In energy storage and conversion systems, the working condition can have a significant influence on their performance. In this article, a phase change material (PCM) block in an enclosure containing a participating medium is studied under the combined impact of nanofluid natural convection and volumetric radiation. The object is to determine the optimal condition that enhances both energy storage and heat transfer performance. For this purpose, the lattice Boltzmann method (LBM) was implemented to solve the governing equations for flow, energy, phase change, and radiative transfer. The simulation results showed that the interaction effects of radiation and buoyancy influence the flow and temperature distribution within the system. Then, an artificial neural network (ANN) model was developed using the obtained data from the numerical simulation. This model was able to provide results within seconds, compared to the time-consuming numerical simulation. Genetic algorithm and particle swarm optimization were both used to find optimal conditions using the developed ANN model. Both optimization methods found similar optimal values, which were validated through numerical simulation. Using the obtained optimal solution can enhance the energy transfer performance by 3.34% and energy storage by 7.86%. Optimization based on LBM-ANNs provided a reliable and computationally efficient tool for the intelligent design of PCM thermal storage units operating under combined heat transfer.
Darani et al. (Sun,) studied this question.