Identification of the most influencing parameters on the properties of corroded concrete beams using an Adaptive Neuro-Fuzzy Inference System (ANFIS)

Mahdi Shariati , Mohammad Saeed Mafipour , James H. Haido , Salim T. Yousif , Ali Toghroli , Nguyen Thoi Trung , Ali Shariati

Abstract

Different parameters potentially affect the properties of corroded reinforced concrete beams. However, the high number of these parameters and their dependence cause that the effectiveness of the parameters could not be simply identified. In this study, an adaptive neuro-fuzzy inference system (ANFIS) was employed to determine the most influencing parameters on the properties of the corrosion-damaged reinforced concrete beams. 207 ANFIS models were developed to analyze the collected data from 107 reinforced concrete (RC) beams. The impact of 23 input parameters on nine output factors was investigated. The results of the paper showed the order of influence of each input parameter on the outputs and revealed that the input parameters regarding the uncorroded properties of concrete beams are the most influencing factors on the corresponding corroded properties of the beams.

Key Words

Adaptive Neuro-Fuzzy Inference System; system identification; corrosion; reinforced concrete beams

Address

Mahdi Shariati and Nguyen Thoi Trung — Division of Computational Mathematics and Engineering, Institute for Computational Science, Ton Duc Thang University, Ho Chi Minh City, Vietnam; Faculty of Civil Engineering, Ton Duc Thang University, Ho Chi Minh City, Vietnam
Mohammad Saeed Mafipour — School of Civil Engineering, College of Engineering, University of Tehran,Tehran, Iran
James H. Haido — Department of Civil Engineering, College of Engineering, University of Duhok, Kurdistan Region, Iraq
Salim T. Yousif — Department of Civil Engineering, Al-Qalam University College, Kirkuk, Iraq
Ali Toghroli and Ali Shariati — Institute of Research and Development, Duy Tan University, Da Nang 550000, Viet Nam

PDF Viewer

Preview is limited to the first 3 pages. Sign in to access the full PDF.

← Back to Volume 34, No. 1