基于AttRes-UNet模型的煤岩裂隙识别技术研究

doi:10.3724/1000-6915.jrme.2025.0589

Abstract
Figure/Table
References (0)
Related Citation (15)

Download: PDF (6141 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The morphological development of coal-rock fractures is a critical factor influencing their mechanical properties, and accurate identification of these fractures is essential for ensuring mine safety. However, existing detection methods often struggle to accurately identify fine fractures and fragmented zones in complex environments. To address this challenge, this study introduces an enhanced AttRes-UNet model based on the ResNet-UNet framework, which incorporates both channel attention (SE) and spatial attention (CBAM). The model utilizes residual structures to improve feature representation and employs attention mechanisms to enhance the extraction of key fracture regions, thereby significantly boosting fracture recognition in complex conditions. A high-quality annotated dataset of real coal-rock images was constructed, and the impacts of two residual backbone depths, ResNet18 and ResNet34, on model performance were systematically assessed. Experimental results reveal that the AttRes34-UNet model significantly outperforms traditional UNet and ResNet-UNet models in terms of accuracy, F1 score, and IoU, demonstrating superior stability and generalization in fine fracture detection and in delineating fragmented zone boundaries. The proposed AttRes-UNet model offers an efficient and precise technical approach for automatic recognition of coal-rock fractures, providing scientific support for safety monitoring and disaster prevention in coal mining operations.

Key words： mining engineering coal rock fractures deep learning ResNet-UNet attention mechanism residual structure image segmentation

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	LUAN Hengjie1
	2
	YANG Yuqing1
	LIU Jiankang1*
	HAO Qingwang2
	JIANG Yujing1
	2
	GUO Yao3
	ZHANG Sunhao1

Cite this article:

LUAN Hengjie1,2,YANG Yuqing1, et al. Coal-rock fracture recognition technology based on the AttRes-UNet model[J]. , 2026, 45(4): 1183-1198.

URL:

https://rockmech.whrsm.ac.cn/EN/10.3724/1000-6915.jrme.2025.0589 OR https://rockmech.whrsm.ac.cn/EN/Y2026/V45/I4/1183

[1] 刘建华，王生维，粟冬梅. 二连盆地群低煤阶煤储层裂隙地质建模与精细描述[J]. 煤炭科学技术，2022，50(5)：198–207.(LIU Jianhua，WANG Shengwei，SU Dongmei. Geological modeling and fine description of fractures in low coal rankcoal reservoirs of Erlian Basin Group[J]. Coal Science and Technology，2022，50(5)：198–207.(in Chinese))
[2] 刘勇，崔洪庆. 基于裂隙形态特征的煤层图像裂隙识别研究[J]. 工矿自动化，2017，43(10)：59–64.(LIU Yong，CUI Hongqing. Research on coal-bed image fractures identification based on fracture shape characteristics[J]. Industry and Mine Automation，2017，43(10)：59–64.(in Chinese))
[3] 汪进超，韩增强，王益腾，等. 基于像素空间信息的孔内低照度图像孔隙结构量化方法研究[J]. 岩石力学与工程学报，2024，43(增1)：3 175–3 186.(WANG Jinchao，HAN Zengqiang，WANG Yiteng，et al. Quantification method of pore structure in low illuminance borehole images based on pixel spatial information[J]. Chinese Journal of Rock Mechanics and Engineering，2024，43(Supp.1)：3 175–3 186. (in Chinese))
[4] 张农，袁钰鑫，韩昌良，等. 基于Mask R-CNN的煤矿巷道掘进迎头裂隙检测与定位算法[J]. 采矿与安全工程学报，2023，40(5)：925–932.(ZHANG Nong，YUAN Yuxin，HAN Changliang，et al. Research on crack detection and localization algorithm for advancing face in coalmine roadways based on Mask R-CNN[J]. Journal of Mining and Safety Engineering，2023，40(5)：925–932.(in Chinese))
[5] HUANG H，LI Q，ZHANG D. Deep learning based image recognition for crack and leakage defects of metro shield tunnel[J]. Tunnelling and Underground Space Technology，2018，77：166–176.
[6] AL-SIT W，AL-NUAIMY W，MARELLI M，et al. Visual texture for au-tomated characterisation of geological features in borehole televiewer imagery[J]. Journal of Applied Geophysics，2015，119：139–146.
[7] 夏丁，葛云峰，唐辉明，等. 数字钻孔图像兴趣区域分割与岩体结构面特征识别[J]. 地球科学，2020，45(11)：4 207–4 217.(XIA Ding，GE Yunfeng，TANG Huiming，et al. Segmentation of region of interest and identification of rock discontinuities in digital borehole images[J]. Earth Science，2020，45(11)：4 207–4 217.(in Chinese))
[8] WANG C，ZOU X，HAN Z，et al. An automatic recognition and pa-rameter extraction method for structural planes in borehole image[J]. Journal of Applied Geophysics，2016，135：135–143.
[9] 汪进超，王川婴，胡胜，等. 孔壁钻孔图像的结构面参数提取方法研究[J]. 岩土力学，2017，38(10)：3 074–3 080.(WANG Jinchao，WANG Chuanying，HU Sheng，et al. A new method for extraction of parameters of structural surface in borehole images[J]. Rock and Soil Mechanics，2017，38(10)：3 074–3 080.(in Chinese))
[10] 汪进超，王川婴，唐新建，等. 基于钻孔摄像技术的岩体节理大小估算方法[J]. 岩土力学，2017，38(9)：2 701–2 707.(WANG Jinchao，WANG Chuanying，TANG Xinjian，et al. A method for estimating rock mass joint size using borehole camera technique[J]. Rock and Soil Mechanics，2017，38(9)：2 701–2 707.(in Chinese))
[11] YUAN Y，ZHANG N，HAN C，et al. Digital image processing-based automatic detection algorithm of cross joint trace and its application in mining roadway excavation practice[J]. International Journal of Mining Science and Technology，2022，32(6)：1 219–1 231.
[12] DEB D，HARIHARAN S，RAO U，et al. Automatic detection and analysis of discontinuity geometry of rock mass from digital images[J]. Computers and Geosciences，2007，34(2)：115–126.
[13] 高峰，黄兴，刘泉声，等. 基于人工神经网络多模型迁移学习的隧(巷)道机械化掘进装备控制参数自主决策方法[J]. 岩石力学与工程学报，2023，42(6)：1 405–1 420.(GAO Feng，HUANG Xing，LIU Quansheng，et al. An autonomous decision-making method for mechanized tunneling equipment control parameters based on transfer learning of multiple ANN models[J]. Chinese Journal of Rock Mechanics and Engineering，2023，42(6)：1 405–1 420.(in Chinese))
[14] SAPOVAL N，AGHAZADEH A，NUTE M G，et al. Current progress and open challenges for applying deep learning across the bio-sciences[J]. Nature Communications，2022，13(1)：1–12.
[15] CHOUDHARY K，DE CSTO B，CHEN C，et al. Recent advances and applications of deep learning methods in materials science[J]. NPJ Computational Materials，2022，8(1)：1–26.
[16] 张紫杉，王述红，王鹏宇，等. 岩坡坡面裂隙网络智能识别与参数提取[J]. 岩土工程学报，2021，43(12)：2 240–2 248.(ZHANG Zishan，WANG Shuhong，WANG Pengyu，et al. Intelligent identification and extraction of geometric parameters for surface fracture networks of rocky slopes[J]. Chinese Journal of Geotechnical Engineering，2021，43(12)：2 240–2 248.(in Chinese))
[17] 徐君，黄昕，王君朋，等. 礁灰岩孔隙结构表征及关键孔隙节点识别研究[J]. 岩石力学与工程学报，2023，42(增1)：3 355– 3 366.(XU Jun，HUANG Xin，WANG Junpeng，et al. Characterization of coral reef limestone?s pore structure and identification of key pore nodes[J]. Chinese Journal of Rock Mechanics and Engineering，2023，42(Supp.1)：3 355–3 366.(in Chinese))
[18] XIN S，YI H，LEI Z，et al. Innovative load identification with Res-UNet：Integrating phase space reconstruction and physics-informed deep learning[J]. Ocean Engineering，2024，312(P2)：119173.
[19] AMIEGHEMEN G E，SHERIF M M. Deep convolutional neural network ensemble for pavement crack detection using high elevation UAV images[J]. Structure and Infrastructure Engineering，2025，21(6)：1 008–1 023.
[20] ZHANG A，WANG K C P，LI B，et al. Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network[J]. Computer-Aided Civil and Infrastructure Engineering，2017，32(10)：805–819.
[21] ZHANG A，WANG K C P，FEI Y，et al. Deep learning-based fully automated pavement crack detection on 3D asphalt surfaces with an improved Crack Net[J]. Journal of Computing in Civil Engineering，2018，32(5)：04018041.
[22] 张庆贺，陈晨，袁亮，等. 基于DIC和YOLO算法的复杂裂隙岩石破坏过程动态裂隙早期智能识别[J]. 煤炭学报，2022，47(3)：1 208–1 219.(ZHANG Qinghe，CHEN Chen，YUAN Liang，et al. Early and intelligent recognition of dynamic cracks during damage of complex fractured rock masses based on DIC and YOLO algorithms[J]. Journal of China Coal Society，2022，47(3)：1 208–1 219.(in Chinese))
[23] 苏钰桐，杨炜毅，李俊霖. 基于YOLO v3的煤岩钻孔图像裂隙智能识别方法[J]. 煤矿安全，2021，52(4)：156–161.(SU Yutong，YANG Weiyi，LI Junlin. Intelligent recognition method of borehole image fractures for coal and rock based on YOLO v3[J]. Safety in Coal Mines，2021，52(4)：156–161.(in Chinese))
[24] 郝晨光，郭晓阳，邓存宝，等. 基于Bi-PTI模型的CT数字煤岩孔裂隙精准识别及阈值反演[J]. 煤炭学报，2023，48(4)：1 516–1 526. (HAO Chenguang，GUO Xiaoyang，DENG Cunbao，et al. Precise identification and threshold inversion of pores and fissures in CT digital coalrock based on Bi-PTI model[J]. Journal of China Coal Society，2023，48(4)：1 516–1 526.(in Chinese))
[25] 张立亚，郝博南，孟庆勇，等. 基于HSV空间改进融合Retinex算法的井下图像增强方法[J]. 煤炭学报，2020，45(增1)：532–540.(ZHANG Liya，HAO Bonan，MENG Qingyong，et al. Method of image enhancement in coal mine based on improved Retinex fusion algorithm in HSV space[J]. Journal of China Coal Society，2020，45(Supp.1)：532–540.(in Chinese))
[26] 杨光宇，郑永果. 一种基于局部和全局拟合的混合多相水平集分割模型及算法[J]. 山东科技大学学报：自然科学版，2019，38(6)：81–90.(YANG Guangyu，ZHENG Yongguo. Segmentation model and algorithm of a hybrid multiphase level set based on local and global fitting[J]. Journal of Shandong University of Science and Technology：Natural Science，2019，38(6)：81–90.(in Chinese))
[27] YANG Y，ZHOU W，JISKANI M I，et al. Extracting unstructured roads for smart open-pit mines based on computer vision：Implications for intelligent mining[J]. Expert Systems With Applications，2024，249(PC)：123628.
[28] 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.(in Chinese))
[29] CHEN J，YANG T，ZHANG D，et al. Deep learning based classification of rock structure of tunnel face[J]. Geoscience Frontiers，2021，12(1)：395–404.