{"title":"Prediction of Slump in Concrete using Artificial Neural Networks","authors":"V. Agrawal, A. Sharma","country":null,"institution":"","volume":45,"journal":"International Journal of Civil and Environmental Engineering","pagesStart":279,"pagesEnd":287,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/8773","abstract":"High Strength Concrete (HSC) is defined as concrete\r\nthat meets special combination of performance and uniformity\r\nrequirements that cannot be achieved routinely using conventional\r\nconstituents and normal mixing, placing, and curing procedures. It is\r\na highly complex material, which makes modeling its behavior a very\r\ndifficult task. This paper aimed to show possible applicability of\r\nNeural Networks (NN) to predict the slump in High Strength\r\nConcrete (HSC). Neural Network models is constructed, trained and\r\ntested using the available test data of 349 different concrete mix\r\ndesigns of High Strength Concrete (HSC) gathered from a particular\r\nReady Mix Concrete (RMC) batching plant. The most versatile\r\nNeural Network model is selected to predict the slump in concrete.\r\nThe data used in the Neural Network models are arranged in a format\r\nof eight input parameters that cover the Cement, Fly Ash, Sand,\r\nCoarse Aggregate (10 mm), Coarse Aggregate (20 mm), Water,\r\nSuper-Plasticizer and Water\/Binder ratio. Furthermore, to test the\r\naccuracy for predicting slump in concrete, the final selected model is\r\nfurther used to test the data of 40 different concrete mix designs of\r\nHigh Strength Concrete (HSC) taken from the other batching plant.\r\nThe results are compared on the basis of error function (or\r\nperformance function).","references":null,"publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 45, 2010"}