A novel hybrid radial basis function method for predicting the fresh and hardened properties of self-compacting concrete

Document Type : Original Article


Department of industrial, civil and road building, М.auezov south Kazakhstan state university, Kazakhstan


It is observed from the published literature that there were so limited studies concentrating on predicting both fresh or hardened properties of self-compacting concrete (SCC). Hence, it is tried to develop models for predicting the fresh and hardened properties of SCC by the optimized radial basis function neural network (RBFNN) method. The RBFNN method's key parameters are optimized using ant-lion optimization (ALO) and biogeography optimization (BBO) algorithms. The considered properties of SCC in the fresh phase are the L-box test, V-funnel test, slump flow, and compressive strength (CS) in the hardened phase. Results demonstrate powerful potential in the learning section as well as approximating in the testing phase. It means that the correlation between observed and predicted properties of SCC from hybrid models is acceptable so that it represents high accuracy in the training and approximating process. Regarding D flow, L-box, V-funnel, and CS, the results of ALO-RBFNN were better than BBO-RBFNN and literature. Overall, the RBFNN model developed by ALO outperforms others, which depicts the capability of the ALO algorithm for determining the optimal parameters of the considered method.