Genetic algorithm for predicting shear strength of steel fiber reinforced concrete beam with parameter identification and sensitivity analysis

By M. Shahnewaz, M. Alam. 2020

49 citations recorded by the source corpus.

Abstract The shear behavior of steel fiber reinforced concrete (SFRC) beams is a complex phenomenon that depends on many parameters. This research investigated the contribution of different parameters on the shear strength of SFRC beams. For this, a database of test results on SFRC beams was constructed. The important parameters were identified using Meta-model of Optimal Prognosis (MOP) where the parameters were ranked based on adjusted coefficient of determination. An improved equation to estimate the shear strength of SFRC beams is proposed based on Genetic Algorithm. Only important parameters from MOP results were incorporated in the proposed equation. The proposed equation showed significant improvement and accuracy compared to previous equations. A sensitivity analysis was performed to evaluate the impact of each parameter on the shear strength of SFRC beams for which an Advanced Latin Hyperbolic Sampling technique was used for the design of experiments. The MOP was also utilized to evaluate the sensitivity of each parameter on the prediction equation.

Subfields: Building and Construction, Civil and Structural Engineering

View Paper: https://www.semanticscholar.org/paper/b5d5c003fb197b12f9eca76bca5f63b42f9c90c1