<abstract xmlns="http://www.w3.org/1999/xhtml"><p>A hybrid ANN-FE solution is presented as a result of two level analysis of soils: a level of a laboratory sample and a level of engineering geotechnical problem. Engineering properties of soils (sands) are represented directly in the form of ANN (this is in contrast with our former paper where ANN approximated constitutive relationships). Initially the ANN is trained with Duncan formula (Duncan and Chang [2]), then it is re-trained (calibrated) with some available experimental data, specific for the soil considered. The obtained approximation of the constitutive parameters is used directly in finite element method at the level of a single element at the scale of the laboratory sample to check the correct representation of the laboratory test. Then, the finite element that was successfully tested at the level of laboratory sample is used at the macro level to solve engineering problems involving the soil for which it was calibrated.</p></abstract>

A hybrid ANN-FE solution is presented as a result of two level analysis of soils: a level of a laboratory sample and a level of engineering geotechnical problem. Engineering properties of soils (sands) are represented directly in the form of ANN (this is in contrast with our former paper where ANN approximated constitutive relationships). Initially the ANN is trained with Duncan formula (Duncan and Chang [2]), then it is re-trained (calibrated) with some available experimental data, specific for the soil considered. The obtained approximation of the constitutive parameters is used directly in finite element method at the level of a single element at the scale of the laboratory sample to check the correct representation of the laboratory test. Then, the finite element that was successfully tested at the level of laboratory sample is used at the macro level to solve engineering problems involving the soil for which it was calibrated.

Two Scales, Hybrid Model for Soils, Involving Artificial Neural Network and Finite Element Procedure

Department of Geotechnics and Engineering Structures, Lódź Univeristy of Technology, al. Politechniki 6, 90-590 Lódź

Studia Geotechnica et Mechanica

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

A hybrid ANN-FE solution is presented as a result of two level analysis of soils: a level of a laboratory sample and a level of engineering geotechnical...

Two Scales, Hybrid Model for Soils, Involving Artificial Neural Network and Finite Element Procedure

Publié en ligne: 28 févr. 2015

Pages: 29 - 36

DOI: https://doi.org/10.2478/sgem-2014-0017

Mots clés
soil model, neural network, Finite Element Method, hybrid FE-ANN model

© 2014 Marcin Krasiński and Marek Lefik

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Two Scales, Hybrid Model for Soils, Involving Artificial Neural Network and Finite Element Procedure

Publié en ligne: 28 févr. 2015

Pages: 29 - 36

DOI: https://doi.org/10.2478/sgem-2014-0017

Mots cléssoil model, neural network, Finite Element Method, hybrid FE-ANN model

© 2014 Marcin Krasiński and Marek Lefik

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Mots clés
soil model, neural network, Finite Element Method, hybrid FE-ANN model