Abstract In order to accurately predict the surrounding rock deformation during construction of soft rock tunnel, the soft rock tunnel crown settlement and horizontal convergence prediction model has been created by using the long short-term memory (LSTM) neural network, the hyper-parameters of LSTM model have been optimized by using the sparrow search algorithm (SSA), and the calculation process framework for SSA-LSTM has been created. With the soft rock section of Liangwangshan Tunnel being used as an example, field measurement and analysis of large deformation of surrounding rock have been conducted. The crown settlement and horizontal convergence monitoring data is obtained and then substituted into the SSA-LSTM model for calculation. The calculation results are compared against the results of LSTM model and the SSA optimized traditional machine learning model and the errors are analyzed. As the results indicate: the relative error rate of SSA-LSTM model is [-1%, 2%], R2 is 0.998 6, MAPE is 2.345 8%, RMSE is 0.529 8, and this model is the best one of all the models. In order to verify the settlement and deformation of unexcavated section predicted by the SSA-LSTM model, the K33+260 section is used as the object ofstudy and the prediction model for settlement and deformation of unexcavated section is created. According to the results of error analysis, the prediction accuracy of the model is good enough to guide construction.
Abstract：
In order to accurately predict the surrounding rock deformation during construction of soft rock tunnel, the soft rock tunnel crown settlement and horizontal convergence prediction model has been created by using the long short-term memory (LSTM) neural network, the hyper-parameters of LSTM model have been optimized by using the sparrow search algorithm (SSA), and the calculation process framework for SSA-LSTM has been created. With the soft rock section of Liangwangshan Tunnel being used as an example, field measurement and analysis of large deformation of surrounding rock have been conducted. The crown settlement and horizontal convergence monitoring data is obtained and then substituted into the SSA-LSTM model for calculation. The calculation results are compared against the results of LSTM model and the SSA optimized traditional machine learning model and the errors are analyzed. As the results indicate: the relative error rate of SSA-LSTM model is [-1%, 2%], R2 is 0.998 6, MAPE is 2.345 8%, RMSE is 0.529 8, and this model is the best one of all the models. In order to verify the settlement and deformation of unexcavated section predicted by the SSA-LSTM model, the K33+260 section is used as the object ofstudy and the prediction model for settlement and deformation of unexcavated section is created. According to the results of error analysis, the prediction accuracy of the model is good enough to guide construction.
WANG Feng
.Study on Intelligent Prediction of the Deformation Characteristics of Soft Rock Tunnel Based on SSA-LSTM Model and Its Application[J] MODERN TUNNELLING TECHNOLOGY, 2024,V61(1): 56-66
2024, Vol. 61 