Temperature and humidity are two important interconnected factors in the performance of PEMFCs (Proton Exchange Membrane Fuel Cells). The fuel and oxidant humidity and stack temperature in a fuel cell were analyzed in this study. There are many factors that affect the temperature and humidity of the stack. We adopt the fuzzy control method of multi-input and multi-output to control the temperature and humidity of the stack. A model including a driver, vehicle, transmission motor, air feeding, electrical network, stack, hydrogen supply and cooling system was established to study the fuel cell performance. A fuzzy controller is proven to be better in improving the output power of fuel cells. The three control objectives are the fan speed control for regulating temperature, the solenoid valve on/off control of the bubble humidifier for humidity variation and the speed of the pump for regulating temperature difference. In addition, the results from the PID controller stack model and the fuzzy controller stack model are compared in this research. The fuel cell bench test has been built to validate the effectiveness of the proposed fuzzy control. The maximum temperature of the stack can be reduced by 5 °C with the fuzzy control in this paper, so the fuel cell output voltage (power) increases by an average of approximately 5.8%.

The cold start of fuel cells limits their wide application. Since the water produced by fuel cells takes up more space when it freezes, it may affect the internal structure of the stack, causing collapse and densification of the pores inside the catalytic layer. This paper mainly analyzes the influence of different startup strategies on the stack cold start, focusing on the change in the stack temperature and the ice volume fraction of the catalytic layer. When designing a startup strategy, it is important to focus not only on the optimization of the startup time, but also on the principle of minimizing the damage to the stack. A lumped parameter cold-start model was constructed, which was experimentally verified to have a maximum error of 8.9%. On this basis, a model predictive control (MPC) algorithm was used to control the starting current. The MPC cold-start strategy reached the freezing point at 17 s when the startup temperature was −10 °C, which is faster than other startup strategies. Additionally, the time to ice production was controlled to about 20 s. Compared with the potentiostatic strategy and maximum power strategy, MPC is optimal and still has great potential for further optimization.

With the growing concerns over the energy crisis and environmental pollution, fuel cells have attracted increasing attention. Proton exchange membrane fuel cells (PEMFCs) have promising prospects due to their economic efficiency, low noise, and minimal environmental pollution. However, the existing commercial testing systems for PEMFCs suffer from limited functionalities and lack of scalability. In this study, we propose the design of a testing platform specifically tailored for water-cooled PEMFCs with a power greater than 1 kW. The functionality of the testing platform is verified through static and dynamic testing, demonstrating its compliance with the required standards. Furthermore, a fault diagnosis model for fuel cell stacks is developed based on the back-propagation (BP) neural network, achieving an overall accuracy rate of over 95% for fault classification.