Proton-exchange membrane fuel cells (PEMFCs) play a crucial role in the transition to sustainable energy systems. Accurately estimating the state of health (SOH) of PEMFCs under dynamic operating conditions is essential for ensuring their reliability and longevity. This study designed dynamic operating conditions for fuel cells and conducted durability tests using both crack-free fuel cells and fuel cells with uniform cracks. Utilizing deep learning methods, we estimated the SOH of PEMFCs under dynamic operating conditions and investigated the performance of long short-term memory networks (LSTM), gated recurrent units (GRU), temporal convolutional networks (TCN), and transformer models for SOH estimation tasks. We also explored the impact of different sampling intervals and training set proportions on the predictive performance of these models. The results indicated that shorter sampling intervals and higher training set proportions significantly improve prediction accuracy. The study also highlighted the challenges posed by the presence of cracks. Cracks cause more frequent and intense voltage fluctuations, making it more difficult for the models to accurately capture the dynamic behavior of PEMFCs, thereby increasing prediction errors. However, under crack-free conditions, due to more stable voltage output, all models showed improved predictive performance. Finally, this study underscores the effectiveness of deep learning models in estimating the SOH of PEMFCs and provides insights into optimizing sampling and training strategies to enhance prediction accuracy. The findings make a significant contribution to the development of more reliable and efficient PEMFC systems for sustainable energy applications.

To improve the heat collection performance of flat plate solar collectors, a corrugated flat plate solar collector (CFPSC) with a triangular collector tube was first innovatively designed in this paper. The effect of various nanofluids that are used as working fluid on the heat collection performance of CFPSC was comprehensively analyzed based on the heat collection characteristics test system and numerical simulation model. The results indicate that when CuO and Al₂O₃ were used as nanoparticles, the heat collection stabilization time of the nanofluids for which ethylene glycol (EG) was used as the base fluid was 12.4~28.6% longer than that of the nanofluids for which water was used as the base fluid. Moreover, when the base fluid was EG, the temperature difference of CuO-EG nanofluid under different radiation intensities was about 5.8~19.2% higher than that of water. Furthermore, the heat collection performance of CuO nanofluids and Al₂O₃ nanofluids was superior to TiN nanofluids. Specifically, the heat collection of CuO-EG nanofluid was 2.9~4% higher than that of TiN-EG nanofluid at different radiation intensities. Therefore, using nanofluids as a working medium and designing a flat plate solar collector with triangular collector tubes can significantly improve the collector performance.

A novel method characterizing the air backflow of the underhood in order to improve the thermal efficiency of the air conditioning system (ACS) and reduce the energy consumption of PHEV is proposed in this paper. In addition, a 1D model for analyzing air backflow occurring in the underhood is established and a CFD method for calculating air backflow rate and distribution is proposed. It is found that the decrease in the air backflow rate of the underhood helps to improve the refrigeration capacity of the ACS, and when the backflow ratio cannot be reduced below 10%, the air backflow should be distributed as evenly as possible at the front end of the condenser. Moreover, in order to eliminate the impact of backflow on the underhood of PHEV, the gap between the radiator and the bracket is sealed and the gap around the air guide is reduced. Compared with the original structure, the backflow rate of the optimized structure is reduced from 32.7% to 9.3% and the cabin temperature can be reduced by 3–5 °C.