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

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 itself.In this study,deep recurrent neural networks(RNNs) and convolutional neural networks(CNNs) were used for vibration-based working face ground identification.First,field monitoring was conducted to obtain the TBM vibration data when tunneling in changing geological conditions,including mixed-face,homogeneous,and transmission ground.Next,RNNs and CNNs were utilized to develop vibration-based prediction models,which were then validated using the testing dataset.The 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 transformation.The CNN models,with an accuracy greater than 96%,performed significantly better than the RNN models.The ResNet-18,with an accuracy of 98.28%,performed the best.When 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 efficiency.The 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.

Numerical and analytical studies on the coupling effects of unloading and cutterhead vibration on tunnel face in dry sandy ground

When tunnelling in difficult ground conditions,shield machine would inevitably produce significant ground loss and vibration,which may disturb the ground ahead of the tunnel face.In this paper,discrete element models calibrated by model tests were established to investigate the response of tunnel face under the coupling effects of unloading and cutterhead vibrations.The results show that the friction angle reduction under cyclic loading and vibration attenuation in the sandy ground are significant and can be estimated by the fitted exponential functions.Under cutterhead vibration,the tunnel face stability is undermined and the limit support pressure(LSP)increases to 1.4 times as that in the static case with the growth of frequency and amplitude.Meanwhile,the loosening zone becomes wider and the arching effect is weakened with the reduction of peak horizontal stress and the increase of vertical stress above the tunnel.Based on the numerical results,a pseudo-static method was introduced into the limit equilibrium analysis of the wedge-prism model for calculating the LSP under vibration.With an error rate less than 5.2%,the proposed analytical method is well validated.Further analytical calculation reveals that the LSP would increase with the growth of vibration amplitude,vibration frequency and covered depth but decrease with the increase of friction angle.This study can not only lay a solid foundation for the further investigation of ground loss,ground water and soft-hard heterogeneous ground under cutterhead vibration,but also provide meaningful references for the control of environmental disturbance in practice.