Artificial Neural Network Based Mechanical Property Prediction of ECC

Fariborz Nateghi-A¹ Mohammad Hossein Ahmadi²

1) Professor, International Institute of Earthquake Engineering and Seismology, Tehran, Iran
2) Ph.D. Candidate, International Institute of Earthquake Engineering and Seismology, Tehran, Iran

Publication : International Congress of Science and Engineering - TOKYO UNIVERSITY - JAPAN(tuicet.com)
Abstract :
Cement-based composite materials like Engineered Cementitious Composites (ECCs) are applicable in the strengthening of structures because of the high tensile strength and strain. In this paper after finding the best mix proportion of ECC based on uniaxial tensile strength and strain, the correlation between these parameters were calculated. Since material properties depend on the content ratios, six mixtures with different Fly Ash (FA) content were considered to find the best ECC mixture called Improved ECC (IECC). The influence of local fine aggregates and FA on the tensile behavior of ECC was considered to introduce IECC which has the best tensile properties. To show the mechanical properties of ECC using prediction models, Artificial Neural Network (ANN) was used. Training and validation of the proposed model were carried out based on 36 experimental results to find the best results. The results show that the proposed model predicts the tensile strength and strain of ECC with different FA ratios accurately. Also, the model can estimate mechanical properties of ECC in previous experimental results.
Keywords : Engineered Cementitious Composites Experimental Study Artificial Neural Network Local Admixtures Mechanical Properties