Face stability is one of the essential problems in shield tunneling.When tunneling in cobble stratum or mixed face ground conditions,significant cutting-induced cutterhead vibration would occur and affect the face sta...Face stability is one of the essential problems in shield tunneling.When tunneling in cobble stratum or mixed face ground conditions,significant cutting-induced cutterhead vibration would occur and affect the face stability.To reveal the mechanism and effect of vibration on the tunnel face stability,a transparent tunnel model with a movable vibration exciter was designed and a series of model tests were performed under different vibration magnitudes Aa and frequencies f.Meanwhile,particle image velocimetry was used to reveal the displacement field and the failure pattern of the tunnel face.The test results indicate that the cutting-induced vibration produces a significant reduction effect on the tunnel face stability,as expressed by the increase of the face support pressure and the failure zone when the vibration magnitude and frequency increase.Compared with the static unloading conditions,the width of the failure wedge Lwt increased by about 5.75%and 35.66%for the loose and dense sand,respectively,under dynamic unloading conditions(Aa=0.2g,f=10 Hz).The limit support pressure increased up to about 0.20γD at a vibration of 0.3g and 50 Hz,much larger than those of static conditions,which were about 0.08γD–0.09γD.An observable self-stabilizing arch can be formed in dense sand under static unloading conditions,while under dynamic unloading conditions,the long-time stable soil arch would not occur.The contributions of this paper could provide an insightful understanding of the effects of cutterhead vibration on tunnel face stability.展开更多
The moving trajectory of the pipe-jacking machine(PJM),which primarily determines the end quality of jacked tunnels,must be controlled strictly during the entire jacking process.Developing prediction models to support...The moving trajectory of the pipe-jacking machine(PJM),which primarily determines the end quality of jacked tunnels,must be controlled strictly during the entire jacking process.Developing prediction models to support drivers in performing rectifications in advance can effectively avoid considerable trajectory deviations from the designed jacking axis.Hence,a gated recurrent unit(GRU)-based deep learning framework is proposed herein to dynamically predict the moving trajectory of the PJM.In this framework,operational data are first extracted from a data acquisition system;subsequently,they are preprocessed and used to establish GRU-based multivariate multistep-ahead direct prediction models.To verify the performance of the proposed framework,a case study of a large pipe-jacking project in Shanghai and comparisons with other conventional models(i.e.,long short-term memory(LSTM)network and recurrent neural network(RNN))are conducted.In addition,the effects of the activation function and input time-step length on the prediction performance of the proposed framework are investigated and discussed.The results show that the proposed framework can dynamically and precisely predict the PJM moving trajectory during the pipe-jacking process,with a minimum mean absolute error and root mean squared error(RMSE)of 0.1904 and 0.5011 mm,respectively.The RMSE of the GRU-based models is lower than those of the LSTM-and RNN-based models by 21.46%and 46.40%at the maximum,respectively.The proposed framework is expected to provide an effective decision support for moving trajectory control and serve as a foundation for the application of deep learning in the automatic control of pipe jacking.展开更多
基金funded by the National Key R&D Program of China(Grant No.2022YFB2602200)National Natural Science Foundation of China(Grant No.52308412)+1 种基金China Postdoctoral Science Foundation(Grant No.2023M732668)Shanghai Postdoctoral Excellence Program(2022553).
文摘Face stability is one of the essential problems in shield tunneling.When tunneling in cobble stratum or mixed face ground conditions,significant cutting-induced cutterhead vibration would occur and affect the face stability.To reveal the mechanism and effect of vibration on the tunnel face stability,a transparent tunnel model with a movable vibration exciter was designed and a series of model tests were performed under different vibration magnitudes Aa and frequencies f.Meanwhile,particle image velocimetry was used to reveal the displacement field and the failure pattern of the tunnel face.The test results indicate that the cutting-induced vibration produces a significant reduction effect on the tunnel face stability,as expressed by the increase of the face support pressure and the failure zone when the vibration magnitude and frequency increase.Compared with the static unloading conditions,the width of the failure wedge Lwt increased by about 5.75%and 35.66%for the loose and dense sand,respectively,under dynamic unloading conditions(Aa=0.2g,f=10 Hz).The limit support pressure increased up to about 0.20γD at a vibration of 0.3g and 50 Hz,much larger than those of static conditions,which were about 0.08γD–0.09γD.An observable self-stabilizing arch can be formed in dense sand under static unloading conditions,while under dynamic unloading conditions,the long-time stable soil arch would not occur.The contributions of this paper could provide an insightful understanding of the effects of cutterhead vibration on tunnel face stability.
基金supported by the National Natural Science Foundation of China(Grant No.52090082)the Natural Science Foundation of Shandong Province,China(No.ZR202103010505)Fundamental Research Funds for the Central Universities of China(No.22120210428).
文摘The moving trajectory of the pipe-jacking machine(PJM),which primarily determines the end quality of jacked tunnels,must be controlled strictly during the entire jacking process.Developing prediction models to support drivers in performing rectifications in advance can effectively avoid considerable trajectory deviations from the designed jacking axis.Hence,a gated recurrent unit(GRU)-based deep learning framework is proposed herein to dynamically predict the moving trajectory of the PJM.In this framework,operational data are first extracted from a data acquisition system;subsequently,they are preprocessed and used to establish GRU-based multivariate multistep-ahead direct prediction models.To verify the performance of the proposed framework,a case study of a large pipe-jacking project in Shanghai and comparisons with other conventional models(i.e.,long short-term memory(LSTM)network and recurrent neural network(RNN))are conducted.In addition,the effects of the activation function and input time-step length on the prediction performance of the proposed framework are investigated and discussed.The results show that the proposed framework can dynamically and precisely predict the PJM moving trajectory during the pipe-jacking process,with a minimum mean absolute error and root mean squared error(RMSE)of 0.1904 and 0.5011 mm,respectively.The RMSE of the GRU-based models is lower than those of the LSTM-and RNN-based models by 21.46%and 46.40%at the maximum,respectively.The proposed framework is expected to provide an effective decision support for moving trajectory control and serve as a foundation for the application of deep learning in the automatic control of pipe jacking.
