To improve the intelligence level of fracture identification in shale gas reservoirs and realize automated analysis of electrical imaging logging data, the TransFracNet deep learning model was proposed. First, MobileNetV3 and the Swin Transformer were integrated to combine lightweight convolution with global attention mechanisms. Subsequently, Watershed positional encoding and an AFPN-CA multi-scale feature fusion module were incorporated into the network architecture. Finally, a preprocessing algorithm based on Filtersim-Inpainting was applied to enhance image quality. Results indicate that the model performs well on the test set of the Wufeng-Longmaxi Formation shale reservoir in the Luzhou block. The accuracy of fracture intersection identification reaches 92.3%, representing a 25% improvement compared to traditional methods. Image quality is significantly improved by the preprocessing algorithm, with a fracture restoration completeness of 98.6%. The system maintains a stable processing speed of 45 FPS, and single-well interpretation efficiency is increased by a factor of 20. Four types of fractures, including low-angle high-conductivity fractures and en echelon induced fractures, are supported for identification, along with the intelligent extraction of their geometric parameters. It is concluded that the TransFracNet model demonstrates excellent performance in handling complex geological structures and multi-scale fracture features. Geological prior knowledge is innovatively fused with deep learning features. The research results provide reliable technical support for the evaluation of shale gas reservoirs.
ZhouJi, NanZhijun, DuanChengdong, et al. Fully electric and automated fracturing technology for shale gas[J]. Industrial Control Computer, 2025, 38(7): 44-45, 48.
LiuLihang, HuHaiyan, ZhanXuefeng, et al. Pore structure and NMR fractal characteristies of deep shale of Longmaxi Formation in Luzhou block, Sichuan Basin[J]. China Sciencepaper, 2023, 18(5): 501-511.
ShiXuewen, WuWei, HuHaiyan, et al. The whole apertures of deeply buried Wufeng-Longmaxi Formation shale and their controlling factors in Luzhou district, Sichuan Basin[J]. Earth Science, 2023, 48(1): 158-172.
[7]
黄登旺. 川南深层页岩气水平井测井解释方法研究[D]. 武汉: 长江大学, 2023.
[8]
HuangDengwang. Study on interpretation method of deep shale gashorizontal well logging in southern Sichuan[D]. Wuhan: Yangtze University, 2023.
WeiBoyang, YangZhanjun, WangLidang, et al. Application of Faster R-CNN in reservoir fractures identification[J]. South-to-North Water Transfers and Water Science & Technology, 2024, 53(11): 62-63.
[11]
ChenS. The wavelet transformation sensitiveness to direction of image characteristics and its application in formation microscanner image fracture identification[J]. Sensors & Transducers, 2014, 173(6): 16-20.
JingJianen, WeiWenbo, MeiZhongwu, et al. Method of well-logging interpretation for fracture reservoirs of carbonate rock: a case study in Tahe oilfield[J]. Progress in Geophysics, 2005, 20(1): 78-82.
LiZhenling, ShenJinsong, LiXining, et al. Estimating porosity spectrum of fracture and karst cave from conductivity image by morphological filtering[J]. Journal of Jilin University(Earth Science Edition), 2017, 47(4): 1295-1307.
[16]
XueY C, ChengL S, MouJ Y, et al. A new fracture prediction method by combining genetic algorithm with neural network in low-permeability reservoirs[J]. Journal of Petroleum Science and Engineering, 2014, 121: 159-166.
[17]
AzimR A. Estimation of reservoirs fracture network properties using an artificial intelligence technique[J]. International Journal of Applied Engineering Research, 2021, 12(15): 5345-5350.
LiBingtao, WangZhizhang, KongChuixian, et al. A new intelligent method of fracture recognition based on imaging logging[J]. Well Logging Technology, 2023, 43(3): 257-262.
ChuHonghu, YuanHuaqing, LongLizhi, et al. A Transformer-based cascade method for segmenting bridge cracks from high-resolution images[J]. China Journal of Highway and Transport, 2024, 37(2): 65-76.
LuoChao, LiJinxi, LiZhiwu, et al. Structural deformation characteristics and formation process of Luzhou block in Sichuan Basin, China[J]. Journal of Chengdu University of Technology (Science & Technology Edition), 2022, 49(6): 665-673.
FengZhou, WuHongliang, GuoHongbo, et al. Sawtooth effect correction for electric lmaging logging curves[J]. Well Logging Technology, 2017, 41(4): 423-427.
LiuYaowei. Electrical image log formation dip processing method study and software developing[D]. Beijing: China University ofPetroleum (Beijing), 2007.
ShenKe, XiaoXiaoling, ZhangXiang, et al. Improved automatic crack identilfication for electrical imaging logging using PSPNet[J]. Science Technology and Engineering, 2025, 25(7): 2691-2702.
[34]
XiangC, GuoJ, CaoR, et al. A crack-segmentation algorithm fusing transformers and convolutional neural networks for complex detection scenarios[J]. Automation in Construction, 2023, 152:104894.