Soil curling is an important phenomenon associated with volume changes induced by increasing soil suction upon desiccation.The study of soil behaviors associated with drying in soils(e.g.soil shrinkage,desiccation cra...Soil curling is an important phenomenon associated with volume changes induced by increasing soil suction upon desiccation.The study of soil behaviors associated with drying in soils(e.g.soil shrinkage,desiccation cracks and curling)has received increasing attention over the last few years,which has been mainly driven by the forecast climate change that will warm up our planet.There are significant gaps in the current knowledge related to the factors that control the development of curling deformations in soils.For this,the curling phenomenon is investigated through laboratory desiccation tests on different mixtures of artificial soils.The effects of soil grain size distribution,mineralogy,soil microstructure,and soil water content on the curling deformation are analyzed.Digital photos were taken at regular time intervals during the tests to understand the volume changes in the soil samples during drying.It is found that soil fabric and soil water content have significant effects on curling scenario.It is observed that the percentage of sand particles and the initial water content play a critical role in the development of soil curling.Samples of pure clayey minerals experienced shrinkage without or with minor curling during drying.展开更多
Ensuring the reliability of pipe pile designs under earthquake loading necessitates an accurate determination of lateral displacement and bending moment,typically achieved through complex numerical modeling to address...Ensuring the reliability of pipe pile designs under earthquake loading necessitates an accurate determination of lateral displacement and bending moment,typically achieved through complex numerical modeling to address the intricacies of soil-pile interaction.Despite recent advancements in machine learning techniques,there is a persistent need to establish data-driven models that can predict these parameters without using numerical simulations due to the difficulties in conducting correct numerical simulations and the need for constitutive modelling parameters that are not readily available.This research presents novel lateral displacement and bending moment predictive models for closed and open-ended pipe piles,employing a Genetic Programming(GP)approach.Utilizing a soil dataset extracted from existing literature,comprising 392 data points for both pile types embedded in cohesionless soil and subjected to earthquake loading,the study intentionally limited input parameters to three features to enhance model simplicity:Standard Penetration Test(SPT)corrected blow count(N60),Peak Ground Acceleration(PGA),and pile slenderness ratio(L/D).Model performance was assessed via coefficient of determination(R^(2)),Root Mean Squared Error(RMSE),and Mean Absolute Error(MAE),with R^(2) values ranging from 0.95 to 0.99 for the training set,and from 0.92 to 0.98 for the testing set,which indicate of high accuracy of prediction.Finally,the study concludes with a sensitivity analysis,evaluating the influence of each input parameter across different pile types.展开更多
文摘Soil curling is an important phenomenon associated with volume changes induced by increasing soil suction upon desiccation.The study of soil behaviors associated with drying in soils(e.g.soil shrinkage,desiccation cracks and curling)has received increasing attention over the last few years,which has been mainly driven by the forecast climate change that will warm up our planet.There are significant gaps in the current knowledge related to the factors that control the development of curling deformations in soils.For this,the curling phenomenon is investigated through laboratory desiccation tests on different mixtures of artificial soils.The effects of soil grain size distribution,mineralogy,soil microstructure,and soil water content on the curling deformation are analyzed.Digital photos were taken at regular time intervals during the tests to understand the volume changes in the soil samples during drying.It is found that soil fabric and soil water content have significant effects on curling scenario.It is observed that the percentage of sand particles and the initial water content play a critical role in the development of soil curling.Samples of pure clayey minerals experienced shrinkage without or with minor curling during drying.
文摘Ensuring the reliability of pipe pile designs under earthquake loading necessitates an accurate determination of lateral displacement and bending moment,typically achieved through complex numerical modeling to address the intricacies of soil-pile interaction.Despite recent advancements in machine learning techniques,there is a persistent need to establish data-driven models that can predict these parameters without using numerical simulations due to the difficulties in conducting correct numerical simulations and the need for constitutive modelling parameters that are not readily available.This research presents novel lateral displacement and bending moment predictive models for closed and open-ended pipe piles,employing a Genetic Programming(GP)approach.Utilizing a soil dataset extracted from existing literature,comprising 392 data points for both pile types embedded in cohesionless soil and subjected to earthquake loading,the study intentionally limited input parameters to three features to enhance model simplicity:Standard Penetration Test(SPT)corrected blow count(N60),Peak Ground Acceleration(PGA),and pile slenderness ratio(L/D).Model performance was assessed via coefficient of determination(R^(2)),Root Mean Squared Error(RMSE),and Mean Absolute Error(MAE),with R^(2) values ranging from 0.95 to 0.99 for the training set,and from 0.92 to 0.98 for the testing set,which indicate of high accuracy of prediction.Finally,the study concludes with a sensitivity analysis,evaluating the influence of each input parameter across different pile types.
