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
High strength reinforced concrete drilling shaft linings have been adopted to solve the difficult problem of supporting coal drilling shafts penetrating through thick top soils. Through model experiments the stress an...High strength reinforced concrete drilling shaft linings have been adopted to solve the difficult problem of supporting coal drilling shafts penetrating through thick top soils. Through model experiments the stress and strength of such shaft linings are studied. The test results indicate that the load beating capacity of the shaft lining is very high and that the main factors affecting the load bearing capacity are the concrete strength, the ratio of lining thickness to inner radius and the reinforcement ratio. Based on the limit equilibrium conditions and the strength theory of concrete under multi-axial compressive stressed state, a formula for calculating the load-beating capacity of a high strength reinforced concrete shaft lining was obtained. Because the concrete in a shaft lining is in a multi-axial compressive stress state the compressive strength increases to a great extent compared to uni-axial loading. Based on experiment a formula for the gain factor in compressive strength was obtained： it can be used in the structural design of the shaft lining. These results have provided a basis for sound engineering practice when designing this kind of shaft lining structure.展开更多
The stability and nonlinear dynamic behavior of drilling shaft system in copper stave deep hole drilling were analyzed. The effects of the fluctuation of the cutting force, the mass eccentricity and the hydrodynamic f...The stability and nonlinear dynamic behavior of drilling shaft system in copper stave deep hole drilling were analyzed. The effects of the fluctuation of the cutting force, the mass eccentricity and the hydrodynamic forces of cutting fluid could be taken into consideration in the model of drilling shaft system. Based on the isoparametric finite element method, the variational form of Reynolds equation in hydrodynamic fluid was used to calculate nonlinear hydrodynamic forces and their Jacobian matrices simultaneously. In the stability analysis, a new shooting method for rapidly determining the periodic orbit of the nonlinear drilling shaft system and its period was presented by rebuilding the traditional shooting method and changing the time scale. Through the combination of theories with experiment, the correctness and effectiveness of the above methods are verified by using the Floquet theory. The results show that the mass eccentricity can inhibit the whirling motion of drilling shaft to some extent.展开更多
A reliability based analysis method for a drilled shaft stabilized slope system is presented in this paper. The drilled shaft stabilization mechanisms for the slope were treated as the drilled shaft induced soil archi...A reliability based analysis method for a drilled shaft stabilized slope system is presented in this paper. The drilled shaft stabilization mechanisms for the slope were treated as the drilled shaft induced soil arching, which was quantified by the load transfer factor in the limited equilibrium analysis. However, due to the inherent uncertainties of the soil properties and the model error of the semi-empirical load transfer equation, an extension modification of the deterministic method into a probabilistic method is developed in this paper. The MCS （Monte Carlo simulation） with log-normal random variables has been employed to calculate the probability of failure （Pf） for the drilled shafts/slope system. The developed theories were coded into a computer program for analyzing complex slope geometry and slope profile conditions. Finally, a case study has been performed to illustrate the application analysis of the developed probability approach in drilled shafts/slope system.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Project 050440502 supported by the Natural Science Foundation of Anhui Province
文摘High strength reinforced concrete drilling shaft linings have been adopted to solve the difficult problem of supporting coal drilling shafts penetrating through thick top soils. Through model experiments the stress and strength of such shaft linings are studied. The test results indicate that the load beating capacity of the shaft lining is very high and that the main factors affecting the load bearing capacity are the concrete strength, the ratio of lining thickness to inner radius and the reinforcement ratio. Based on the limit equilibrium conditions and the strength theory of concrete under multi-axial compressive stressed state, a formula for calculating the load-beating capacity of a high strength reinforced concrete shaft lining was obtained. Because the concrete in a shaft lining is in a multi-axial compressive stress state the compressive strength increases to a great extent compared to uni-axial loading. Based on experiment a formula for the gain factor in compressive strength was obtained： it can be used in the structural design of the shaft lining. These results have provided a basis for sound engineering practice when designing this kind of shaft lining structure.
基金Project(2007CB707706) supported by the Major State Basic Research Development Program of ChinaProjects(2007E213,2007E203) supported by the Natural Science Foundation of Shaanxi Province,China
文摘The stability and nonlinear dynamic behavior of drilling shaft system in copper stave deep hole drilling were analyzed. The effects of the fluctuation of the cutting force, the mass eccentricity and the hydrodynamic forces of cutting fluid could be taken into consideration in the model of drilling shaft system. Based on the isoparametric finite element method, the variational form of Reynolds equation in hydrodynamic fluid was used to calculate nonlinear hydrodynamic forces and their Jacobian matrices simultaneously. In the stability analysis, a new shooting method for rapidly determining the periodic orbit of the nonlinear drilling shaft system and its period was presented by rebuilding the traditional shooting method and changing the time scale. Through the combination of theories with experiment, the correctness and effectiveness of the above methods are verified by using the Floquet theory. The results show that the mass eccentricity can inhibit the whirling motion of drilling shaft to some extent.
文摘A reliability based analysis method for a drilled shaft stabilized slope system is presented in this paper. The drilled shaft stabilization mechanisms for the slope were treated as the drilled shaft induced soil arching, which was quantified by the load transfer factor in the limited equilibrium analysis. However, due to the inherent uncertainties of the soil properties and the model error of the semi-empirical load transfer equation, an extension modification of the deterministic method into a probabilistic method is developed in this paper. The MCS （Monte Carlo simulation） with log-normal random variables has been employed to calculate the probability of failure （Pf） for the drilled shafts/slope system. The developed theories were coded into a computer program for analyzing complex slope geometry and slope profile conditions. Finally, a case study has been performed to illustrate the application analysis of the developed probability approach in drilled shafts/slope system.
