Estimation of strengths of hybrid FR-SCC by using deep-learning and support vector regression models

Abstract

In this work, to estimate the compressive, splitting tensile, and flexuralstrength of self-compacting concrete (SCC) having single fiber and binary, ter-nary, and quaternary fiber hybridization, the deep-learning (DL) and supportvector regression (SVR) models were devised. The fiber content and coarseaggregate/total aggregate ratio (CA/TA) were the variables for 24 designedmixtures. Four different fibers, which were a macro steel fiber, two types ofmicro steel fibers with different aspect ratio, and polyvinyl alcohol (PVA) fiber,were used in SCC mixtures. The specimens of each mixture were tested to mea-sure the engineering properties for 7, 28, and 90 days. The amount of cement,fly ash, fine aggregate, CA, high-range water-reducing admixture, water, macrosteel fiber, PVA fiber, two types of micro steel fibers, and curing time wereselected as input layers while the output layers were strength results. Theexperimental results were compared with the estimation results. The engineer-ing properties were estimated using the SVR model with 95.25%, 87.81%, and93.89% accuracy, respectively. Furthermore, the DL model estimated compres-sive strength, tensile strength, and flexural strength with 99.27%, 98.59%, and99.15% accuracy, respectively. It was found that the DL estimated the engineer-ing properties of hybrid fiber–reinforced SCC with higher accuracy than SVR