Multi-objective Newton-Raphson-based optimizer for fractional-order control of PEM fuel cells

This paper proposes a novel Multi-objective Newton-Raphson-based Optimizer (MONRBO) for solving multi-objective optimization problems. The proposed algorithm adopts the nondominated sorting and the crowding distance sorting techniques to effectively explore the Pareto front. The performance of the proposed MONRBO algorithm is validated using a set of constrained and unconstrained benchmark problems. Results demonstrate the competitive capabilities of the proposed MONRBO algorithm compared to established algorithms including the Nondominated Sorting Genetic Algorithm-II (NSGA-II), Multi-objective Evolutionary Algorithm based on Decomposition (MOEA-D), and Multi-objective Particle Swarm Optimization with Crowding Distance (MOPSO-CD). To further validate its practical applicability, the proposed MONRBO algorithm is employed to obtain the Pareto front of conflicting objectives for an observer-based nonlinear fractional-order PI^λD^μ controller applied to the PEM fuel cell air-feeding system. The first objective is preventing oxygen starvation by minimizing the integral of time-weighted absolute error between the reference and the actual oxygen excess ratio. The second objective is minimizing the compressor power to increase the net power output of the PEMFC stack. Results prove the efficiency of the proposed MONRBO algorithm for solving the PEMFC air-feeding multi-objective control problem.