An Intelligent Classification Model of Surrounding Rock for Large Cross-Section Tunnel Based on the Information Fusion of Drilling Parameters and Tunnel Face Images
1.School of Civil Engineering, Southwest Jiaotong University, Chengdu Sichuan 610031, China
2.Key Laboratory of Intelligent Construction and Maintenance for Geotechnical and Tunnel Engineering in Extreme Environments, Southwest Jiaotong University, Chengdu Sichuan 610031, China
To achieve rapid and accurate surrounding rock classification during the construction phase, a surrounding rock classification model was proposed by integrating information of 2 types of multi-source heterogeneous data including drilling parameters and high-definition digital images of the tunnel face. Based on 2 large cross-section tunnel projects with drilling and blasting methods in the mountainous regions, 807 samples of drilling parameters and 807 samples of high-definition digital images of the tunnel face were collected, and information of these 2 types of samples were processed specifically. Using the processed data, based on the training of Random Forest model and an Inception-v3 model, intelligent classification models of surrounding rock based on drilling parameters and high-definition digital images of the tunnel face were established respectively. Information fusion techniques were then applied to integrate the features of these 2 types of data, constructing an information fused surrounding rock classification model based on drilling parameters and high-definition digital images of the tunnel face. The 3 models were validated and compared using data from the background projects. The results indicated that under identical sample conditions, the fused classification model achieved the best performance, with an accuracy of 94.48%, an average recall rate of 91.52%, an average precision of 91.13%, and a balanced F-score of 91.20%. Further field experiments were conducted to evaluate the performance of the 3 models on new samples, where the fused classification model achieved an accuracy of 92.31%, demonstrating its engineering applicability. This model enabled the automatic processing and information extraction of drilling parameters and tunnel face images at each tunnel face in the field, providing intelligent surrounding rock classification.
WANGMingnian, ZHANGXiao, ZHAOSiguang, et al. Research on Design Method of Advance Support System for Mechanized Full-Face Excavation of Tunnels in Soft and Weak Surrounding Rock [J]. Journal of the China Railway Society, 2020, 42 (8): 146-154. in Chinese
WANGZhijian. Research on Key Technology of Large Cross-Sectional Mechanized Construction of Zhengzhou-Wanzhou High-Speed Railway Tunnel [J]. Tunnel Construction, 2018, 38 (8): 1257-1270. in Chinese
[5]
ZHANGX, WANGM N, LIJ W, et al. Safety Factor Analysis of a Tunnel Face with an Unsupported Span in Cohesive-Frictional Soils [J]. Computers and Geotechnics, 2020, 117: 103221.
[6]
姚萌.基于凿岩台车钻进参数的隧道围岩智能分级方法研究[D].成都:西南交通大学,2020.
[7]
YAOMeng. Study on Intelligent Classification of Surrounding Rock Based on Drilling Jumbo’s Drilling Parameters [D]. Chengdu: Southwest Jiaotong University, 2020. in Chinese
[8]
ZHANGX, WANGM N, WANGZ L, et al. A Limit Equilibrium Model for the Reinforced Face Stability Analysis of a Shallow Tunnel in Cohesive-Frictional Soils [J]. Tunnelling and Underground Space Technology, 2020, 105: 103562.
YIWenhao, WANGMingnian, TONGJianjun, et al. Inhomogeneity Identification Method for Surrounding Rock of Large-Section Rock Tunnel Face Based on Support Vector Machine [J]. China Railway Science, 2021, 42 (5): 112-122. in Chinese
[11]
WANGM N, ZHAOS G, TONGJ J, et al. Intelligent Classification Model of Surrounding Rock of Tunnel Using Drilling and Blasting Method [J]. Underground Space, 2021, 6 (5): 539-550.
WANGYang, WANGShuhong, GUOMudan, et al. Fast Digital Identification of Joint Information of Tunnel Work Face and Its Stability Analysis [J]. Chinese Journal of Geotechnical Engineering, 2011, 33 (11): 1734-1739. in Chinese
LENGBiao, ZHANGYi, YANGHui, et al. Rapid Recognition of Rock Mass Fractures in Tunnel Faces [J]. Journal of Southwest Jiaotong University, 2021, 56 (2): 246-252, 322. in Chinese
[16]
TEALER. The Concept of Specific Energy in Rock Drilling [J]. International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts, 1965, 2 (1): 57-73.
ZHANGYouzhen, ZHANGNing, SHAOJunjie, et al. Fuzzy Identification of Coal-Bearing Strata Lithology Based on Drilling Parameter Clustering [J]. Journal of China Coal Society, 2019, 44 (8): 2328-2335. in Chinese
[19]
LIQ F, PENGC, FUJ H, et al. A Comprehensive Machine Learning Model for Lithology Identification while Drilling [J]. Geoenergy Science and Engineering, 2023, 231: 212333.
[20]
ZHAOR J, SHIS S, LIS C, et al. Deep Learning for Intelligent Prediction of Rock Strength by Adopting Measurement while Drilling Data [J]. International Journal of Geomechanics, 2023, 23 (4): 04023028.
ZHAOSiguang, WANGMingnian, LUOLiju, et al. Calculation Method for Basic Quality Index of Tunnel Surrounding Rock Based on Penetration Velocity of Drill Jumbo [J]. China Railway Science, 2023, 44 (2): 83-91. in Chinese
WANGMingnian, ZHAOSiguang, TONGJianjun, et al. Three-Dimensional Fine Classification Method for Tunnel Face Surrounding Rock Based on Blasting Hole Drilling Parameters of Drilling Jumbo [J]. Journal of the China Railway Society, 2024, 46 (10): 163-173. in Chinese
YIWenhao, WANGMingnian, TONGJianjun, et al. Inhomogeneity Identification Method for Surrounding Rock of Large-Section Rock Tunnel Face Based on Support Vector Machine [J]. China Railway Science, 2021, 42 (5): 112-122. in Chinese
[27]
冷彪.基于数码成像的隧道掌子面地质信息系统研究[D].成都:西南交通大学,2009.
[28]
LENGBiao. Research on Tunnel Face Geology Information System Based on Digital Image [D]. Chengdu: Southwest Jiaotong University, 2009. in Chinese
YINGuansheng, GAOJianguo, SHIMinghui, et al. Tunnel Crack Recognition Method under Image Block [J]. Journal of Traffic and Transportation Engineering, 2022, 22 (2): 148-159. in Chinese
LIUXuezeng, YEKang. A Long-Distance Image Measuring Technique for Crack on Tunnel Lining [J]. Journal of Tongji University (Natural Science), 2012, 40 (6): 829-836. in Chinese
LIUHouxiang, LIWangshi, ZHAHuanyi, et al. Method for Surrounding Rock Mass Classification of Highway Tunnels Based on Deep Learning Technology [J]. Chinese Journal of Geotechnical Engineering, 2018, 40 (10): 1809-1817. in Chinese
FANGYu, LIUBaoguo, LIUKaiyun. Tunnel Surrounding Rock Grading Model Based on Genetic-Support Vector Classification Coupling Algorithm [J]. Journal of the China Railway Society, 2013, 35 (1): 108-114. in Chinese
LINGTonghua, CHENZinong, ZHANGSheng, et al. Lightweight Network Identification Method of Rock Lithology and Its Application in Tunnel Engineering [J]. Journal of Railway Science and Engineering, 2023, 20 (9): 3604-3615. in Chinese
ZHANGYe, LIMingchao, HANShuai. Automatic Identification and Classification in Lithology Based on Deep Learning in Rock Images [J]. Acta Petrologica Sinica, 2018, 34 (2): 333-342. in Chinese
TIANSiming, WUKefei, WANGZhiwei, et al. Development Status and Implementation Path Analysis on Intelligent Construction of Mountain Tunnels in China [J]. Journal of the China Railway Society, 2022, 44 (1): 134-142. in Chinese
[43]
NAVARROJ, SANCHIDRIÁNJ A, SEGARRAP, et al. Detection of Potential Overbreak Zones in Tunnel Blasting from MWD Data [J]. Tunnelling and Underground Space Technology Incorporating Trenchless Technology Research, 2018, 82: 504-516.
[44]
GHOSHR, DANIELSSONM, GUSTAFSONA, et al. Assessment of Rock Mass Quality Using Drill Monitoring Technique for Hydraulic ITH Drills [J]. International Journal of Mining and Mineral Engineering, 2017, 8 (3): 169-186.
[45]
VAN ELDERTJ, SCHUNNESSONH, SAIANGD, et al. Improved Filtering and Normalizing of Measurement-while-Drilling (MWD) Data in Tunnel Excavation [J]. Tunnelling and Underground Space Technology, 2020, 103: 103467.
[46]
BREIMANL. Random Forests: Random Features [J]. Machine Learning, 2001, 45 (1): 5-32.
SONGShufang, HERuyang. Importance Measure Index System Based on Random Forest [J]. Journal of National University of Defense Technology, 2021, 43 (2): 25-32. in Chinese
[49]
ZHAOS G, WANGM N, YIW H, et al. Intelligent Classification of Surrounding Rock of Tunnel Based on 10 Machine Learning Algorithms [J]. Applied Sciences, 2022, 12 (5): 2656.
[50]
PANX Y, JIAR, HUANGJ H, et al. A Resistance Outlier Sampling Algorithm for Imbalanced Data Prediction [J]. Intelligent Data Analysis, 26 (3): 583-598.
[51]
JAHANDAD, SAMS M, KAMARDINK, et al. Offline Signature Verification Using Deep Learning Convolutional Neural Network (CNN) Architectures GoogLeNet Inception-V1 and Inception-V3 [J]. Procedia Computer Science, 2019, 161: 475-483.
LIYang, ZHAOMing, XUMengyao, et al. A Survey of Research on Multi-Source Information Fusion Technology [J]. Intelligent Computer and Applications, 2019, 9 (5): 186-189. in Chinese
WANGZhongtian, XUMinyi, YOUDongfang, et al. Comparison on Classification Performance between Random Forest and Deep Forest [J]. Chinese Journal of Health Statistics, 2023, 40 (3): 349-353. in Chinese
TANGZhili, XUQianjun. Rockburst Prediction Based on Nine Machine Learning Algorithms [J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39 (4): 773-781. in Chinese