An Mrfo Based Artificial Neural Network Based Prediction of Geopolymer Containing Waste Fibre Performance

Abstract

Geopolymer concrete (GPC) based on fly ash (FA) is being studied as a possible alternative solution with a lower environmental impact rather than the use of Portland cement based composites. However, the accuracy of the strength prediction still needs to be improved. This study was based on the investigation of various types of machine learning (ML) approaches to predict the compressive strength (C-S) of GPC. This paper proposes a novel approach to predict the compressive strength (C-S) of GPC utilizing Manta Ray Foraging Optimization (MRFO) based on Artificial Neural Network (ANN). Manta ray has three foraging behaviors like chain foraging, cyclone foraging, and somersault foraging for solving various optimization problems. The coefficient of determination (R2) is used to measure how accurate the results are, which usually ranged from 0 to 1. ANN is utilized to forecast the optimized outcomes. Various statistical assessment criteria, such as the coefficient of determination, the mean-absolute percentage deviation, and root-mean-square deviation, were used to evaluate the efficiency of the developed models. The cross-validation technique (k-fold) confirmed the model's performance. The results indicated that the ANN-MRFO model predicted the C–S of FA-GPC mixtures better than the other models. Also, the sensitivity analysis of the proposed model shows that the curing temperature, the ratio of alkaline liquid to the binder, and the amount of sodium silicate are the most important parameters for estimating the C–S of the FA-GPC.