Skip navigation

Thermo-mechanical modelling of unsaturated soils using EPR

Thermo-mechanical modelling of unsaturated soils using EPR

Ahangar-Asr, A., Javadi, A.A. and Faramarzi, A. (2012) Thermo-mechanical modelling of unsaturated soils using EPR. In: Proceedings of the 2012 eg-ice Workshop. Technische Universität München, Herrsching (Munich), Germany. ISBN 9783000384554

Full text not available from this repository.

Abstract

A new approach is presented for modelling of the thermo-mechanical behaviour of unsaturated soils using Evolutionary Polynomial regression (EPR). EPR is a data-driven technique based on evolutionary computing developed with the aim of searching for polynomial structures representing the behaviour of a system. In this technique, a combination of a genetic algorithm (GA) and the least square method is used to find feasible structures and the appropriate parameters of those structures. An EPR model was developed and validated based on results from a comprehensive set of triaxial tests conducted on an unsaturated silt. The developed model was used to predict the shear behaviour of the soil considering the effects of temperature. The results of the EPR model predictions were compared with experimental results. Comparison of the results reveals that the proposed model is highly accurate and robust in predicting the thermo-mechanical behaviour of unsaturated soils.

Item Type: Conference Proceedings
Title of Proceedings: Proceedings of the 2012 eg-ice Workshop
Additional Information: [1] This paper was first presented at the 2012 EG-ICE (European Group for Intelligent Computing in Engineering) Workshop held from 4-6 July 2012 in Munich, Germany. The paper was given within Session 10, Optimisation, on 6th July 2012.
Uncontrolled Keywords: unsaturated soil, thermo-mechanical modelling, EPR
Subjects: T Technology > TP Chemical technology
Pre-2014 Departments: School of Engineering
School of Engineering > Department of Civil Engineering
Related URLs:
Last Modified: 14 Oct 2016 09:26
Selected for GREAT 2016: None
Selected for GREAT 2017: None
Selected for GREAT 2018: None
URI: http://gala.gre.ac.uk/id/eprint/11145

Actions (login required)

View Item View Item