Abstract
This study presents an estimate of various strength and toughness properties of steel–polyester hybrid fibre-reinforced concrete obtained using artificial neural network techniques. Input parameters used in the development of single and hybrid fibre-reinforced concrete composites in the experimental programme were given as input variables in artificial neural network models. The constituents of concrete, such as cement, fly ash, silica fume, sand, coarse aggregate, water, chemical admixture, steel fibre, polyester fibre and its combinations, were used as input parameters in artificial neural network modelling. Two artificial neural network models were proposed, trained, tested and validated to predict the compressive strength, split tensile strength, flexural strength, impact resistance and energy absorption capacity of single and hybrid fibre-reinforced concrete composites. The performances of these two artificial neural network models were compared based on probabilistic analysis. Regression plots made between experimental output and predicted output values yielded good correlation. From the regression plots, it is understood that this neural network is an effective tool in predicting the strength or toughness of the steel–polyester hybrid fibre-reinforced composites. By adopting these neural network techniques, expensive laboratory arrangements, costs of testing, and waits for curing time could be saved.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call