Modeling the thermo-mechanical triaxial shearing behavior of unsaturated soils using EPR

Ahangar Asr, A; Javadi, A; Khalili, N

Abstract

The proposed approach for modeling the thermo-mechanical of behavior of unsaturated soils is based on the evolutionary polynomial regression (EPR), which generates a transparent and structured representation of the behavior of systems directly from raw data. The approach operates on large quantities of data to capture com-plex relationships between contributing variables. The developed model allows the user to gain a clear insight into the behavior of the system. Unsaturated triaxial test data was used for development and verification of the model. Comparison of the EPR model predictions with the experimental data revealed the robustness and capability of the proposed methodology in capturing and reproducing the thermo-mechanical stress-strain be-havior of unsaturated soils. More importantly, the capability of the developed model in accurately generalizing the predictions to unseen data cases was illustrated. The results of a sensitivity analysis showed that the model developed from data was able to capture and represent the physical aspects of the unsaturated soil behavior accurately. The merits and advantages of the proposed methodology are highlighted in this paper.

Citation

Ahangar Asr, A., Javadi, A., & Khalili, N. (2014, July). Modeling the thermo-mechanical triaxial shearing behavior of unsaturated soils using EPR. Presented at International Conference on Unsaturated Soils: Research & Applications UNSAT2014, Sydney, Australia

• Presentation Conference Type: Other
• Conference Name: International Conference on Unsaturated Soils: Research & Applications UNSAT2014
• Conference Location: Sydney, Australia
• Start Date: Jul 2, 2014
• End Date: Jul 4, 2014
• Deposit Date: Dec 15, 2015
• Publisher URL: https://www.interpore.org/events/third-party-conference/unsat2014-international-conference-on-unsaturated-soils-research-applications
• Additional Information: Event Type : Conference