Compression index Ccis an essential parameter in geotechnical design for which the effectiveness of correlation is still a challenge.This paper suggests a novel modelling approach using machine learning(ML)technique.T...Compression index Ccis an essential parameter in geotechnical design for which the effectiveness of correlation is still a challenge.This paper suggests a novel modelling approach using machine learning(ML)technique.The performance of five commonly used machine learning(ML)algorithms,i.e.back-propagation neural network(BPNN),extreme learning machine(ELM),support vector machine(SVM),random forest(RF)and evolutionary polynomial regression(EPR)in predicting Cc is comprehensively investigated.A database with a total number of 311 datasets including three input variables,i.e.initial void ratio e0,liquid limit water content wL,plasticity index Ip,and one output variable Cc is first established.Genetic algorithm(GA)is used to optimize the hyper-parameters in five ML algorithms,and the average prediction error for the 10-fold cross-validation(CV)sets is set as thefitness function in the GA for enhancing the robustness of ML models.The results indicate that ML models outperform empirical prediction formulations with lower prediction error.RF yields the lowest error followed by BPNN,ELM,EPR and SVM.If the ranges of input variables in the database are large enough,BPNN and RF models are recommended to predict Cc.Furthermore,if the distribution of input variables is continuous,RF model is the best one.Otherwise,EPR model is recommended if the ranges of input variables are small.The predicted correlations between input and output variables using five ML models show great agreement with the physical explanation.展开更多
The assessment of the wave-induced soil liquefaction plays a key role in the geotechnical design for offshore foundations. The underlying shortcomings of the existing momentary liquefaction criteria are identified and...The assessment of the wave-induced soil liquefaction plays a key role in the geotechnical design for offshore foundations. The underlying shortcomings of the existing momentary liquefaction criteria are identified and clarified by mechanism analyses and the recent field observations. A modified criterion for the wave-induced momentary liquefaction of a sandy seabed is given to describe the vertical pore- pressure distributions. An improved approximation of the momentary liquefaction depth is further presented. Parametric study of the effects of the saturation degree of soils indicates that this modification is significant for the evaluation of wave-induced momentary liauefaction.展开更多
As the offshore industries move from shallow to deep waters in excess of 1000 m, there has been rapid development of ocean engineering practices. Innovations in theoretical and applied me- chanics have been essential ...As the offshore industries move from shallow to deep waters in excess of 1000 m, there has been rapid development of ocean engineering practices. Innovations in theoretical and applied me- chanics have been essential in this shift and in underpinning the exploitation of offshore oil and gas and renewable energy re- sources worldwide. Understanding and predicting physical mech- anisms of structure-soil interactions are vital for the stability and safety of offshore engineering structures. Accordingly, in this spe- cial issue of Theoretical & Applied Mechanics Letters (TAME), eight letter-papers are published to present recent advances in analyti- cal and numerical analysis and in physical modeling of offshore structure-soil interactions in marine environments. They all provide examples of how enhanced understanding of mechanics can imoact on aoDlied oroiects.展开更多
A numerical method is proposed for the elasto-plasticity and pore-pressure coupled analysis on the pull- out behaviors of a plate anchor. The bounding-surface plasticity (BSP) model combined with Blot's consol- ida...A numerical method is proposed for the elasto-plasticity and pore-pressure coupled analysis on the pull- out behaviors of a plate anchor. The bounding-surface plasticity (BSP) model combined with Blot's consol- idation theory is employed to simulate the cyclic loading induced elasto-plastic deformation of the soil skeleton and the accompanying generation/dissipation of the excess pore water pressure. The suction force generated around the anchor due to the cyclic variation of the pore water pressure has much effect on the pullout capacity of the plate anchor. The calculated pullout capacity with the proposed method (i.e., the coupled analysis) gets lower than that with the conventional total stress analysis for the case of long-term sustained loading, but slightly higher for the case of short-term monotonic loading. The cyclic loading induced accumulation of pore water pressure may result in an obvious decrease of the stiffness of the soil-Plate anchor svstem.展开更多
基金financial support provided by the RIF project(Grant No.PolyU R5037-18F)from the Research Grants Council(RGC)of Hong Kong is gratefully acknowledged。
文摘Compression index Ccis an essential parameter in geotechnical design for which the effectiveness of correlation is still a challenge.This paper suggests a novel modelling approach using machine learning(ML)technique.The performance of five commonly used machine learning(ML)algorithms,i.e.back-propagation neural network(BPNN),extreme learning machine(ELM),support vector machine(SVM),random forest(RF)and evolutionary polynomial regression(EPR)in predicting Cc is comprehensively investigated.A database with a total number of 311 datasets including three input variables,i.e.initial void ratio e0,liquid limit water content wL,plasticity index Ip,and one output variable Cc is first established.Genetic algorithm(GA)is used to optimize the hyper-parameters in five ML algorithms,and the average prediction error for the 10-fold cross-validation(CV)sets is set as thefitness function in the GA for enhancing the robustness of ML models.The results indicate that ML models outperform empirical prediction formulations with lower prediction error.RF yields the lowest error followed by BPNN,ELM,EPR and SVM.If the ranges of input variables in the database are large enough,BPNN and RF models are recommended to predict Cc.Furthermore,if the distribution of input variables is continuous,RF model is the best one.Otherwise,EPR model is recommended if the ranges of input variables are small.The predicted correlations between input and output variables using five ML models show great agreement with the physical explanation.
基金supported by the National Natural Science Foundation of China(11232012 and 10872198)the Major State Basic Research Development Program of China(973 Program)(2014CB046204)
文摘The assessment of the wave-induced soil liquefaction plays a key role in the geotechnical design for offshore foundations. The underlying shortcomings of the existing momentary liquefaction criteria are identified and clarified by mechanism analyses and the recent field observations. A modified criterion for the wave-induced momentary liquefaction of a sandy seabed is given to describe the vertical pore- pressure distributions. An improved approximation of the momentary liquefaction depth is further presented. Parametric study of the effects of the saturation degree of soils indicates that this modification is significant for the evaluation of wave-induced momentary liauefaction.
文摘As the offshore industries move from shallow to deep waters in excess of 1000 m, there has been rapid development of ocean engineering practices. Innovations in theoretical and applied me- chanics have been essential in this shift and in underpinning the exploitation of offshore oil and gas and renewable energy re- sources worldwide. Understanding and predicting physical mech- anisms of structure-soil interactions are vital for the stability and safety of offshore engineering structures. Accordingly, in this spe- cial issue of Theoretical & Applied Mechanics Letters (TAME), eight letter-papers are published to present recent advances in analyti- cal and numerical analysis and in physical modeling of offshore structure-soil interactions in marine environments. They all provide examples of how enhanced understanding of mechanics can imoact on aoDlied oroiects.
基金supported by the National Natural Science Foundation of China(51309213)the 973 program of China (2014CB046200)
文摘A numerical method is proposed for the elasto-plasticity and pore-pressure coupled analysis on the pull- out behaviors of a plate anchor. The bounding-surface plasticity (BSP) model combined with Blot's consol- idation theory is employed to simulate the cyclic loading induced elasto-plastic deformation of the soil skeleton and the accompanying generation/dissipation of the excess pore water pressure. The suction force generated around the anchor due to the cyclic variation of the pore water pressure has much effect on the pullout capacity of the plate anchor. The calculated pullout capacity with the proposed method (i.e., the coupled analysis) gets lower than that with the conventional total stress analysis for the case of long-term sustained loading, but slightly higher for the case of short-term monotonic loading. The cyclic loading induced accumulation of pore water pressure may result in an obvious decrease of the stiffness of the soil-Plate anchor svstem.