A review of adaptive neural control applied to proton exchange membrane fuel cell systems

Proton exchange membrane fuel cell systems are promising technologies for the integration of renewable energy. They pave the way for further emission-reduction and energy autonomy initiatives. However, widespread commercialization still faces several challenges to extend their durability, improve their reliability while reducing their cost. Control strategies included information about the state of heath are among promising levers to tackle these challenges. In this context, an active fault tolerant control strategy based on three modules is introduced. Firstly, a fault diagnosis tool identify the system state of health and detect abnormal conditions. Then, a decision process based on diagnosis results, manages to find a fault strategy mitigation. Finally, a set of controllers, or a re-configurable controller, are used to apply the decision strategy. This third module has to be suited to the real-time specifications of the system. In this context, neural networks-based controllers with adaptive learning appear to be especially appropriate methods for system state of health consideration. For this reason, this paper aims to bring a literature review for adaptive neural-based control applied on proton exchange membrane fuel cell systems. Based on this overview of recent works available, propositions are made to fill the resource gaps about fuel cell control and give some answers to the aforementioned issues. (C) 2019 Elsevier Ltd. All rights reserved.