Soft computing techniques are becoming even more popular and particularly amenable to model the complex behaviors of most geotechnical engineering systems since they have demonstrated superior predictive capacity,comp...Soft computing techniques are becoming even more popular and particularly amenable to model the complex behaviors of most geotechnical engineering systems since they have demonstrated superior predictive capacity,compared to the traditional methods.This paper presents an overview of some soft computing techniques as well as their applications in underground excavations.A case study is adopted to compare the predictive performances of soft computing techniques including eXtreme Gradient Boosting(XGBoost),Multivariate Adaptive Regression Splines(MARS),Artificial Neural Networks(ANN),and Support Vector Machine(SVM) in estimating the maximum lateral wall deflection induced by braced excavation.This study also discusses the merits and the limitations of some soft computing techniques,compared with the conventional approaches available.展开更多
In the design of geotechnical infrastructure,engineers have to deal with naturally occurring soils and rocks which are subjected to spatial variability as well as other uncertainties such as errors in measurement and ...In the design of geotechnical infrastructure,engineers have to deal with naturally occurring soils and rocks which are subjected to spatial variability as well as other uncertainties such as errors in measurement and in modeling methods.Reliability assessment which provides a systematic approach for quantifying the risk of failure has been shown to be a promising tool for solving these challenging geotechnical engineering problems.The method provides a more consistent measure of the level of safety or“structural reliability”through the evaluation of a reliability index and the associated“failure”probability,and is a method that satisfies the need to clearly convey safety issues to the public and regulatory authorities.Various methods for calculating the reliability of geotechnical infrastructures with regard to the assessment of the ultimate and serviceability limit states have been proposed by many researchers and these approaches include:the direct Monte Carlo Simulation,Bayesian and other sampling techniques,the first-order reliability method and the second-order reliability method,the random field method,the response surface method and other surrogate models with the related probabilistic procedures.In this special issue of Geoscience Frontiers,we assemble eleven invited papers which provide insights on the latest developments and challenges in applying probabilistic and reliability methods to geotechnical infrastructure design.展开更多
基金supported by High-end Foreign Expert Introduction program (No.G20190022002)Chongqing Construction Science and Technology Plan Project (2019-0045)
文摘Soft computing techniques are becoming even more popular and particularly amenable to model the complex behaviors of most geotechnical engineering systems since they have demonstrated superior predictive capacity,compared to the traditional methods.This paper presents an overview of some soft computing techniques as well as their applications in underground excavations.A case study is adopted to compare the predictive performances of soft computing techniques including eXtreme Gradient Boosting(XGBoost),Multivariate Adaptive Regression Splines(MARS),Artificial Neural Networks(ANN),and Support Vector Machine(SVM) in estimating the maximum lateral wall deflection induced by braced excavation.This study also discusses the merits and the limitations of some soft computing techniques,compared with the conventional approaches available.
文摘In the design of geotechnical infrastructure,engineers have to deal with naturally occurring soils and rocks which are subjected to spatial variability as well as other uncertainties such as errors in measurement and in modeling methods.Reliability assessment which provides a systematic approach for quantifying the risk of failure has been shown to be a promising tool for solving these challenging geotechnical engineering problems.The method provides a more consistent measure of the level of safety or“structural reliability”through the evaluation of a reliability index and the associated“failure”probability,and is a method that satisfies the need to clearly convey safety issues to the public and regulatory authorities.Various methods for calculating the reliability of geotechnical infrastructures with regard to the assessment of the ultimate and serviceability limit states have been proposed by many researchers and these approaches include:the direct Monte Carlo Simulation,Bayesian and other sampling techniques,the first-order reliability method and the second-order reliability method,the random field method,the response surface method and other surrogate models with the related probabilistic procedures.In this special issue of Geoscience Frontiers,we assemble eleven invited papers which provide insights on the latest developments and challenges in applying probabilistic and reliability methods to geotechnical infrastructure design.
