基于优化的U-net网络掘进工作面煤岩识别方法研究  

Research on coal and rock identification method of excavation working face based on optimized U-net network

作　　者：栾恒杰[1,2] 杨玉晴 刘建康 蒋宇静[1,2] 刘建荣[2] 马德良 张孙豪 LUAN Hengjie;YANG Yuqing;LIU Jiankang;JIANG Yujing;LIU Jianrong;MA Deliang;ZHANG Sunhao(State Key Laboratory of Mining Disaster Prevention and Control Co-founded by Shandong Province and the Ministry of Science and Technology,Shandong University of Science and Technology,Qingdao 266590,China;Academician(Expert)Workstation,Inner Mongolia Shanghaimiao Mining Co.,Ltd.,Ordos 016299,China;Qingdao Zhiyan Intelligent Control Technology Co.,Ltd.,Qingdao 266590,China)

机构地区：[1]山东科技大学矿山灾害预防控制省部共建国家重点实验室培育基地,山东青岛266590 [2]内蒙古上海庙矿业有限责任公司院士专家工作站,内蒙古鄂尔多斯016299 [3]青岛知岩智控科技有限公司,山东青岛266590

出　　处：《采矿与岩层控制工程学报》2025年第1期94-108,共15页Journal of Mining and Strata Control Engineering

基　　金：国家自然科学基金资助项目(52204099);山东省自然科学基金资助项目(ZR2022QE203);省部共建矿山岩层智能控制与绿色开采国家重点实验室培育基地开放基金资助项目(MDPC2024ZR03)。

摘　　要：为了提高煤岩识别的精准度,采集了内蒙古上海庙矿业有限责任公司榆树井煤矿掘进工作面煤岩原始图像并制作了深度学习数据集,通过FCN全卷积神经网络(FCN网络)、Unet语义分割网络(U-net网络)与加入Canny边缘检测算法改进后的U-net网络等3种网络模型对数据集进行训练,并对训练结果进行对比分析。分析结果表明:在训练次数达到100次时,3种网络模型准确率分别为89.25%, 93.52%及94.55%,改进U-net网络模型准确率相较改进前提高1.03%;在煤岩识别方面, U-net网络模型比FCN网络模型取得了更高的准确率,在测试环节中也表现出了更好的性能;在预测环节中,对煤岩边缘部分的识别做到了更为精准的处理。该方法可为煤岩识别的精准度的提高提供参考。To improve the accuracy of coal rock recognition,this study collected the original images of coal rock from the excavation face in Yushujing coal mine of Shanghai Temple Mining Co.Inner Mongolia,and produced a deep learning dataset.The dataset is trained by three kinds of network models,including FCN fully convolutional neural network(FCN network),U-net Semantic Segmentation Network(U-net Network),and U-net Network improved by adding Canny Edge Detection Algorithm,and the training results were compared and analyzed.The results show that the accuracy of the three network models is 89.25%,93.52%and 94.55%,respectively.When the number of training times reaches 100,the accuracy of the improved U-net network model increased by 1.03%.In coal rock identification,the U-net network model achieved higher accuracy than the FCN network model and showed better performance in the testing session.In the prediction session,the recognition of the edge part of the coal rock was achieved with more accurate treatment.The method can provide a reference for improvement of the accuracy of coal rock recognition.

关 键 词：煤岩识别 深度学习 U-net网络 CANNY边缘检测算法 

分 类 号：TD67[矿业工程—矿山机电] TP183[自动化与计算机技术—控制理论与控制工程]