Application of Artificial Neural Networks (ANNS) in Prediction of Compressive Strength of PCM-Integrated Concretes

Phase Change Materials (PCMs) have been proven to enhance the thermal performance of cementitious composites owing to their thermal energy storage (TES) capacity. Nevertheless, they can hamper the compressive strength of the concrete. Several pertinent factors have a complex and non-linear negative influence on the compressive strength, and thus it is difficult to model the mechanical strength development of such composites using conventional statistical procedures. Therefore, this study explores the feasibility of using Artificial Neural Networks (ANNs) to predict the compressive strength of cement mortar and concrete integrating PCM microcapsules. For this purpose, a dataset comprising 160 examples of mixture proportions and 10 input features is used to create the ANN model. The dataset is currently the largest that could be extracted from studies in the open literature. Several statistical metrics are used to evaluate the performance of the proposed model. It is demonstrated that the developed ANN has a very promising capability in predicting the compressive strength of cementitious composites incorporating PCM microcapsules with desirable accuracy.