受载煤体裂隙智能表征方法及发育规律研究Intelligent characterization methods and evolution laws of fractures in loaded coal
孙成成,翟成,魏星宇,江丙友,李波波,刘厅,徐吉钊,余旭,孙勇,王继伟,王宇,徐鹤翔
摘要(Abstract):
煤岩裂隙网络是瓦斯运移的主要通道,研究其在加载条件下的动态演化规律对瓦斯高效抽采和煤岩动力灾害防治具有重要意义.针对煤岩裂隙网络裂隙识别精度不足,且静态表征与动态演化分析相脱节缺乏系统框架等问题,融合原位X射线计算机断层扫描(CT)与深度学习技术,提出了一种基于改进U-Net的煤岩裂隙网络智能分割模型,构建了煤岩裂隙网络智能提取端到端框架;结合数字岩心和孔隙网络模型进行三维重构,实现了对等效孔隙半径和配位数等关键参数的定量表征;采用数字体积相关建模方法,分析了受载煤体应力演化和损伤特征,探究了受载煤体裂隙网络动态发育规律.研究结果表明:基于改进U-Net的深度学习模型在裂隙提取中识别准确率较传统方法大幅提升,实现了煤岩裂隙网络智能精准提取,解决了现有方法对微裂隙识别模糊、连续性差等问题;随着应力的增加,等效孔隙半径和配位数成倍增加,受载煤体裂隙结构从孤立裂隙到网状贯通,其复杂性与连通性急剧增强;单轴加载下煤体破坏受控于轴向应力诱导的横向应变集中及材料非均质性引发的局部应力重分布,主应变由离散分布向条带状集中的转变,揭示了煤岩损伤从分布式量变积累到局部化质变临界状态的转变过程.
关键词(KeyWords): 受载煤体;裂隙网络;智能表征;数字岩心;深度学习
基金项目(Foundation): 江苏省基础研究计划项目(BK20251653);; 国家自然科学基金联合基金重点项目(U25B20138);; 中央高校基本科研业务费项目(2025QN1023)
作者(Author): 孙成成,翟成,魏星宇,江丙友,李波波,刘厅,徐吉钊,余旭,孙勇,王继伟,王宇,徐鹤翔
DOI: 10.13247/j.cnki.jcumt.20260029
参考文献(References):
- [1]袁亮,马衍坤,黄勤豪,等.煤岩动力灾害模型试验灾变地层模拟材料研制现状与展望[J].中国矿业大学学报,2024,53(5):827-856.Yuan Liang, Ma Yankun, Huang Qinhao, et al. Development status and prospects of simulation materials for catastrophic prone strata in the physical model experiments on coal and rock dynamic disasters[J].Journal of China University of Mining&Technology,2024, 53(5):827-856.
- [2]王刚,陈昊,陈雪畅,等.基于CT三维重构煤体变开度裂隙渗流特性研究[J].中国矿业大学学报,2024,53(1):59-67.Wang Gang, Chen Hao, Chen Xuechang, et al.Study on seepage characteristics of coal fissures with variable apertures based on CT 3D reconstruction[J].Journal of China University of Mining&Technology,2024, 53(1):59-67.
- [3]王磊,刘化强,李少波,等.煤体张开型裂隙演化规律及失稳前兆试验[J].中国矿业大学学报,2024,53(2):250-263.Wang Lei, Liu Huaqiang, Li Shaobo, et al. Evolution law of open fracture of coal body and instability precursor test[J]. Journal of China University of Mining&Technology, 2024, 53(2):250-263.
- [4]贾男.煤孔隙结构对瓦斯解吸-扩散-渗流过程的影响[J].工矿自动化,2024,50(3):122-130.Jia Nan. Effect of coal pore structure on gas desorption-diffusion-seepage process[J]. Journal of Mine Automation, 2024, 50(3):122-130.
- [5]朱文涛,李小刚,任勇,等.基于CT扫描的煤岩孔隙结构全孔径表征[J].特种油气藏,2024,31(4):71-80.Zhu Wentao, Li Xiaogang, Ren Yong, et al. Full pore size characterization of coal pore structure based on CT scanning[J]. Special Oil&Gas Reservoirs,2024, 31(4):71-80.
- [6]李小二,王鹏,靳翔飞,等.基于CT扫描的煤样图像处理及裂隙形态表征[J].煤矿安全,2022,53(2):125-129.Li Xiaoer, Wang Peng, Jin Xiangfei, et al. Coal sample image processing and fracture morphological representation based on CT scanning[J]. Safety in Coal Mines, 2022, 53(2):125-129.
- [7]Fan C J, Jiang X F, Fan N, et al. Scale effect of coal porosity and permeability characteristics based on CT3D reconstruction from a microperspective[J]. Energy&Fuels, 2024, 38(3):1813-1821.
- [8]王登科,魏强,魏建平,等.煤的裂隙结构分形特征与分形渗流模型研究[J].中国矿业大学学报,2020,49(1):103-109.Wang Dengke, Wei Qiang, Wei Jianping, et al. Fractal characteristics of fracture structure and fractal seepage model of coal[J]. Journal of China University of Mining&Technology, 2020, 49(1):103-109.
- [9]元永国,王瑞,范楠.基于micro-CT扫描的孔裂隙结构表征及渗流模拟[J].煤矿安全,2021,52(8):15-20.Yuan Yongguo, Wang Rui, Fan Nan. Characterization of pore-fracture structure and seepage simulation based on micro-CT scanning[J]. Safety in Coal Mines, 2021, 52(8):15-20.
- [10]张艳博,徐跃东,刘祥鑫,等.基于CT的岩石三维裂隙定量表征及扩展演化细观研究[J].岩土力学,2021,42(10):2659-2671.Zhang Yanbo, Xu Yuedong, Liu Xiangxin, et al.Quantitative characterization and mesoscopic study of propagation and evolution of three-dimensional rock fractures based on CT[J]. Rock and Soil Mechanics, 2021, 42(10):2659-2671.
- [11]朱传奇,谢广祥,王磊.基于CT扫描的煤体裂隙演化与破坏状态表征[J].中国矿业大学学报,2024,53(1):93-105.Zhu Chuanqi, Xie Guangxiang, Wang Lei. Evolution of fracture and failure state characterization of coal based on CT scanning[J]. Journal of China University of Mining&Technology, 2024, 53(1):93-105.
- [12]冯雪健,沈永星,周动,等.基于CT数字岩心深度学习的煤裂隙分布识别研究[J].煤炭科学技术,2023,51(8):97-104.Feng Xuejian, Shen Yongxing, Zhou Dong, et al.Multi-scale distribution of coal fractures based on CT digital core deep learning[J]. Coal Science and Technology, 2023, 51(8):97-104.
- [13]袁永,秦正寒,夏永琪,等.基于改进U-Net的煤矸图像分割模型与放煤控制技术研究[J].煤炭学报,2025,50(5):2722-2738.Yuan Yong, Qin Zhenghan, Xia Yongqi, et al. Coal gangue image recognition model based on improved U-Net and top coal caving control[J]. Journal of China Coal Society, 2025, 50(5):2722-2738.
- [14]郑江韬,齐子豪,刘佳存,等.基于卷积神经网络的煤岩微裂隙提取方法[J].矿业科学学报,2022,7(6):680-688.Zheng Jiangtao, Qi Zihao, Liu Jiacun, et al. Segmentation of micro-cracks in fractured coal based on convolutional neural network[J]. Journal of Mining Science and Technology, 2022, 7(6):680-688.
- [15]Lu F L, Fu C C, Zhang G Y, et al. Convolution neural network based on fusion parallel multiscale features for segmenting fractures in coal-rock images[J]. Journal of Electronic Imaging, 2020, 29(2):023008.
- [16]蔡宇恒,滕奇志,涂秉宇.基于深度学习的岩石铸体薄片图像孔隙自动提取[J].科学技术与工程,2020,20(28):11685-11692.Cai Yuheng, Teng Qizhi, Tu Bingyu. Automatic extraction of pores in thin slice images of rock castings based on deep learning[J]. Science Technology and Engineering, 2020, 20(28):11685-11692.
- [17]王登科,房禹,魏建平,等.基于深度学习的煤岩Micro-CT裂隙智能提取与应用[J].煤炭学报,2024,49(8):3439-3452.Wang Dengke, Fang Yu, Wei Jianping, et al. Intelligent extraction of Micro-CT fissures in coal based on deep learning and its application[J]. Journal of China Coal Society, 2024, 49(8):3439-3452.
- [18]Vishal V, Chandra D. Mechanical response and strain localization in coal under uniaxial loading, using digital volume correlation on X-ray tomography images[J]. International Journal of Rock Mechanics and Mining Sciences, 2022, 154:105103.
- [19]Wang X L, Pan J N, Wang K, et al. Fracture variation in high-rank coal induced by hydraulic fracturing using X-ray computer tomography and digital volume correlation[J]. International Journal of Coal Geology, 2022, 252:103942.
- [20]Liu H Z, Mao L T, Ju Y, et al. Damage evolution in coal under different loading modes using advanced digital volume correlation based on X-ray computed tomography[J]. Energy, 2023, 275:127447.
- [21]Rassouli F S, Lisabeth H. Analysis of timedependent strain heterogeneity in shales using X-ray microscopy and digital volume correlation[J]. Journal of Natural Gas Science and Engineering, 2021,92:103984.
- [22]Duan D, Chen X Y, Feng X J, et al. Study on failure mechanism of mudstone based on digital core and digital volume correlation method[J]. Applied Sciences-Basel, 2022, 12(15):7933.
- [23]Mao L T, Hao N, An L Q, et al. 3D mapping of carbon dioxide-induced strain in coal using digital volumetric speckle photography technique and X-ray computer tomography[J]. International Journal of Coal Geology, 2015, 147:115-125.
- [24]于岩斌,尼传文,崔文亭,等.基于Micro-CT和DVC的单轴压缩下煤岩损伤特征研究[J].采矿与岩层控制工程学报,2025,7(3):68-81.Yu Yanbin, Ni Chuanwen, Cui Wenting, et al.Study on damage characteristics of coal under uniaxial compression based on Micro CT and DVC[J].Journal of Mining and Strata Control Engineering,2025, 7(3):68-81.
- [25]Liu T, Li M Y, Lin B Q, et al. Evolution of coal fractures and its influence on permeability during progressive failure based on in situ CT scanning[J]. Energy&Fuels, 2024, 38(15):14119-14135.
- [26]冯雪健,沈永星,周动,等.基于CT数字岩心深度学习的煤裂隙分布识别研究[J].煤炭科学技术,2023,51(8):97-104.Feng Xuejian, Shen Yongxing, Zhou Dong, et al.Multi-scale distribution of coal fractures based on CT digital core deep learning[J]. Coal Science and Technology, 2023, 51(8):97-104.
- [27]郝天轩,徐新革,赵立桢.煤岩裂隙图像识别方法研究[J].工矿自动化,2023,49(10):68-74.Hao Tianxuan, Xu Xinge, Zhao Lizhen. Research on image recognition methods for coal rock fractures[J]. Journal of Mine Automation, 2023, 49(10):68-74.
- [28]Kazak A, Simonov K, Kulikov V. Machine-learningassisted segmentation of focused ion beam-scanning electron microscopy images with artifacts for improved void-space characterization of tight reservoir rocks[J]. SPE Journal, 2021, 26(4):1739-1758.
- [29]Wu X, Wang F, Zhang X Q, et al. Extraction of fractures in shale CT images using improved U-Net[J]. Energy Geoscience, 2024, 5(2):100185.
- [30]Rushood I A, Alqahtani N, Wang Y D, et al. Segmentation of X-ray images of rocks using deep learning[C]//2020 SPE Annual Technical Conference and Exhibition. Dallas:Society of Petroleum Engineers, 2020:SPE-201282-MS.
- [31]王长盛,翟培城,王林森,等.基于Micro-CT技术的煤岩裂隙精细表征[J].煤炭科学技术,2017,45(4):137-142.Wang Changsheng, Zhai Peicheng, Wang Linsen,et al. Careful features of lithotype creaks based on Micro-CT technology[J]. Coal Science and Technology, 2017, 45(4):137-142.
- [32]王刚,沈俊男,褚翔宇,等.基于CT三维重建的高阶煤孔裂隙结构综合表征和分析[J].煤炭学报,2017,42(8):2074-2080.Wang Gang, Shen Junnan, Chu Xiangyu, et al.Characterization and analysis of pores and fissures of high-rank coal based on CT three-dimensional reconstruction[J]. Journal of China Coal Society, 2017,42(8):2074-2080.
- [33]Sun Y, Feng L, Xu H R, et al. Progressive evolution of flow and heat transfer channels in hot dry rock stimulated by liquid nitrogen cold shock[J]. ACS Omega, 2024, 9(51):50742-50757.