Multiobjective genetic programming for reinforced concrete beam modeling

Amirhessam Tahmassebi,Behshad Mohebali,Anke Meyer‐Baese,Amir H Gandomi

doi:10.1002/ail2.9

Amirhessam Tahmassebi, Behshad Mohebali + Show 2 more

Open Access

PDF Available

https://doi.org/10.1002/ail2.9

Copy DOI

Export

Save

Cite

Abstract
Highlights/Summary
Full-Text PDF
Similar Papers

Abstract

Listen

AbstractThis paper presents the application of multiobjective genetic programming (MOGP) in engineering issues. An evolutionary symbolic implementation was developed based on a case study on prediction of the shear strength of slender reinforced concrete beams without stirrups including 1942 set of published test results. In the implementation of the MOGP model, the nondominated sorting genetic algorithm II with adaptive regression by mixing algorithm with considering the optimization of mean‐square error as the fitness measure and the subtree complexity was used. The developed MOGP model was compared to previously developed genetic programming models, different building codes, and additional machine learning based approaches. It is clearly shown that the MOGP model outperformed the other algorithms applied on this database and can be a general solution on any engineering problems with the main advantage of prediction equations without assuming prior form of the relevance among the input predictor variables.

Highlights

Since its conception in 1992 by John Koza,[1] genetic programming (GP) has been an attractive tool for researchers to identify models and systems
The regression model[15,16] in Algorithm 1 is implemented as an multiobjective genetic programming (MOGP) approach based on the work of Deb et al on nondominated sorting genetic algorithm II (NSGA-II).[18]
This paper shows the application of robust solutions (R = 0.9487, mean absolute error (MAE) = 25.18, mean squared error (MSE) = 2480.92, μ = 1.0840, coefficient of variation (CV) = 0.309, and regression error characteristic (REC) − area under the curve (AUC) = 84.50) employing MOGP in engineering problems

Summary

Introduction

Since its conception in 1992 by John Koza,[1] genetic programming (GP) has been an attractive tool for researchers to identify models and systems. Various models including different characteristics via the combination of multiobjective genetic programming (MOGP) and adaptive regression by mixing algorithm were proposed.

Results

Conclusion