To enhance the efficiency of phase change heat storage, this study investigates the synergistic effects and parameter interactions of a coupled strategy integrating fins, metal foam, and nanoparticles. A validated numerical model is developed for a shell-and-tube heat storage unit. The influence of porosity and pore density of metal foam, as well as Al₂O₃ nanoparticle concentration, on melting behavior, heat storage rate, and fluid flow features are systematically analyzed. Results indicate that reducing porosity significantly enhances heat conduction, shortening the complete melting time by up to 53.71%. Conversely, increasing pore density markedly suppresses natural convection, reducing the average liquid velocity by 64.62% and consequently extending the melting duration. The incorporation of nanoparticles consistently improves thermal performance; specifically, a 15% concentration reduces the melting time by 25.49%. Notably, a strong synergistic interaction is revealed. The enhancement of nanoparticles is more pronounced in metal foams with lower intrinsic conductivity, yielding an average additional enhancement of 17.24%. The optimal configuration identified in this study comprises metal foam with a porosity of 0.98 and a pore density of 10 PPI, coupled with 15% nanoparticles, achieving a heat storage rate 51.47% higher than the least efficient design. These findings elucidate the underlying coupling mechanisms and provide practical guidelines for the multi-parameter optimization of high-performance composite PCM-based thermal energy storage systems.

Indoor air pollution resulting from volatile organic compounds (VOCs), especially formaldehyde, is a significant health concern needed to predict indoor formaldehyde concentration (C_f) in green intelligent building design. This study develops a thermal and wet coupling calculation model of porous fabric to account for the migration of formaldehyde molecules in indoor air and cotton, silk, and polyester fabric with heat flux in Harbin, Beijing, Xi’an, Shanghai, Guangzhou, and Kunming, China. The time-by-time indoor dry-bulb temperature (T), relative humidity (RH), and C_f, obtained from verified simulations, were collated and used as input data for the long short-term memory (LSTM) of the deep learning model that predicts indoor multivariate time series C_f from the secondary source effects of indoor fabrics (adsorption and release of formaldehyde). The trained LSTM model can be used to predict multivariate time series C_f at other emission times and locations. The LSTM-based model also predicted C_f with mean absolute percentage error (MAPE), symmetric mean absolute percentage error (SMAPE), mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) that fell within 10%, 10%, 0.5, 0.5, and 0.8, respectively. In addition, the characteristics of the input dataset, model parameters, the prediction accuracy of different indoor fabrics, and the uncertainty of the data set are analyzed. The results show that the prediction accuracy of single data set input is higher than that of temperature and humidity input, and the prediction accuracy of LSTM is better than recurrent neural network (RNN). The method’s feasibility was established, and the study provides theoretical support for guiding indoor air pollution control measures and ensuring human health and safety.