Prediction of Fresh and Hardened Properties of Self-Consolidating Concrete Using Neurofuzzy Approach

Self-consolidating concrete (SCC) developed in Japan in the late 80s has enabled the construction industry to reduce demand on the resources, improve the work conditions and also reduce the impact on the environment by elimination of the need for compaction. This investigation aimed at exploring the potential use of the neurofuzzy (NF) approach to model the fresh and hardened properties of SCC containing pulverised fuel ash (PFA) as based on experimental data investigated in this paper. Twenty six mixes were made with water-to-binder ratio ranging from 0.38 to 0.72, cement content ranging from 183 to 317 kg/m3 , dosage of PFA ranging from 29 to 261 kg/m3 , and percentage of superplasticizer, by mass of powder, ranging from 0 to 1%. Nine properties of SCC mixes modeled by NF were the slump flow, JRing combined to the Orimet, JRing combined to cone, V-funnel, L-box blocking ratio, segregation ratio, and the compressive strength at 7, 28, and 90 days. These properties characterized the filling ability, the passing ability, the segregation resistance of fresh SCC, and the compressive strength. NF model is constructed by training and testing data using the experimental results obtained in this study. The results of NF models were compared with experimental results and were found to be quite accurate. The proposed NF models offers useful modeling approach of the fresh and hardened properties of SCC containing PFA.