For the operation process of proton exchange membrane fuel cells (PEMFCs) system, fault diagnosis plays a crucial role in ensuring the safety and reliability of system. To improve the accuracy and rapidity of fault diagnosis, a fault diagnosis method of PEMFC based on data space feature decision tree group (DTS) and extreme learning machine (ELM) is proposed. Firstly, principal component analysis (PCA) is used to reduce the dimension of sensor data such as current, temperature and gas flow rate of system, which reflects the operating states of fuel cell. Besides, spatial features of system can be extracted and processed by random rotation matrix. Furthermore, multiple sets of spatial rotation feature data are set to diagnose the health state of fuel cell system by combining decision tree group and extreme learning machine (DTS-ELM). Finally, the proposed method was verified and analyzed, and the experimental results indicate that this method can quickly identify four operating states such as normal state, flooding, membrane dying and hydrogen leakage. The diagnostic accuracy and operating time of this method are 99.54% 0.261s, respectively. Therefore, on-line rapid fault diagnosis of proton exchange membrane fuel cell system can be realized by the proposed method.

Electrochemical impedance spectroscopy (EIS) has broad application prospects in the field of structural analysis and performance optimization of proton exchange membrane fuel cells (PEMFC), and the establishment of an equivalent impedance model based on EIS can intuitively and accurately characterize the internal characteristics of fuel cells. In this paper, an EIS diagram is drawn based on experimental data, and an equivalent impedance model that can well characterize PEMFC is proposed, and compared with commonly used equivalent models. The correspondence between each topology in the model design and the actual PEMFC electrochemical process is explained, and the electrochemical reaction principle of the catalytic layer is explained based on the model. The fitting analysis shows that the accuracy (chi-square error) of the designed model on the experimental data is improved by about 58.16%. This model can guide the process of EIS image analysis and establishing equivalent circuit models, and provide guiding ideas for related mechanism research.

Thermal management control of cathode open PEMFC system is important for its durability and reliability. To adjust the temperature of PEMFC stack to near the optimal temperature, this paper adopted the control method of second-order ADRC to realize the optimal output of power. On this basis, an improved ADRC thermal management control method for fuel cell system based on sliding mode observer was proposed, and relevant control parameters were also adjusted. A PEMFC thermal management control platform had been built to compare and analyze the traditional strategy with the proposed improvement strategy. The experimental results show that compared with traditional control methods, the proposed strategy significantly reduces the overshoot and response time of the fuel cell under load and unload conditions. At the same time, it can quickly and stably track the optimal control temperature of the system, reduce the output steady-state error range, ensure that the system operates more smoothly, and effectively improve the efficiency and output performance of the fuel cell.