<<
[an error occurred while processing this directive] | [an error occurred while processing this directive] >>
Calculation of Horizontal Convergence Safety Factor for Tunnels in Spatially Variable Soil Based on Deep Learning
(1. Anhui Transportation Holding Construction Management Co., Ltd, Hefei 230000; 2. College of Civil Engineering, Tongji University, Shanghai 200092; 3. Engineering Research Center of Civil-informatics, Ministry of Education, Shanghai 200092; 4. Key Laboratory of Geotechnical and Underground Engineering of the Ministry of Education, Shanghai 200092)
Abstract To improve the efficiency of using the random finite element method (RFEM) for calculating the safety factor of tunnel horizontal convergence in spatially variable soil, a spatial attention-convolutional neural network(SA-CNN) is proposed as a surrogate model for RFEM. This surrogate model takes spatially variable soil parameters as input and the tunnel horizontal convergence safety factor as output, learning the relationship between soil parameter random fields and the tunnel safety factor from a limited number of RFEM samples. It then replaces the RFEM method for calculating safety factors on larger samples. Tested on a Shanghai metro tunnel, the model shows a relative error of less than 2% compared to RFEM, with MAPE, RMSE, and MAE values below 10%, 0.12, and 0.10 respectively, and R2 above 0.8, meeting engineering accuracy requirements. Additionally, the calculation efficiency of the surrogate model is approximately 880 times higher than RFEM.
Abstract：
To improve the efficiency of using the random finite element method (RFEM) for calculating the safety factor of tunnel horizontal convergence in spatially variable soil, a spatial attention-convolutional neural network(SA-CNN) is proposed as a surrogate model for RFEM. This surrogate model takes spatially variable soil parameters as input and the tunnel horizontal convergence safety factor as output, learning the relationship between soil parameter random fields and the tunnel safety factor from a limited number of RFEM samples. It then replaces the RFEM method for calculating safety factors on larger samples. Tested on a Shanghai metro tunnel, the model shows a relative error of less than 2% compared to RFEM, with MAPE, RMSE, and MAE values below 10%, 0.12, and 0.10 respectively, and R2 above 0.8, meeting engineering accuracy requirements. Additionally, the calculation efficiency of the surrogate model is approximately 880 times higher than RFEM.
LI Zhanfu1 ZHANG Yu2 WANG Jun1 LV Yanyun2,
3 RUI Yi2,
3 etc
.Calculation of Horizontal Convergence Safety Factor for Tunnels in Spatially Variable Soil Based on Deep Learning[J] MODERN TUNNELLING TECHNOLOGY, 2024,V61(5): 88-98
2024, Vol. 61 