Implementation of soft-computing models for prediction of flexural strength of pervious concrete hybridized with rice husk ash and calcium carbide waste

Pervious concrete is a kind of concrete used for storm-water management due to its high porosity and permeability. However, its’ flexural strength as the most desirable mechanical properties was predicted in this study. The paper aims to demonstrate three soft-computing models, i.e., artificial neural network (ANN), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS) were applied for the prediction of flexural strength (σf) of pervious Concrete (PC) incorporated with calcium carbide waste (CCW) and rice husk ash (RHA) as supplementary cementation materials. The models were trained on the experimental data obtained by replacing cement content from 0 to 10% RHA and 0 to 20% CCW in the PC at 3-, 7-, and 28-days curing age. The results indicated that three AI-based models ANN, SVM, and ANFIS have predicted the flexural strength with high accuracy in both the testing and training stages, following the performance evaluation involving; Nash–Sutcliffe efficiency (NSE), correlation coefficient (CC), mean square error (MSE), and root mean square error (RMSE). All the input variables contribute to the accuracy of the model. The ANFIS-M5 (NSE = 0.9997 and RMSE = 0.0044 in testing phase) proved merit despite the acceptable accuracy obtained in the ANN model. The hybrid ANFIS predicts the flexural strength of hybridized pervious concrete with the highest accuracy compared to the other two soft-computing models.