| Citation: |
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. DOI: 10.13199/j.cnki.cst.2022-0530
|
In order to realize high-precision and high-efficiency identification of multi-scale distribution characteristics of coal fractures, carry out the study of multi-scale distribution characteristics identification methods based on CT digital core deep learning. Industrial CT scanning system is used to collect a large number of coal original CT digital core information array, the CT digital core information array is converted into a two-dimensional gray-scale image and then it is divided into square images of different scales and the image brightness is enhanced to different levels as training samples, Finally, the construction and optimization of model parameters of AlexNet, ResNet-18, GoogLeNet and Inception-V3 models for the identification of CT-containing fractures are realized by Matlab platform. Study the recognition accuracy and verification accuracy of different model training under different number of training samples; Study the accuracy, calculation efficiency and training time of different models for images with different scales and brightness under the same training sample, obtain the optimal model for calculating the fractal dimension of two-dimensional CT images with fractures, then, the fractal distribution characteristics of each fracture image are calculated according to the statistical method of box-counting dimension, compared with the traditional binarization method and human eye recognition method, The applicability of the multi-scale distribution characteristics identification method of coal fractures based on CT digital core deep learning is verified. The result shows: ① ResNet-18 model is the optimal model for calculating the fractal dimension of two-dimensional CT images with cracks when the image sample is brightness 4 and the scale is 3.5 mm to 21 mm, the model has high accuracy and short training time in calculating the fractal dimension of two-dimensional CT fracture images. ② Compared with the traditional binarization method, the multi-scale recognition method of coal fracture based on CT digital core deep learning has the advantages of fast speed, high accuracy and is not easily affected by impurities in coal.
| [1] |
孟巧荣,赵阳升,胡耀青,等. 焦煤孔隙结构形态的实验研究[J]. 煤炭学报,2011,36(3):487−490.
MENG Qiaorong,ZHAO Yangsheng,HU Yaoqing,et al. Experimental study on pore structure morphology of coking coal[J]. Journal of China Coal Society,2011,36(3):487−490.
|
| [2] |
MANDELBROT B B. Stochastic models for the Earth's relief, the shape and the fractal dimension of the coastlines, and the number-area rule for islands[J]. Proceedings of the National Academy of Sciences of the United States of America,1975,72(10):3825−3828. doi: 10.1073/pnas.72.10.3825
|
| [3] |
龚 爽,赵毅鑫,王 震,等. 层理对煤岩动态裂纹扩展分形特征的影响[J]. 煤炭学报,2021,46(8):2574−2582.
GONG Shuang,ZHAO Yixin,WANG Zhen,et al. Effect of bedding on frac tal characteristics of dynamic crack propagation in coal and rock[J]. Journal of China Coal Society,2021,46(8):2574−2582.
|
| [4] |
康天合,赵阳升,靳钟铭. 煤体裂隙尺度分布的分形研究[J]. 煤炭学报,1995(4):393−398.
KANG Tianhe,ZHAO Yangsheng,JIN Zhongming. Fractal study on the scale distribution of coal fractures[J]. Journal of China Coal Society,1995(4):393−398.
|
| [5] |
冯增朝, 赵阳升. 岩体裂隙尺度对其变形与破坏的控制作用[J]. 岩石力学与工程学报, 2008(1): 78–83.
FENG Zengchao, ZHAO Yangsheng. Chinese Journal of Rock Mechanics and Engineering, 2008(1): 78–83.
|
| [6] |
赵阳升, 马 宇, 段康廉. 岩层裂缝分形分布相关规律研究[J]. 岩石力学与工程学报, 2002(2): 219–222.
ZHAO Yangsheng, MA Yu, DUAN Kanglian. Chinese Journal of Rock Mechanics and Engineering, 2002(2): 219–222.
|
| [7] |
袁 媛,潘鹏志,赵善坤,等. 基于数字图像相关法的含填充裂隙大理岩单轴压缩破坏过程研究[J]. 岩石力学与工程学报,2018,37(2):339−351.
YUAN yuan,PAN Pengzhi,ZHAO Shankun,et al. Study on uniaxial compres sion failure process of marble with filled fractures based on digital image correlation method[J]. Journal of Rock Mechanics and Engineering,2018,37(2):339−351.
|
| [8] |
宋晓夏,唐跃刚,李 伟,等. 基于显微CT的构造煤渗流孔精细表征[J]. 煤炭学报,2013,38(3):435−440.
SONG Xiaoxia,TANG Yuegang,LI Wei,et al. Fine characterization of seep age holes in structural coal based on Micro CT[J]. Journal of China Coal Society,2013,38(3):435−440.
|
| [9] |
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. Comprehensive characteri zation and analysis of high-order coal pore fracture structure based on CT three-dimensional reconstruction[J]. Journal of China Coal Society,2017,42(8):2074−2080.
|
| [10] |
冯子军,赵阳升. 煤的热解破裂过程−孔裂隙演化的显微CT细观特征[J]. 煤炭学报,2015,40(1):103−108.
FENG Zijun,ZHAO Yangsheng. Pyrolysis and fracture process of coal –- Micro CT microscopic characteristics of pore and fissure evolution[J]. Journal of China Coal Society,2015,40(1):103−108.
|
| [11] |
冯增朝,赵阳升. 岩体裂隙分维数与岩体强度的相关性研究[J]. 岩石力学与工程学报,2003(S1):2180−2182.
FENG Zengchao,ZHAO Yangsheng. Study on the correlation between fractal dimension of rock fracture and rock strength[J]. Journal of Rock Mechanics and Engineering,2003(S1):2180−2182.
|
| [12] |
张青成,左建民,毛灵涛. 基于体视学原理的煤岩裂隙三维表征试验研究[J]. 岩石力学与工程报,2014,33(6):1227−1232.
ZHANG Qingcheng,ZUO Jianmin,Mao Lingtao. Experimental study on three-dimensional characterization of coal rock fractures based on stereological principle[J]. Journal of Rock Mechanics and Engineering,2014,33(6):1227−1232.
|
| [13] |
冯春成. 基于深度学习的水电站溢流坝表观裂缝检测方法研究[D]. 绵阳: 西南科技大学, 2021.
FENG Chuncheng. Research on apparent crack detection method of hydropower station overflow dam based on deep learning [D]. Mianyang: Southwest University of Science and Technology, 2021.
|
| [14] |
李生元. 基于深度学习的混凝土结构表面损伤检测方法研究[D]. 大连: 大连理工大学, 2020.
LI Shengyuan. Research on surface damage detection method of con crete structure based on deep learning [D]. Dalian: Dalian University of Technology, 2020.
|
| [15] |
魏世银. 大跨桥梁结构健康诊断和管养决策的机器学习方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2020.
WEI Shiyin. Research on machine learning method for structural health diagnosis and management and maintenance decision of long-span bridges [D]. Harbin: Harbin Institute of Technology, 2020.
|
| [16] |
陈涵深. 基于深度学习的路面破损检测研究[D]. 杭州: 浙江工业大学, 2020.
CHEN Hanshen. Research on pavement damage detection based on deep learning [D]. Hangzhou: Zhejiang University of Technology, 2020.
|
| [17] |
黄宏伟, 李庆桐. 基于深度学习的盾构隧道渗漏水病害图像识别[J]. 岩石力学与工程学报, 2017, 36(12): 2861–2871.
HUANG Hongwei, LI Qingtong. Image recognition of water leakage disease of shield tunnel based on deep learning [J] . Journal of Rock Mechanics and Engineering, 2017, 36(12): 2861–2871.
|
| [18] |
袁 峰,申 涛,谢晓深,等. 基于深度学习的地震多属性融合技术在导水裂隙带探测中的应用[J]. 煤炭学报,2021,46(10):3234−3244.
YUAN Feng,SHEN Tao,XIE Xiaoshen,et al. Application of seismic multi-attribute fusion technology based on deep learning in the detection of water conducting fracture zone[J]. Journal of China Coal Society,2021,46(10):3234−3244.
|
| [19] |
冯增朝, 赵阳升. 岩体裂隙分维数与岩体强度的相关性研究[J]. 岩石力学与工程学报, 2003(S1): 2180–2182.
FENG Zengchao, ZHAO Yangsheng. Study on the correlation between the fractal dimension of rock mass fractures and rock mass strength [J]. Chinese Journal of Rock Mechanics and Engineering, 2003 (S1): 2180-2182.
|
| [20] |
周 动,冯增朝,王 辰,等. 煤吸附甲烷结构变形的多尺度特征[J]. 煤炭学报,2019,44(7):2159−2166.
ZHOU Dong,FENG Zengchao,WANG Chen,et al. Multiscale character istics of structural deformation of coal adsorbed methane[J]. Journal of China Coal Society,2019,44(7):2159−2166.
|
| [21] |
KRIZHEVSKY A,SUTSKEVER I,HINTON G. ImageNet Classification with Deep Convolutional Neural Networks[J]. Advances in Neural Information Processing Systems,2012:1097−1105.
|
| [22] |
HE K , ZHANG X, REN S, et al. Deep residual learning for image recognition[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770−778.
|
| [23] |
SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1−9.
|
| [24] |
SZEGEDY C,VANHOUCKE V,IOFFE S,et al. Rethinking the Incep tion Architecture for Computer Vision[J]. IEEE,2016:2818−2826.
|
| [1] | LEI Guorong, LI Chunyuan, QI Qingxin, WANG Jiamin, DU Weisheng, LI Xiangshang, HE Tuan. Ultrasonic and CT scanning analysis of coal-rock mass under the primary bedding structure[J]. COAL SCIENCE AND TECHNOLOGY, 2024, 52(3): 74-86. DOI: 10.13199/j.cnki.cst.2023-0314 |
| [2] | ZHANG Liang, QI Qingxin, REN Ting, LI Xiangchun, GAO Ke, LI Chunyuan, LI Xiaopeng, YUAN Honghui. Study on the damage and fracture characteristics of coal rock based on the X-ray micro-CT scanning technology and statistical strength theory[J]. COAL SCIENCE AND TECHNOLOGY, 2023, 51(S2): 1-12. DOI: 10.13199/j.cnki.cst.2022-2185 |
| [3] | WANG Jiamin, WANG Shouguang, LI Xiangshang, BU Mohua, LUAN Zhaolong, ZHANG Peng. Study on mechanical properties and damage characteristics of granite under thermal shock based on CT scanning[J]. COAL SCIENCE AND TECHNOLOGY, 2023, 51(8): 58-72. DOI: 10.13199/j.cnki.cst.2023-0180 |
| [4] | LIU Jianhua, WANG Shengwei, SU Dongmei. Geological modeling and fine description of fractures in low coal rank coal reservoirs of Erlian Basin Group[J]. COAL SCIENCE AND TECHNOLOGY, 2022, 50(5). |
| [5] | WANG Gang, CHEN Xuechang, HAN Dongyang, QIN Xiangjie, FENG Jing. Research on threshold segmentation algorithm of coal CT images based on improved Otsu[J]. COAL SCIENCE AND TECHNOLOGY, 2021, 49(1): 264-271. DOI: 10.13199/j.cnki.cst.2021.01.023 |
| [6] | WEN Hu, FAN Shixing, MA Li, GUO Jun, CHENG Xiaojiao, TONG Xiaozhang. CT Scanning Technology on coal-rock damage: a comprehensive review[J]. COAL SCIENCE AND TECHNOLOGY, 2019, (1). |
| [7] | GONG Weili, WU Xiaodong, ZHANG Zixiang, ZHAO Haiyan. Study on microscopic damage features of coal-rock based on CT scanning[J]. COAL SCIENCE AND TECHNOLOGY, 2018, (9). |
| [8] | Wang Qiao Zhao Dong Feng Zengchao Zhou Dong Zhang Chao, . Experimental study on fracturing of coal by injection liquid nitrogen in drill based on CT scanning[J]. COAL SCIENCE AND TECHNOLOGY, 2017, (4). |
| [9] | Wang Changsheng Zhai Peicheng Wang Linsen Wang Chunguang Zhang Xuepeng Wu Xuezhen Jiang Yujing, . Careful features of lithotype cracks based on Micro-CT technology[J]. COAL SCIENCE AND TECHNOLOGY, 2017, (4). |
| [10] | Study on Seismic CT Technology Applied to Coal Mining Face[J]. COAL SCIENCE AND TECHNOLOGY, 2012, (7). |
| 1. |
刘纪坤, 张博浩, 王翠霞, 赵兰华, 徐栋梁. 基于DeepLabv3+网络的煤体孔隙识别及分析. 西安科技大学学报. 2025(03)
| |
| 2. |
王磊，张宇，朱传奇，刘怀谦，陈礼鹏，李少波，吴雨轩. 吸附CO_2煤体静力学特性及细观损伤破坏特征. 岩石力学与工程学报. 2025(01): 56-68 .
| |
| 3. |
康长豪. 基于数字岩心的鄂尔多斯盆地烟煤的REV计算与非均质性评估. 陕西煤炭. 2025(05): 77-81 .
| |
| 4. |
刘高峰，关文博，张震，李宝林，刘欢，司念. 基于CT扫描的CO_2相变致裂煤裂隙演化特征. 矿业科学学报. 2024(03): 342-350 .
| |
| 5. |
肖福坤，刘欢欢，单磊. 基于连通性阈值分割的煤岩裂隙识别方法. 工矿自动化. 2024(08): 127-134 .
| |
| 6. |
王登科，房禹，魏建平，张宏图，赵立桢，王龙航，夏缘帝，李璐，王少璞，张强，任海慧. 基于深度学习的煤岩Micro-CT裂隙智能提取与应用. 煤炭学报. 2024(08): 3439-3452 .
| |
| 7. |
张超，程仁辉，秦荣荣，段晨烨，张源福. 单轴载荷下钻孔不同倾角试件能量演化特征. 西安科技大学学报. 2024(05): 805-816 .
| |
| 8. |
刘大锰，王子豪，陈佳明，邱峰，朱凯，高羚杰，周柯宇，许少博，孙逢瑞. 基于ResNet残差神经网络识别的深部煤层显微组分和微裂缝分类——以鄂尔多斯盆地石炭系本溪组8~#煤层为例. 石油与天然气地质. 2024(06): 1524-1536 .
| |
| 9. |
李智勇，刘恩强，高辉. 基于YOLOv7的煤样受载裂隙识别研究. 现代矿业. 2024(12): 32-35 .
| |
| 10. |
王辰，冯增朝，杨涛. 分形理论在煤中甲烷分布研究领域的应用探索. 华北科技学院学报. 2023(05): 108-116 .
|
Supported by: Beijing Renhe Information Technology Co., Ltd. 
DownLoad: