This paper introduces an intelligent framework for predicting the advancing speed during earth pressure balance(EPB)shield tunnelling.Five artificial intelligence(AI)models based on machine and deep learning technique...This paper introduces an intelligent framework for predicting the advancing speed during earth pressure balance(EPB)shield tunnelling.Five artificial intelligence(AI)models based on machine and deep learning techniques-back-propagation neural network(BPNN),extreme learning machine(ELM),support vector machine(SVM),long-short term memory(LSTM),and gated recurrent unit(GRU)-are used.Five geological and nine operational parameters that influence the advancing speed are considered.A field case of shield tunnelling in Shenzhen City,China is analyzed using the developed models.A total of 1000 field datasets are adopted to establish intelligent models.The prediction performance of the five models is ranked as GRU>LSTM>SVM>ELM>BPNN.Moreover,the Pearson correlation coefficient(PCC)is adopted for sensitivity analysis.The results reveal that the main thrust(MT),penetration(P),foam volume(FV),and grouting volume(GV)have strong correlations with advancing speed(AS).An empirical formula is constructed based on the high-correlation influential factors and their corresponding field datasets.Finally,the prediction performances of the intelligent models and the empirical method are compared.The results reveal that all the intelligent models perform better than the empirical method.展开更多
Proper regulation of the earth pressure on the bulkhead of earth-pressure balanced(EPB)shield tunneling machines is significant to ensure safe construction.This study proposes a procedure for regulating the bulkhead p...Proper regulation of the earth pressure on the bulkhead of earth-pressure balanced(EPB)shield tunneling machines is significant to ensure safe construction.This study proposes a procedure for regulating the bulkhead pressure by combining numerical simulations and data mining,and applies the procedure to a metro line constructed in sandy pebble stratum using EPB shield.Firstly,the relationship between the bulkhead pressure and the pressure on the tunnel face is carefully obtained from discrete element modeling,and the required supporting earth pressure is derived by considering the arching effect.Secondly,aided with the machine learning method,a model is constructed for predicting the average bulkhead pressure per ring according to the operational parameters(i.e.,the average driving speed and the rotation speed of the screw conveyor).Given the target value of the bulkhead pressure,the optimal values of the operational parameters are obtained from the model.In addition,an autoregressive moving average stochastic process model is developed to monitor the real-time fluctuation of the bulkhead pressure and guide the actions taken in time to avoid dramatic fluctuations.The results indicate that the pressure difference between the tunnel face and the bulkhead is considerable,and the consideration of the arching effect can avoid overestimating the bulkhead pressure.A combination of the machine learning model and the stochastic process model provides a plausible performance in regulating the bulkhead pressure around the target value without dramatic fluctuation.展开更多
Cutterhead torque is a crucial parameter for the design and operation of earth pressure balance （EPB） shield tunneling machine. However, the traditional calculation models of cutterhead torque are too rough or exist...Cutterhead torque is a crucial parameter for the design and operation of earth pressure balance （EPB） shield tunneling machine. However, the traditional calculation models of cutterhead torque are too rough or exist gross errors under variable geological conditions. In order to improve the precision of the calculation model of cutterhead torque, dynamic operation parameters are considered and a new model is proposed. Experiment is carried out on a ~1.8 m shield machine test rig and the calculating re- sult with the new model is compared with the experimental data to verify the validity of the new model. The relative error of the new model is as low as 4% at smooth stage and is reduced to 5% at the end of trembling stage. Based on the results of the new model and the test data obtained from the 001.8 m test rig and the construction site, the inner relationships between several operation parameters and cutterhead torque are investigated and some quantitative conclusions are obtained.展开更多
基金funded by“The Pearl River Talent Recruitment Program”in 2019(Grant No.2019CX01G338),。
文摘This paper introduces an intelligent framework for predicting the advancing speed during earth pressure balance(EPB)shield tunnelling.Five artificial intelligence(AI)models based on machine and deep learning techniques-back-propagation neural network(BPNN),extreme learning machine(ELM),support vector machine(SVM),long-short term memory(LSTM),and gated recurrent unit(GRU)-are used.Five geological and nine operational parameters that influence the advancing speed are considered.A field case of shield tunnelling in Shenzhen City,China is analyzed using the developed models.A total of 1000 field datasets are adopted to establish intelligent models.The prediction performance of the five models is ranked as GRU>LSTM>SVM>ELM>BPNN.Moreover,the Pearson correlation coefficient(PCC)is adopted for sensitivity analysis.The results reveal that the main thrust(MT),penetration(P),foam volume(FV),and grouting volume(GV)have strong correlations with advancing speed(AS).An empirical formula is constructed based on the high-correlation influential factors and their corresponding field datasets.Finally,the prediction performances of the intelligent models and the empirical method are compared.The results reveal that all the intelligent models perform better than the empirical method.
基金supported by the National Natural ScienceFoundation of China(Grant No.41672360)Science and Technology Commission of Shanghai Munici-pality(Grant No.17DZ1203800)Shanghai Shentong Metro Group Co.,Ltd.(Grant No.17DZ1203804).
文摘Proper regulation of the earth pressure on the bulkhead of earth-pressure balanced(EPB)shield tunneling machines is significant to ensure safe construction.This study proposes a procedure for regulating the bulkhead pressure by combining numerical simulations and data mining,and applies the procedure to a metro line constructed in sandy pebble stratum using EPB shield.Firstly,the relationship between the bulkhead pressure and the pressure on the tunnel face is carefully obtained from discrete element modeling,and the required supporting earth pressure is derived by considering the arching effect.Secondly,aided with the machine learning method,a model is constructed for predicting the average bulkhead pressure per ring according to the operational parameters(i.e.,the average driving speed and the rotation speed of the screw conveyor).Given the target value of the bulkhead pressure,the optimal values of the operational parameters are obtained from the model.In addition,an autoregressive moving average stochastic process model is developed to monitor the real-time fluctuation of the bulkhead pressure and guide the actions taken in time to avoid dramatic fluctuations.The results indicate that the pressure difference between the tunnel face and the bulkhead is considerable,and the consideration of the arching effect can avoid overestimating the bulkhead pressure.A combination of the machine learning model and the stochastic process model provides a plausible performance in regulating the bulkhead pressure around the target value without dramatic fluctuation.
基金supported by the National Basic Research Program ("973"Program) of China (Grant No. 2007CB714004)
文摘Cutterhead torque is a crucial parameter for the design and operation of earth pressure balance （EPB） shield tunneling machine. However, the traditional calculation models of cutterhead torque are too rough or exist gross errors under variable geological conditions. In order to improve the precision of the calculation model of cutterhead torque, dynamic operation parameters are considered and a new model is proposed. Experiment is carried out on a ~1.8 m shield machine test rig and the calculating re- sult with the new model is compared with the experimental data to verify the validity of the new model. The relative error of the new model is as low as 4% at smooth stage and is reduced to 5% at the end of trembling stage. Based on the results of the new model and the test data obtained from the 001.8 m test rig and the construction site, the inner relationships between several operation parameters and cutterhead torque are investigated and some quantitative conclusions are obtained.
