Reliability‐Based Geotechnical Design Method Using the Gaussian Process Regression–Based Differential Evolution Algorithm DOI Creative Commons
Kun‐Li Wen, Zhicong Kuang, Wei Zeng

et al.

Advances in Civil Engineering, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

A fundamental challenge in reliability‐based geotechnical design is optimizing cost‐effectiveness while adhering to a predefined failure probability target. Traditionally, assessed via Monte Carlo simulation (MCS), which, despite its accuracy, often prohibitively time‐consuming and expensive. This scenario frames as constrained optimization problem (COP) characterized by low‐cost objective high‐cost constraints. Recent advancements have seen the application of Gaussian process regression (GPR) enhanced evolutionary algorithms (EAs) for managing COPs where both objectives constraints incur significant expenses. However, methodologies adept at handling with inexpensive yet costly remain underexplored. paper introduces novel approach utilizing GPR–based differential evolution (DE) algorithm designed specifically this cost disparity. Here, GPR serves surrogate model estimate actual performance derived from MCS assessments. The innovative use expected improvement (EI) selection criterion potential solutions key feature method. EI quantitatively evaluates each candidate’s enhance economic efficiency safety reliability, effectively converting COP into single‐objective (SOOP). We demonstrate efficacy our proposed DE through case study Sau Mau Ping rock slope Hong Kong, highlighting method’s ability achieve superior accuracy substantial computational savings.

Language: Английский

Reconstruction and prediction of tunnel surrounding rock deformation data based on PSO optimized LSSVR and GPR models DOI Creative Commons

Zhenqian Huang,

Zhen Huang,

Pengtao An

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103445 - 103445

Published: Nov. 1, 2024

Language: Английский

Citations

4

Efficient kriging-based wall deflection prediction in braced excavation considering model and measurement errors DOI
Xiong Xiao, Quanwang Li, Hao Zhang

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 149, P. 110506 - 110506

Published: March 14, 2025

Language: Английский

Citations

0

Probabilistic analysis of tunnel deformation and ground surface settlement induced by surcharge in spatially variable soil DOI
Han Han, Wengang Zhang, Zhihao Wu

et al.

Computers and Geotechnics, Journal Year: 2025, Volume and Issue: 186, P. 107369 - 107369

Published: May 31, 2025

Language: Английский

Citations

0

Hybrid and multiple ensemble metamodel-based evaluation for operating tunnel performance in three-dimensional spatially variable soils DOI
Ning Tian, Jinsong Huang, Jian Chen

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 156, P. 111321 - 111321

Published: June 3, 2025

Language: Английский

Citations

0

Lateral Convergence Deformation Prediction of Subway Shield Tunnel Based on Kalman Model DOI Open Access
Yan Bao, Yexin Zheng, Chao Tang

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(7), P. 2798 - 2798

Published: March 27, 2024

In order to optimize the structure of a subway shield tunnel, minimize injuries, and avoid potential safety hazards, lateral convergence deformation tunnels should be predicted. terms accuracy stability, existing prediction models perform poorly in obtaining value non-stationary small-sized sample tunnel. this paper, model tunnel based on Kalman algorithm is constructed filtering theory. The efficient, adaptive, robust can accurately predict Taking horizontal diameter 200-ring segment interval section as an example, we have proved that residuals are small, residual distribution conforms normal distribution, effect great. suitable for more than five periods data, improves with increase number data periods. addition, compare GM(1,1) GM–Markov model, RMSE, NRMSE, MAPE, R2 used evaluation indices. results show has higher predicting

Language: Английский

Citations

2

Reliability‐Based Geotechnical Design Method Using the Gaussian Process Regression–Based Differential Evolution Algorithm DOI Creative Commons
Kun‐Li Wen, Zhicong Kuang, Wei Zeng

et al.

Advances in Civil Engineering, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

A fundamental challenge in reliability‐based geotechnical design is optimizing cost‐effectiveness while adhering to a predefined failure probability target. Traditionally, assessed via Monte Carlo simulation (MCS), which, despite its accuracy, often prohibitively time‐consuming and expensive. This scenario frames as constrained optimization problem (COP) characterized by low‐cost objective high‐cost constraints. Recent advancements have seen the application of Gaussian process regression (GPR) enhanced evolutionary algorithms (EAs) for managing COPs where both objectives constraints incur significant expenses. However, methodologies adept at handling with inexpensive yet costly remain underexplored. paper introduces novel approach utilizing GPR–based differential evolution (DE) algorithm designed specifically this cost disparity. Here, GPR serves surrogate model estimate actual performance derived from MCS assessments. The innovative use expected improvement (EI) selection criterion potential solutions key feature method. EI quantitatively evaluates each candidate’s enhance economic efficiency safety reliability, effectively converting COP into single‐objective (SOOP). We demonstrate efficacy our proposed DE through case study Sau Mau Ping rock slope Hong Kong, highlighting method’s ability achieve superior accuracy substantial computational savings.

Language: Английский

Citations

0