Heat transfer characteristics of nonlinearly graded metal foam in thermal storage tank: A novel framework model of BP neural network fused with tactical unit algorithm

Metal foams (MF) are widely used in phase change materials (PCMs) due to their high thermal conductivity, high porosity and large specific surface area. These characteristics jointly improve the thermal performance of PCMs. This study investigates the influence of porosity variation (ranging from 0.85 to 0.96) on the thermal behavior of a phase change thermal storage (PCTS) unit. The research finds that while the reduction of porosity significantly improves the heat storage efficiency, it concurrently reduces the overall storage capacity. Specifically, compared to a porosity of 0.96, a porosity of 0.85 leads to a 71.06% increase in efficiency but is accompanied by a 10.51% decrease in capacity. To further optimize the prediction performance, an improved Tactical Unit Algorithm (ITUA), incorporating elite retention, Lévy flight, and Gaussian mutation strategies, is proposed. Compared to conventional algorithms, ITUA exhibits markedly enhanced optimization performance. Furthermore, ITUA is integrated with a backpropagation artificial neural network (BP-ANN) to develop a model of liquid phase distribution during the melting process. To maintain heat storage capacity while enhancing efficiency, both linear and nonlinear porosity distributions are investigated. At an average porosity of 0.95, energy storage efficiency is increased by 58.46% and 68.95% for linear and nonlinear arrangements, respectively, relative to uniform porosity distribution. The proposed model provides valuable guidance for optimizing MF porosity configuration in PCTS systems.