步验证MRAU模型在实际生产中的实用性,为矿井水害监测提供了有效的技术手段. |
|---|---|
| AbstractList | TD742; 矿井涌(突)水视频识别是智能化矿井建设的关键之一,通过识别涌(突)水从无到有、从小到大的动态演变过程,有助于防止水量超出矿井排水能力并演变为水害.为此提出了一种基于多通道残差注意力机制的U2Net视频分割模型(MRAU),旨在识别涌(突)水的演变过程.首先,基于卷积注意力模块(CBAM)改进U2Net网络模型,以提高特征提取效果.通过多通道残差预处理,区分水流动态特征与静态背景,并将处理结果作为注意力机制输入模型,从而强化水流特征的学习.此外,使用中间帧掩码作为标签进行多帧融合学习,进一步提升网络对水流动态特征的识别能力.最终,通过学习不同场景下的水流特征,实现对未知场景中涌(突)水动态演变的有效识别.通过与Deeplab、LRASPP、FCN、U2Net网络模型的对比试验,选用Dice和IoU作为评价指标.试验结果表明,MRAU模型的Dice和IoU分别达到 92.88%和 87.51%,相比U2Net基础网络,识别结果分别提高了 4.71%和 7.41%.在未知的涌(突)水场景中测试时,MRAU的 Dice和 IoU得分分别达到了86.75%和 80.23%.与其他模型相比,MRAU的识别精度最高,表明该模型在不同场景下对水流特征具有更强的泛化能力.此外,MRAU能够精准监测涌(突)水流量从小到大的演变过程.最后,通过在井下环境中模拟突水场景,进一步验证MRAU模型在实际生产中的实用性,为矿井水害监测提供了有效的技术手段. |
| Abstract_FL | Mine water inrush video recognition is a key component in intelligent mine construction.By recognizing the dynamic evolution of water inrush from none to some and from small to large,it helps prevent the water volume from exceeding the mine's drainage capacity and turning into a water hazard.Therefore,a video segmentation model based on the Multi-channel Residual Attention mechanism and U2Net(MRAU)was proposed to identify the evolution process of water inrush.First,the U2Net network model was improved based on the Convolutional Block Attention Module(CBAM)to enhance feature extraction.Then,through multi-channel residual preprocessing,the dynamic features of water flow were distinguished from the static background,and the processed results were input into the model as an at-tention mechanism to reinforce the learning of water flow features.In addition,intermediate frame masks were used as labels for multi-frame fusion learning,further enhancing the network's ability to recognize the dynamic features of water flow.Finally,by learning the wa-ter flow features in different scenarios,the model effectively recognizes the dynamic changes of water inrush in unknown scenarios.Com-parative experiments with Deeplab,LRASPP,FCN,and U2Net network models,using Dice and IoU as evaluation metrics,show that the Dice and IoU of the MRAU model reach 92.88%and 87.51%,respectively,which represents improvements of 4.71%and 7.41%over the baseline U2Net network.When tested in unknown water inrush scenarios,the MRAU model achieves Dice and IoU scores of 86.75%and 80.23%.Compared to other models,MRAU achieves the highest recognition accuracy,demonstrating stronger generalization capabilities in recognizing water flow features across different scenarios.Moreover,MRAU can accurately monitor the dynamic evolution of water in-rush from small to large.Finally,simulations of water inrush scenarios in underground environments further verify the practical utility of the MRAU model in real-world production,providing an effective technical solution for mine water hazard monitoring. |
| Author | 武强 赵颖旺 杜沅泽 徐华 张帅 |
| AuthorAffiliation | 矿业大学(北京)内蒙古研究院,内蒙古 鄂尔多斯 017000;中国矿业大学(北京)国家煤矿水害防治工程技术研究中心,北京 100083;矿山水防治与资源化利用国家矿山安全监察局重点实验室,北京 100083%北京石油化工学院信息工程学院,北京 102617 |
| AuthorAffiliation_xml | – name: 矿业大学(北京)内蒙古研究院,内蒙古 鄂尔多斯 017000;中国矿业大学(北京)国家煤矿水害防治工程技术研究中心,北京 100083;矿山水防治与资源化利用国家矿山安全监察局重点实验室,北京 100083%北京石油化工学院信息工程学院,北京 102617 |
| Author_FL | WU Qiang DU Yuanze ZHANG Shuai XU Hua ZHAO Yingwang |
| Author_FL_xml | – sequence: 1 fullname: WU Qiang – sequence: 2 fullname: ZHANG Shuai – sequence: 3 fullname: DU Yuanze – sequence: 4 fullname: XU Hua – sequence: 5 fullname: ZHAO Yingwang |
| Author_xml | – sequence: 1 fullname: 武强 – sequence: 2 fullname: 张帅 – sequence: 3 fullname: 杜沅泽 – sequence: 4 fullname: 徐华 – sequence: 5 fullname: 赵颖旺 |
| BookMark | eNrjYmDJy89LZWAQMzTQMzQyMbbQTy4u0TMyMDLRNTQ2N2Bh4DQwMjXWNTI2NuNg4C0uzkwyMAVKmBgamHEyOD2dv-vJrj7fIMfQF8vbXi6a-LSj7WnnpmcrFj6d1_18Vsvz-fuf7Jr6bFuPxvNVjZrPNmx5ubjv5cyVL9a3Pe1Y_Wzazmebp_IwsKYl5hSn8kJpboZQN9cQZw9dH393T2dHH91iQwMjI13zFGMjE8tEYyMDSwsTCwNLIGloaWBhmJxqkWhilmJqZGJimJxkampoYmFhkmRuapGUZJlmbJgKVGJsnAwkuBnUIeaWJ-alJealx2fllxblAW2Mzy3JrsgqBvnY0NDAwMgYAHPzX9Y |
| ClassificationCodes | TD742 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.12438/cst.2024-1370 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| DocumentTitle_FL | Mine water inrush risk identification method based on MRAU video segmentation model |
| EndPage | 28 |
| ExternalDocumentID | mtkxjs202411002 |
| GrantInformation_xml | – fundername: (国家自然科学基金); (国家自然科学基金); (中央高校基本科研业务费资助项目) funderid: (国家自然科学基金); (国家自然科学基金); (中央高校基本科研业务费资助项目) |
| GroupedDBID | -02 2B. 4A8 5XA 5XC 92H 92I 93N ABJNI ACGFS ALMA_UNASSIGNED_HOLDINGS CCEZO CDRFL CW9 GROUPED_DOAJ PSX TCJ TGT U1G U5L |
| ID | FETCH-LOGICAL-s1022-7d3249a32098480998419081ce8a46d52441cb5514884b758bb9f31e08133c813 |
| ISSN | 0253-2336 |
| IngestDate | Thu May 29 04:07:34 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 11 |
| Keywords | 视频分割 注意力机制 矿井涌(突)水 mine water inrush U2Net multichannel residual preprocessing attention mechanism video segmentation MRAU 多通道残差预处理 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1022-7d3249a32098480998419081ce8a46d52441cb5514884b758bb9f31e08133c813 |
| PageCount | 12 |
| ParticipantIDs | wanfang_journals_mtkxjs202411002 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-11-01 |
| PublicationDateYYYYMMDD | 2024-11-01 |
| PublicationDate_xml | – month: 11 year: 2024 text: 2024-11-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | 煤炭科学技术 |
| PublicationTitle_FL | Coal Science and Technology |
| PublicationYear | 2024 |
| Publisher | 中国矿业大学(北京)国家煤矿水害防治工程技术研究中心,北京 100083 矿业大学(北京)内蒙古研究院,内蒙古 鄂尔多斯 017000 矿山水防治与资源化利用国家矿山安全监察局重点实验室,北京 100083%北京石油化工学院信息工程学院,北京 102617 |
| Publisher_xml | – name: 中国矿业大学(北京)国家煤矿水害防治工程技术研究中心,北京 100083 – name: 矿山水防治与资源化利用国家矿山安全监察局重点实验室,北京 100083%北京石油化工学院信息工程学院,北京 102617 – name: 矿业大学(北京)内蒙古研究院,内蒙古 鄂尔多斯 017000 |
| SSID | ssib051374106 ssj0037581 ssib001105251 ssib012291398 ssib036204842 |
| Score | 2.3709204 |
| Snippet | TD742;... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 17 |
| Title | 基于MRAU视频分割模型的矿井涌(突)水风险识别方法 |
| URI | https://d.wanfangdata.com.cn/periodical/mtkxjs202411002 |
| Volume | 52 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3LaxNBGF9qvehBfOKbHhxQJLo7j92Z426yoQj1IC30VrKbrKIYwaQgvQlSKkrBQwU9WNSDr4OiIpiL_0yTNP4Vft-3k-22FXxAGCaz33yP37ez880wD8c5lwVJM3N1WuGqmcEARRm8yL1RUVmLiyDJgoaL-51nrvrTc_LKvJqf2POztGppsZtcSpd-u6_kf7wKZeBX3CX7D54tmEIB5MG_kIKHIf0rH7NYMVNnUchiiamOZ66FcyzWLAyY9llsWMiZ8ZBOayqBjGERZ7HPQiCjRyZmOmJxwAywkJQBpnXL1CgkjnymqxCN4tMQyOADaKjcZZEkQQLEY8ZA3pAO9bFEyEdIbIA-ryVYfunlOC5GtlqxkKRrzsIaCQqs8vA39LGiDnFpBrKqAv_x20LW5CSKRVW2NflgC0KXMgCBKtcxNeSD-nCUnisW1bZVjpmhyroG9pXnSLi0mwXHbzXhpUl1wDQCRtuh1IhvTEaCYYVViKlCcE1gEQ-rBG7BBChjdEAZI8u2cEBOI8gB2joY0igiIwBKRYBq8vROHOmRywxxBuehrJItIEgLaIu79bzoUXRd6k24EhUu8tNmxl2f4uUm7pU6snxDrQ2J8u37uzpbLuls_bSDa5IRdJHfAbPjAPPb3Vv3bnaQAo8nhHBpLw-CfEmFnf6g0N3DGxWLvsbjHA-sLfoGgfcmaFmE4gqESVohkEddAsa9dDvm2Ex7QCvqeHmbhrQ7r5012tdLgeTsQeeAHQFOhXlzPuRMLN047OwvnQt6xIn6672N3io25s03y6NXT_ory_2HnwdvX_ZfPBo-fzBc_7HRWxt8e3x--P7-hcGnr6PXq6Nn7zY_LvdXPgyefh98WTvqzNXj2ep0xV52UungpEslaMLQxjQEd42WGsZtWkKsrr20pRvSbyoIw700wfGN1jIBa5PEZMJrAYkQKSTHnMn2nXbruDPFm35LJpkERDyJ8x3wU02RZSJ1vYaXnXCmLAIL9mPWWdjhpJN_Jjnl7Ntqaqedye7dxdYZCNC7yVny7C_LgKYe |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8EMRAU%E8%A7%86%E9%A2%91%E5%88%86%E5%89%B2%E6%A8%A1%E5%9E%8B%E7%9A%84%E7%9F%BF%E4%BA%95%E6%B6%8C%28%E7%AA%81%29%E6%B0%B4%E9%A3%8E%E9%99%A9%E8%AF%86%E5%88%AB%E6%96%B9%E6%B3%95&rft.jtitle=%E7%85%A4%E7%82%AD%E7%A7%91%E5%AD%A6%E6%8A%80%E6%9C%AF&rft.au=%E6%AD%A6%E5%BC%BA&rft.au=%E5%BC%A0%E5%B8%85&rft.au=%E6%9D%9C%E6%B2%85%E6%B3%BD&rft.au=%E5%BE%90%E5%8D%8E&rft.date=2024-11-01&rft.pub=%E4%B8%AD%E5%9B%BD%E7%9F%BF%E4%B8%9A%E5%A4%A7%E5%AD%A6%28%E5%8C%97%E4%BA%AC%29%E5%9B%BD%E5%AE%B6%E7%85%A4%E7%9F%BF%E6%B0%B4%E5%AE%B3%E9%98%B2%E6%B2%BB%E5%B7%A5%E7%A8%8B%E6%8A%80%E6%9C%AF%E7%A0%94%E7%A9%B6%E4%B8%AD%E5%BF%83%2C%E5%8C%97%E4%BA%AC+100083&rft.issn=0253-2336&rft.volume=52&rft.issue=11&rft.spage=17&rft.epage=28&rft_id=info:doi/10.12438%2Fcst.2024-1370&rft.externalDocID=mtkxjs202411002 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fmtkxjs%2Fmtkxjs.jpg |