Applying a meta-heuristic algorithm to predict and optimize compressive strength of concrete samples

作     者：Sun, Lei Koopialipoor, Mohammadreza Armaghani, Danial Jahed Tarinejad, Reza Tahir, M. M. 

作者机构：Hohhot Vocat Coll Dept Civil Engn & Architecture Hohhot 010051 Peoples R China Inner Mongolia Agr Univ Water Conservancy & Civil Engn Coll Hohhot 010018 Peoples R China Amirkabir Univ Technol Fac Civil & Environm Engn Tehran 15914 Iran Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Univ Tabriz Fac Civil Engn 29 Bahman Blvd Tabriz 51666 Iran Univ Teknol Malaysia Fac Engn UTM Construct Res Ctr Sch Civil EngnISIIC Skudai 81310 Johor Malaysia 

出 版 物：《ENGINEERING WITH COMPUTERS》 (计算机在工程中的应用)

年 卷 期：2021年第37卷第2期

页      面：1133-1145页

核心收录：

学科分类：08[工学] 0802[工学-机械工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：University of Tabriz University of Tabriz 

主　　题：Compressive strength of concrete Meta-heuristic algorithms Artificial bee colony Optimization technique 

摘      要：The successful use of fly ash (FA) and silica fume (SF) materials has been reported in the design of concrete samples in the literature. Due to the benefits of using these materials, they can be utilized in many industrial applications. However, the proper use of them in the right mixes is one of the important factors with respect to the strength and weight of concrete. Therefore, this paper develops relationships based on meta-heuristic (MH) algorithms (artificial bee colony technique) to evaluate the compressive strength of concrete specimens using laboratory experiments. A database comprising silica fume replacement ratio, fly ash replacement ratio, total cementitious material, water content coarse aggregate, high-rate water-reducing agent, fine aggregate, and age of samples, as model inputs, was used to evaluate and predict the compressive strength of concrete samples. Developed models of the MH technique created relationships between the mentioned parameters. In the new models, the influence of each parameter on the compressive strength was determined. Finally, using the developed model, optimum conditions for compressive strength of concrete samples were presented. This paper demonstrated that the MH algorithms are able to develop relationships that can serve as good substitutes for empirical models.