Skip navigation

An EPR approach to the modeling of civil and geotechnical engineering systems

An EPR approach to the modeling of civil and geotechnical engineering systems

Javadi, Akbar A., Ahangar-Asr, Alireza, Faramarzi, Asaad and Mottaghifard, Nasim (2012) An EPR approach to the modeling of civil and geotechnical engineering systems. In: Yang, Xin-She, Gandomi, Amir Hossein, Talatahari, Siamak and Alavi, Amir Hossein, (eds.) Metaheuristics in Water, Geotechnical and Transport Engineering. Elsevier Inc., Waltham, MA, USA, pp. 311-326. ISBN 978-0-12-398296-4 (doi:https://doi.org/10.1016/B978-0-12-398296-4.00013-1)

Full text not available from this repository.

Abstract

Evolutionary polynomial regression (EPR) is a data-driven technique based on evolutionary computing that aims to search for polynomial structures representing a system. In this technique, a combination of the genetic algorithm and the least squares method is used to find feasible structures representing the behavior of the system directly from data. The accuracy of the developed models and their generalization capabilities are directly related to the accuracy and completeness of the data used to develop the models. Several examples are presented on practical applications of EPR. It is shown that EPR models are applicable to a diverse range of engineering systems and are capable of modeling the behavior of complex systems with very high accuracy. An example is also presented to show the possibility of using EPR-based models in the finite element method. The merits and advantages of the proposed approach are highlighted.

Item Type: Book Section
Additional Information: [1] Chapter 13, in Part Two - Geotechnical Engineering.
Uncontrolled Keywords: evolutionary computation, polynomial regression, data mining, constitutive modeling, finite element method
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
Pre-2014 Departments: School of Engineering
Related URLs:
Last Modified: 14 Oct 2016 09:24
Selected for GREAT 2016: None
Selected for GREAT 2017: None
Selected for GREAT 2018: None
URI: http://gala.gre.ac.uk/id/eprint/9678

Actions (login required)

View Item View Item