In 2023,pivotal advancements in artificial intelligence(AI)have significantly experienced.With that in mind,traditional methodologies,notably the p-y approach,have struggled to accurately model the complex,nonlinear s...In 2023,pivotal advancements in artificial intelligence(AI)have significantly experienced.With that in mind,traditional methodologies,notably the p-y approach,have struggled to accurately model the complex,nonlinear soil-structure interactions of laterally loaded large-diameter drilled shafts.This study undertakes a rigorous evaluation of machine learning(ML)and deep learning(DL)techniques,offering a comprehensive review of their application in addressing this geotechnical challenge.A thorough review and comparative analysis have been carried out to investigate various AI models such as artificial neural networks(ANNs),relevance vector machines(RVMs),and least squares support vector machines(LSSVMs).It was found that despite ML approaches outperforming classic methods in predicting the lateral behavior of piles,their‘black box'nature and reliance only on a data-driven approach made their results showcase statistical robustness rather than clear geotechnical insights,a fact underscored by the mathematical equations derived from these studies.Furthermore,the research identified a gap in the availability of drilled shaft datasets,limiting the extendibility of current findings to large-diameter piles.An extensive dataset,compiled from a series of lateral loading tests on free-head drilled shaft with varying properties and geometries,was introduced to bridge this gap.The paper concluded with a direction for future research,proposes the integration of physics-informed neural networks(PINNs),combining data-driven models with fundamental geotechnical principles to improve both the interpretability and predictive accuracy of AI applications in geotechnical engineering,marking a novel contribution to the field.展开更多
There are two kinds of internationally recognized approaches in terms of lightweight design.One is based on fatigue accumulated damage theory to achieve better reliability by optimal structural design; another is to u...There are two kinds of internationally recognized approaches in terms of lightweight design.One is based on fatigue accumulated damage theory to achieve better reliability by optimal structural design; another is to use high performance lightweight materials.The former method takes very few considerations on the structural strengthening effects caused by the massive small loads in service.In order to ensure safety,the design is usually conservative,but the strength potential of the component is not fully exerted.In the latter method,cost is the biggest obstacle to lightweight materials in automotive applications.For the purpose of light weighting design on a fuel cell vehicle,the new design method is applied on drive shafts.The method is based on the low amplitude load strengthening characteristics of the material,and allows the stress,corresponding to test load,to enter into the strengthened range of the material.Under this condition,the light weighting design should assure that the reliability of the shaft is not impaired,even maximizes the strength potential of machine part in order to achieve the weight reduction and eventually to reduce the cost.At last,the feasibility of the design is verified by means of strength analysis and modal analysis based on the CAD model of light weighted shaft.The design applies to the load case of half shaft in independent axle,also provides technological reference for the structural lightweight design of vehicles and other machineries.展开更多
基金supported by Prince Sultan University(Grant No.PSU-CE-TECH-135,2023).
文摘In 2023,pivotal advancements in artificial intelligence(AI)have significantly experienced.With that in mind,traditional methodologies,notably the p-y approach,have struggled to accurately model the complex,nonlinear soil-structure interactions of laterally loaded large-diameter drilled shafts.This study undertakes a rigorous evaluation of machine learning(ML)and deep learning(DL)techniques,offering a comprehensive review of their application in addressing this geotechnical challenge.A thorough review and comparative analysis have been carried out to investigate various AI models such as artificial neural networks(ANNs),relevance vector machines(RVMs),and least squares support vector machines(LSSVMs).It was found that despite ML approaches outperforming classic methods in predicting the lateral behavior of piles,their‘black box'nature and reliance only on a data-driven approach made their results showcase statistical robustness rather than clear geotechnical insights,a fact underscored by the mathematical equations derived from these studies.Furthermore,the research identified a gap in the availability of drilled shaft datasets,limiting the extendibility of current findings to large-diameter piles.An extensive dataset,compiled from a series of lateral loading tests on free-head drilled shaft with varying properties and geometries,was introduced to bridge this gap.The paper concluded with a direction for future research,proposes the integration of physics-informed neural networks(PINNs),combining data-driven models with fundamental geotechnical principles to improve both the interpretability and predictive accuracy of AI applications in geotechnical engineering,marking a novel contribution to the field.
基金supported by National Natural Science Foundation of China (Grant No. 50875173)Shanghai Municipal Education Commission Key Foundation of China (Grant No. 09ZZ157)Shanghai Leading Academic Discipline Project of China (Grant No. J50503)
文摘There are two kinds of internationally recognized approaches in terms of lightweight design.One is based on fatigue accumulated damage theory to achieve better reliability by optimal structural design; another is to use high performance lightweight materials.The former method takes very few considerations on the structural strengthening effects caused by the massive small loads in service.In order to ensure safety,the design is usually conservative,but the strength potential of the component is not fully exerted.In the latter method,cost is the biggest obstacle to lightweight materials in automotive applications.For the purpose of light weighting design on a fuel cell vehicle,the new design method is applied on drive shafts.The method is based on the low amplitude load strengthening characteristics of the material,and allows the stress,corresponding to test load,to enter into the strengthened range of the material.Under this condition,the light weighting design should assure that the reliability of the shaft is not impaired,even maximizes the strength potential of machine part in order to achieve the weight reduction and eventually to reduce the cost.At last,the feasibility of the design is verified by means of strength analysis and modal analysis based on the CAD model of light weighted shaft.The design applies to the load case of half shaft in independent axle,also provides technological reference for the structural lightweight design of vehicles and other machineries.