Lateral load bearing capacity model for piles in cohesive soils

Ahangar Asr, A; Javadi, A; Johari, A; Chen, Y

Abstract

In this research work an evolutionary approach is proposed to develop a structured polynomial model for predicting the lateral load bearing capacity of piles in undrained conditions. The proposed polynomial regression technique is an evolutionary data mining methodology that generates a transparent and structured representation of the behaviour of a system directly from raw data. It can operate on large quantities of data in order to capture nonlinear and complex relationships between contributing variables. Field measurement data from literature was used to develop the proposed model. Comparison of the proposed model predictions with the field data shows that the EPR model is capable of capturing, predicting and generalising predictions to unseen data cases the lateral load bearing capacity of piles with very high accuracy. The merits and advantages of the proposed methodology are also discussed.

Citation

Ahangar Asr, A., Javadi, A., Johari, A., & Chen, Y. (2014). Lateral load bearing capacity model for piles in cohesive soils. In A. Javadi, & M. Hussain (Eds.), Proceedings of the 22nd UK National Conference of the Association for Computational Mechanics in Engineering (264-267). University of Exeter

• Start Date: Apr 2, 2014
• End Date: Apr 4, 2014
• Publication Date: Jan 1, 2014
• Deposit Date: Dec 15, 2015
• Pages: 264-267
• Book Title: Proceedings of the 22nd UK National Conference of the Association for Computational Mechanics in Engineering
• ISBN: 9780902746305
• Publisher URL: http://emps.exeter.ac.uk/engineering/research/acme/programmeproceedings/
• Additional Information: Additional Information : 2nd - 4th April 2014 College of Engineering, Mathematics and Physical Sciences, University of Exeter, UK; Event Type : Conference