To efficiently predict the mechanical parameters of granular soil based on its random micro-structure,this study proposed a novel approach combining numerical simulation and machine learning algorithms.Initially,3500 ...To efficiently predict the mechanical parameters of granular soil based on its random micro-structure,this study proposed a novel approach combining numerical simulation and machine learning algorithms.Initially,3500 simulations of one-dimensional compression tests on coarse-grained sand using the three-dimensional(3D)discrete element method(DEM)were conducted to construct a database.In this process,the positions of the particles were randomly altered,and the particle assemblages changed.Interestingly,besides confirming the influence of particle size distribution parameters,the stress-strain curves differed despite an identical gradation size statistic when the particle position varied.Subsequently,the obtained data were partitioned into training,validation,and testing datasets at a 7:2:1 ratio.To convert the DEM model into a multi-dimensional matrix that computers can recognize,the 3D DEM models were first sliced to extract multi-layer two-dimensional(2D)cross-sectional data.Redundant information was then eliminated via gray processing,and the data were stacked to form a new 3D matrix representing the granular soil’s fabric.Subsequently,utilizing the Python language and Pytorch framework,a 3D convolutional neural networks(CNNs)model was developed to establish the relationship between the constrained modulus obtained from DEM simulations and the soil’s fabric.The mean squared error(MSE)function was utilized to assess the loss value during the training process.When the learning rate(LR)fell within the range of 10-5e10-1,and the batch sizes(BSs)were 4,8,16,32,and 64,the loss value stabilized after 100 training epochs in the training and validation dataset.For BS?32 and LR?10-3,the loss reached a minimum.In the testing set,a comparative evaluation of the predicted constrained modulus from the 3D CNNs versus the simulated modulus obtained via DEM reveals a minimum mean absolute percentage error(MAPE)of 4.43%under the optimized condition,demonstrating the accuracy of this approach.Thus,by combining DEM and CNNs,the variation of soil’s mechanical characteristics related to its random fabric would be efficiently evaluated by directly tracking the particle assemblages.展开更多
Loessic soil in the north-west of Argentina, which consists of silt and silty clay with reduced content of fine sand, has collapsible characteristics. This means that by increasing the moisture content close to the li...Loessic soil in the north-west of Argentina, which consists of silt and silty clay with reduced content of fine sand, has collapsible characteristics. This means that by increasing the moisture content close to the liquid limit value, the loess soil＇s macro porous structure breaks experiencing large volumetric deformations. The collapse pressure and soil constrained modulus are fundamentals parameters for the characterization of these soils and the study of solutions to geotechnical problems. In this work we study the loess from the north-west region of our country, especially the Santiago del Estero＇s plain, based on numerous field tests and laboratory tests in order to correlate the modulus and collapse pressure from double-odometer test with the blow count from SPT （standard penetration test）. It also analyzes the influence of these parameters on moisture content, void ratio and the presence of salts and calcareous concretions in soils and discusses the validity of these correlations as well as those proposed by other authors.展开更多
A new approach is developed to determine the shear wave velocity in saturated soft to firm clays using measurements of the liquid limit, plastic limit, and natural water content with depth. The shear wave velocity is ...A new approach is developed to determine the shear wave velocity in saturated soft to firm clays using measurements of the liquid limit, plastic limit, and natural water content with depth. The shear wave velocity is assessed using the site-specific variation of the natural water content with the effective mean stress. Subsequently, an iterative process is envisaged to obtain the clay stiffness and strength parameters.The at-rest earth pressure coefficient, as well as bearing capacity factor and rigidity index related to the cone penetration test, is also acquired from the analyses. Comparisons are presented between the measured clay parameters and the results of corresponding analyses in five different case studies. It is demonstrated that the presented approach can provide acceptable estimates of saturated clay stiffness and strength parameters. One of the main privileges of the presented methodology is the site-specific procedure developed based on the relationships between clay strength and stiffness parameters, rather than adopting direct correlations. Despite of the utilized iterative processes, the presented approach can be easily implemented using a simple spreadsheet, benefiting both geotechnical researchers and practitioners.展开更多
This paper aims to deal with the comparison of the estimated settlements derived by in situ tests with the observed settlements in site, in order to evaluate the accuracy of settlement prediction by in situ tests, in ...This paper aims to deal with the comparison of the estimated settlements derived by in situ tests with the observed settlements in site, in order to evaluate the accuracy of settlement prediction by in situ tests, in comparison not only with site observation by topographic means, but also with the values of settlements derived by numerical analysis by means of PLAXIS 2D and 3 D. The site where are carried out the tests and periodically are observed the settlements since the beginning of construction process, is located in the Oil Product Terminal, at the industrial park of Porto Romano, Durres, Albania. The main purpose of this project was the ground improvement by using preloading method in order to prevent liquefaction process and settlements. The data used to conduct this study are taken by the site investigation done after inserting into the soil vertical drains made of columns of free--draining gravel （gravel pile drains） until 14 m depth and center-to-center spacing of 2 m, and wick drains （premanufactured） until 25 m depth and center-to-center spacing of 1.8 m. The observed settlements are periodically measured by topographic equipments. This paper will present the conclusions derived by settlement analyzes from in situ tests and site observations.展开更多
基金supported by the National Key R&D Program of China (Grant No.2022YFC3003401)the National Natural Science Foundation of China (Grant Nos.42041006 and 42377137).
文摘To efficiently predict the mechanical parameters of granular soil based on its random micro-structure,this study proposed a novel approach combining numerical simulation and machine learning algorithms.Initially,3500 simulations of one-dimensional compression tests on coarse-grained sand using the three-dimensional(3D)discrete element method(DEM)were conducted to construct a database.In this process,the positions of the particles were randomly altered,and the particle assemblages changed.Interestingly,besides confirming the influence of particle size distribution parameters,the stress-strain curves differed despite an identical gradation size statistic when the particle position varied.Subsequently,the obtained data were partitioned into training,validation,and testing datasets at a 7:2:1 ratio.To convert the DEM model into a multi-dimensional matrix that computers can recognize,the 3D DEM models were first sliced to extract multi-layer two-dimensional(2D)cross-sectional data.Redundant information was then eliminated via gray processing,and the data were stacked to form a new 3D matrix representing the granular soil’s fabric.Subsequently,utilizing the Python language and Pytorch framework,a 3D convolutional neural networks(CNNs)model was developed to establish the relationship between the constrained modulus obtained from DEM simulations and the soil’s fabric.The mean squared error(MSE)function was utilized to assess the loss value during the training process.When the learning rate(LR)fell within the range of 10-5e10-1,and the batch sizes(BSs)were 4,8,16,32,and 64,the loss value stabilized after 100 training epochs in the training and validation dataset.For BS?32 and LR?10-3,the loss reached a minimum.In the testing set,a comparative evaluation of the predicted constrained modulus from the 3D CNNs versus the simulated modulus obtained via DEM reveals a minimum mean absolute percentage error(MAPE)of 4.43%under the optimized condition,demonstrating the accuracy of this approach.Thus,by combining DEM and CNNs,the variation of soil’s mechanical characteristics related to its random fabric would be efficiently evaluated by directly tracking the particle assemblages.
文摘Loessic soil in the north-west of Argentina, which consists of silt and silty clay with reduced content of fine sand, has collapsible characteristics. This means that by increasing the moisture content close to the liquid limit value, the loess soil＇s macro porous structure breaks experiencing large volumetric deformations. The collapse pressure and soil constrained modulus are fundamentals parameters for the characterization of these soils and the study of solutions to geotechnical problems. In this work we study the loess from the north-west region of our country, especially the Santiago del Estero＇s plain, based on numerous field tests and laboratory tests in order to correlate the modulus and collapse pressure from double-odometer test with the blow count from SPT （standard penetration test）. It also analyzes the influence of these parameters on moisture content, void ratio and the presence of salts and calcareous concretions in soils and discusses the validity of these correlations as well as those proposed by other authors.
文摘A new approach is developed to determine the shear wave velocity in saturated soft to firm clays using measurements of the liquid limit, plastic limit, and natural water content with depth. The shear wave velocity is assessed using the site-specific variation of the natural water content with the effective mean stress. Subsequently, an iterative process is envisaged to obtain the clay stiffness and strength parameters.The at-rest earth pressure coefficient, as well as bearing capacity factor and rigidity index related to the cone penetration test, is also acquired from the analyses. Comparisons are presented between the measured clay parameters and the results of corresponding analyses in five different case studies. It is demonstrated that the presented approach can provide acceptable estimates of saturated clay stiffness and strength parameters. One of the main privileges of the presented methodology is the site-specific procedure developed based on the relationships between clay strength and stiffness parameters, rather than adopting direct correlations. Despite of the utilized iterative processes, the presented approach can be easily implemented using a simple spreadsheet, benefiting both geotechnical researchers and practitioners.
文摘This paper aims to deal with the comparison of the estimated settlements derived by in situ tests with the observed settlements in site, in order to evaluate the accuracy of settlement prediction by in situ tests, in comparison not only with site observation by topographic means, but also with the values of settlements derived by numerical analysis by means of PLAXIS 2D and 3 D. The site where are carried out the tests and periodically are observed the settlements since the beginning of construction process, is located in the Oil Product Terminal, at the industrial park of Porto Romano, Durres, Albania. The main purpose of this project was the ground improvement by using preloading method in order to prevent liquefaction process and settlements. The data used to conduct this study are taken by the site investigation done after inserting into the soil vertical drains made of columns of free--draining gravel （gravel pile drains） until 14 m depth and center-to-center spacing of 2 m, and wick drains （premanufactured） until 25 m depth and center-to-center spacing of 1.8 m. The observed settlements are periodically measured by topographic equipments. This paper will present the conclusions derived by settlement analyzes from in situ tests and site observations.
