Abstract:In this work, to estimate the compressive, splitting tensile, and flexural strength of self‐compacting concrete (SCC) having single fiber and binary, ternary, and quaternary fiber hybridization, the deep‐learning (DL) and support vector regression (SVR) models were devised. The fiber content and coarse aggregate/total aggregate ratio (CA/TA) were the variables for 24 designed mixtures. Four different fibers, which were a macro steel fiber, two types of micro steel fibers with different aspect ratio, and polyvi… Show more
“…The study demonstrated that out of all the boosting algorithms employed, extreme gradient boosting algorithm proved to be the most accurate depicting the least absolute error of 1.43 MPa between real and predicted values. Similarly, Kina et al [ 56 ] utilized deep learning and SVM to estimate cs, fs, and split-tensile strength of SCC containing a mix of macro steel and micro synthetic fibres. The authors prepared 24 laboratory samples and measured their strength at 7, 28 and 90 days, then utilized that data to build ML models and concluded that deep learning predicted the SCC strength reinforced with different fibres more accurately than SVM.…”
“…The study demonstrated that out of all the boosting algorithms employed, extreme gradient boosting algorithm proved to be the most accurate depicting the least absolute error of 1.43 MPa between real and predicted values. Similarly, Kina et al [ 56 ] utilized deep learning and SVM to estimate cs, fs, and split-tensile strength of SCC containing a mix of macro steel and micro synthetic fibres. The authors prepared 24 laboratory samples and measured their strength at 7, 28 and 90 days, then utilized that data to build ML models and concluded that deep learning predicted the SCC strength reinforced with different fibres more accurately than SVM.…”
“…In order to improve the engineering properties of concrete in terms of brittle-ness, post-cracking capability and burst failure, short and randomly distributed fibers can be gradually added into concrete [2,3]. Adding fibers such as basalt, polypropylene (PP), glass, and steel fibers into cement-based composites is so common to upgrade the tensile performance and mechanical properties [4][5][6][7][8][9][10]. These advantageous properties of fibers cause an increase in the application of fiber-reinforced concrete throughout the world.…”
An experimental study was herein presented focusing the effect of different type, shape and volume fraction of fibers on the hardened properties of concrete including compressive, splitting tensile and flexural strengths at 7 and 28 curing days. A control concrete mixture with no fiber was prepared and six fiber reinforced concrete mixtures were designed by using two different types of fibers which were steel fibers with different shapes (short straight and hooked end) and polypropylene fiber with the volume fraction of 0.4% and 0.8%. The load-deflection curves and toughness of the specimens were analyzed based on ASTM C1609. The results showed that the utilization of short straight steel fibers with 0.8% volume fraction was most efficient at improving the compressive strength while the use of 0.8% long hooked end steel fibers provided better splitting tensile and flexural strengths. Besides, the long hooked end steel fibers with the volume fraction of 0.8% contributed to an excellent deflection hardening behavior resulting in higher load deflection capacity and toughness at peak load, L/600 and L/150. On the other hand, with incorporation of polypropylene fiber, all strength values were decreased regardless of the volume fraction and curing days.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.