Modeling and temperature control of a water-cooled PEMFC system using intelligent algorithms

Proton exchange membrane fuel cell (PEMFC) is the most promising future energy source owing to its low operating temperature, high energy efficiency, high power density, and environmental friendliness. In this paper, a comprehensive PEMFC system control-oriented model with parameter identification is developed, which includes various subsystems and components such as the hydrogen supply subsystem, air supply subsystem, thermal management subsystem. To investigate temperature control strategy by the thermal management subsystem, the energy balance equation is used for the PEMFC stack, water tank and radiator to reflect the transient temperature variation during the operation. Four typical temperature control strategies are implemented on the thermal management subsystem and their performances are evaluated in terms of temperature profiles, overshoot and integral absolute error criterion (IAE). Besides, this paper also considers the parasitic power of the fan under different control strategies. It is found that among the four strategies, Case 4 has the best performance on the controlling both water pump and fan with the PID. To improve the control effect further, fuzzy control is introduced to optimize the PID controller of the pump, and the radial basis function (RBF) neural network is introduced to optimize the PID controller of the fan. The results demonstrate that Fuzzy-PID and RBF-PID can achieve a better control effect with 22.66% decrease in IAE of T_st (stack temperature) and 77.56% decrease in IAE of T_in (inlet cooling water temperature).