Enhancing solar thermal collector systems for hot water production through machine learning-driven multi-objective optimization with phase change material (PCM)

Energy storage and supply in solar thermal collector systems rely heavily on phase change materials (PCM). It is vital to establish the appropriate values for energy discharge time (tPCM) and net amount of stored energy (Qnet) within the PCMs in order to increase the efficiency of solar thermal collectors. For this study, we implemented a multi-objective evolutionary algorithm based on decomposition (MOEA/D) for the optimization process using the MATLAB simulator software. The simulation findings show that, under ideal circumstances where tPCM is large and Qnet is low, these two goal functions are inversely connected to one another. According to an analysis of how input parameters affect the objective functions, the mass of PCM is minimized and the mass flow rate of the input water is increased under ideal circumstances. The relationship between the tube's inner diameter and the tPCM objective function shows that an increase in the tube's diameter corresponds to an increase in the energy discharge time. The amount of stored energy in the PCM increases when the system parameters are held constant while the tube diameter is increased. Additionally, we investigated the effects of several solid PCM materials on the discharge time and the energy stored.