Abstract

This paper examines the applications of artificial intelligence (AI) in predicting and optimizing phase change material (PCM) parameters for heat storage and transport systems. The study reviews research on material parameters, focusing on the role of machine learning (ML) in shaping the characteristics of modified PCMs. It summarizes the input and output parameters, as well as the figures of merit criteria, employed in various PCMrelated studies. The paper explores AI's role in enhancing heat transfer and storage in PCMs, highlighting models used to predict the amount of heat stored in PCM-based storage tanks. Also, the application of genetic algorithms (GAs) to optimize the operating parameters of these storage systems is discussed. AI techniques for improving heat transfer processes in PCMs are also reviewed. The prediction quality of different ML methods is analyzed. Other deviations used to evaluate the accuracy of these methods are presented. A third area of focus is the application of AI in systems and energy systems utilizing PCMs. These applications include temperature stabilization in solar systems, maintaining thermal comfort in buildings, ensuring consistent vaccine storage temperatures, and other uses. The study outlines the types of PCMs used in various thermal systems, the AI methods applied, and the criteria for prediction and optimization. Finally, the paper identifies knowledge gaps and research areas requiring further investigation to better understand the potential of ML and GA in optimizing PCM parameters and thermal systems containing PCMs.