Abstract
The convergence-confinement method (CCM) is an important approach to analysis the rock-support interaction and to design tunnel and its support. To make an effort on efficient reliability analysis of tunnels integrated with CCM, of which performance functions are mostly highly nonlinear and implicit, a hybrid intelligent algorithm combing uniform design (UD) and Gaussian process regression (GPR) is proposed. Based on the generated UD samples, GPR-parameter metamodels to predict the important parameters of CCM and GPR-probability metamodels to approximate the real performance functions are constructed consequently. Then sensitivity analysis, determination of the optimal preliminary support timing and failure probabilities calculations can be performed in conjunction with Monte Carlo simulation (MCS) based on the constructed GPR-parameter metamodels and GPR-probability metamodels. To verify the efficiency and accuracy of the proposed method, a typical circle tunnel is analyzed and good results are achieved. Finally, a practical hydraulic tunnel is analyzed using the proposed method and some beneficial conclusions are drawn.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
