Underground geotechnical engineering encounters persistent challenges in ensuring the stability and safety of surrounding rock structures, particularly within rocky tunnels. Rock reinforcement techniques, including th...Underground geotechnical engineering encounters persistent challenges in ensuring the stability and safety of surrounding rock structures, particularly within rocky tunnels. Rock reinforcement techniques, including the use of steel mesh, are critical to achieving this goal. However, there exists a knowledge gap regarding the comprehensive understanding of the mechanical behavior and failure mechanisms exhibited by steel mesh under diverse loading conditions. This study thoroughly explored the steel mesh's performance throughout the entire loading-failure process, innovating with detailed analysis and modeling techniques. By integrating advanced numerical modeling with laboratory experiments, the study examines the influence of varying reinforcement levels and geometric parameters on the steel mesh strength and deformation characteristics. Sensitivity analysis, employing gray correlation theory, identifies the key factors affecting the mesh performance, while a BP (Backpropagation) neural network model predicts maximum vertical deformation with high accuracy. The findings underscore the critical role of steel diameter and mesh spacing in optimizing peak load capacity, displacement, and energy absorption, offering practical guidelines for design improvements. The use of a Bayesian Regularization (BR) algorithm further enhances the predictive accuracy compared to traditional methods. This research provides new insights into optimizing steel mesh design for underground applications, offering an innovative approach to enhancing structural safety in geotechnical projects.展开更多
基金funded by the National Natural Science Foundation of China(Grant No.52178396).
文摘Underground geotechnical engineering encounters persistent challenges in ensuring the stability and safety of surrounding rock structures, particularly within rocky tunnels. Rock reinforcement techniques, including the use of steel mesh, are critical to achieving this goal. However, there exists a knowledge gap regarding the comprehensive understanding of the mechanical behavior and failure mechanisms exhibited by steel mesh under diverse loading conditions. This study thoroughly explored the steel mesh's performance throughout the entire loading-failure process, innovating with detailed analysis and modeling techniques. By integrating advanced numerical modeling with laboratory experiments, the study examines the influence of varying reinforcement levels and geometric parameters on the steel mesh strength and deformation characteristics. Sensitivity analysis, employing gray correlation theory, identifies the key factors affecting the mesh performance, while a BP (Backpropagation) neural network model predicts maximum vertical deformation with high accuracy. The findings underscore the critical role of steel diameter and mesh spacing in optimizing peak load capacity, displacement, and energy absorption, offering practical guidelines for design improvements. The use of a Bayesian Regularization (BR) algorithm further enhances the predictive accuracy compared to traditional methods. This research provides new insights into optimizing steel mesh design for underground applications, offering an innovative approach to enhancing structural safety in geotechnical projects.
