Tunnel boring machine vibration-based deep learning for the ground identification of working faces

作     者：Mengbo Liu Shaoming Liao Yifeng Yang Yanqing Men Junzuo He Yongliang Huang Mengbo Liu;Shaoming Liao;Yifeng Yang;Yanqing Men;Junzuo He;Yongliang Huang

作者机构：Department of Geotechnical EngineeringTongji UniversityShanghai200092China Jinan Rail Transit Group Co.Ltd.Jinan250101China 

出 版 物：《Journal of Rock Mechanics and Geotechnical Engineering》 (岩石力学与岩土工程学报（英文版）)

年 卷 期：2021年第13卷第6期

页      面：1340-1357页

核心收录：

学科分类：081406[工学-桥梁与隧道工程] 08[工学] 0814[工学-土木工程] 082301[工学-道路与铁道工程] 0823[工学-交通运输工程] 

基　　金：supported by the National Natural Science Foundation of China(Grant No.52090082) the Natural Science Foundation of Shandong Province,China(Grant No.ZR2020ME243) the Shanghai Committee of Science and Technology(Grant No.19511100802) 

主　　题：Deep learning Transfer learning Convolutional neural network(CNN) Recurrent neural network(RNN) Ground detection Tunnel boring machine(TBM)vibration Mixed-face ground 

摘      要：Tunnel boring machine(TBM) vibration induced by cutting complex ground contains essential information that can help engineers evaluate the interaction between a cutterhead and the ground *** this study,deep recurrent neural networks(RNNs) and convolutional neural networks(CNNs) were used for vibration-based working face ground ***,field monitoring was conducted to obtain the TBM vibration data when tunneling in changing geological conditions,including mixed-face,homogeneous,and transmission ***,RNNs and CNNs were utilized to develop vibration-based prediction models,which were then validated using the testing *** accuracy of the long short-term memory(LSTM) and bidirectional LSTM(Bi-LSTM) models was approximately 70% with raw data;however,with instantaneous frequency transmission,the accuracy increased to approximately 80%.Two types of deep CNNs,GoogLeNet and ResNet,were trained and tested with time-frequency scalar diagrams from continuous wavelet *** CNN models,with an accuracy greater than 96%,performed significantly better than the RNN *** ResNet-18,with an accuracy of 98.28%,performed the *** the sample length was set as the cutterhead rotation period,the deep CNN and RNN models achieved the highest accuracy while the proposed deep CNN model simultaneously achieved high prediction accuracy and feedback *** proposed model could promptly identify the ground conditions at the working face without stopping the normal tunneling process,and the TBM working parameters could be adjusted and optimized in a timely manner based on the predicted results.