Search

Proton exchange membrane fuel cell (PEMFC) is a promising future power source, which uses hydrogen energy to generate electricity with the byproduct of water. In general, PEMFC includes several strongly coupled subsystems with high nonlinearity and complex dynamic processes. Therefore, proper control strategies are crucial for a reliable and effective PEMFC operation. This paper aims to carry out a comprehensive and systematic overview of state-of-the-art PEMFC control strategies. Based on a thorough investigation of 180 literatures, these control strategies are classified into nine main categories, including proportional integral derivative (PID) control, adaptive control (APC), fuzzy logic control (FLC), robust control, observer-based control, model predictive control (MPC), fault tolerant control (FTC), optimal control and artificial intelligence control. Furthermore, a comprehensive evaluation and detailed summary of their control deigns, objectives, performance, applications, advantages/disadvantages, complexity, robustness and accuracy are conducted thoroughly. Finally, five valuable and insightful perspectives/recommendations are proposed for future research. [Display omitted] • Summarize nine groups of PEMFC system control strategies. • Control complexity, robustness, and accuracy are summarized and evaluated. • Present the advantages/disadvantages of all methods. • Five invaluable and insightful perspectives/recommendations are proposed. [ABSTRACT FROM AUTHOR]

It is essential to develop an accurate model of proton exchange membrane fuel cell (PEMFC) for a reliable operation and analysis, in which unknown parameters usually need to be determined. The inherent nonlinear, strong coupling, and diversification of PEMFC model seriously hinder traditional methods to identify the parameters. For the sake of overcoming these thorny obstacles, Levenberg-Marquardt backpropagation (LMBP) algorithm based on artificial neural networks (ANNs) is proposed for PEMFC parameter identification. Furthermore, the performance of LMBP is thoroughly evaluated and compared with four typical meta-heuristic algorithms under three cases. Simulation results indicate that LMBP performs a higher accuracy and faster speed for parameter identification. In particular, accuracy and convergence speed can achieve as much as 99.8% and 95.9% growth via LMBP, respectively. • LMBP algorithm is applied to PEMFC parameter identification for the first time. • Performance of LMBP is proved via comparison with four meta-heuristic algorithms. • Feasibility of the proposed method is investigated based on a Ballard-Mark-V PEMFC. [ABSTRACT FROM AUTHOR]