Prediction of the Effect of Fly Ash on the Unconfined Compressive Strength of Basalt Fiber Reinforced Clay Using Artificial Neural Networks

Abstract

In this study, the effects of fly ash (FA) and basalt fiber (BF) additives on the unconfined compressive strength (qu) of kaolin clay were experimentally investigated, and a dataset was created based on the results. This dataset was used in an artificial neural network (ANN) model to predict the qu based on the additive ratio, water content, and curing time. For this purpose, samples were prepared by adding 1% BF with a length of 24 mm and FA at ratios of 3%, 6%, 9%, 12%, and 15% to the clay, followed by the addition of 25% and 30% water. Unconfined compressive tests were performed before curing and after 28, 42, and 56 days of curing to determine the qu values. The evaluation of the obtained experimental results was carried out by creating an ANN model. To validate the prediction capabilities of the ANN, a comparative analysis was performed using various artificial intelligence models, and the model's overall performance was assessed with a 5-fold cross-validation technique. The evaluations revealed that the ANN model, using data from experimental studies, demonstrated the highest prediction accuracy and was in close agreement with the experimental results. According to the results obtained, the R value of the ANN model was calculated as 0.97, while the RMSE values were found as 0.09, 0.10, 0.06 and 0.04 for pre-curing, 28th day, 42nd day and 56th day, respectively.