Novel optimized closed-loop fuzzy control for maximum power tracking of proton exchange membrane fuel cell

The present era has observed a demanding reliance on non-conventional energy systems such as solar, wind, and fuel cells (FC) aiming to reduce the greenhouse effect, global warming, and dependency on fossil fuels. The potential of low-carbon substitutes, namely FC, has been prioritized in this regard. However, the output of the FC is not stable, but varies under variable scenarios. Subsequently, this work presents an advanced type of fuzzy logic integrated control mechanism to seek a stable operating point for proton exchange membrane FC. In this effect, grey wolf optimization optimizes the rule base of closed-loop type-2 fuzzy logic. Eventually, neurons of a neural network are trained to proffer the optimized rules to the control topology to cope with real-time uncertainties, thus optimizing the control parameters in real time; therefore, real-time scenarios can be achieved. Consequently, the results are evaluated and analyzed to divulge the potency of the proposed mechanism, thereby exhibiting an improved dynamic response with 58.38 % faster tracking in an effectual steady-state scenario that ensures the goals of energy efficiency, reliability, and cost-effectiveness.