Estimation of properties of ultra great workability concrete by optimized ANFIS models

Abstract

The mechanical properties of the ultra-great workability concrete (UGWC) are deeply related to the weights of components, curing period and condition, and occasionally property of admixtures. This study aimed to appraise the usefulness of the adaptive neuro-fuzzy inference system (ANFIS) technique for forecasting the compressive strength of UGWC and enhancing the accuracy of the literature. To outline the forecasting process, two improved ANFIS were suggested, in which determinative variables of them were determined by metaheuristic algorithms named imperialist competitive algorithm (ICA) and multi-verse optimizer (MVO) algorithms. For this purpose, 170 data samples were collected from published literature separated accidentally for the train and test phase. The calculated performance criteria for proposed ANFIS models demonstrate that both ICA-ANFIS and MVO-ANFIS models can result in justifiable workability for fc of the UGWC prediction procedure. The MVO-ANFIS model could outperform ICA-ANFIS regarding all criteria. For instance, the value of R2 and VAF for the ICA-ANFIS model are roughly smaller than the MVO-ANFIS model, at 0.9012 and 90% in the training dataset and 0.8973 and 89% in the testing stage, respectively. While the best values of criteria have belonged to the MVO-ANFIS model, with R2 at 0.937 and 0.944 for the train and test phases, respectively. Overall, the hybrid MVO-ANFIS model can obtain higher workability than ICA-ANFIS and literature (R2 at 0.801), where causes are recognized as the proposed model.