Optimal proton exchange membrane fuel cell modelling based on hybrid Teaching Learning Based Optimization – Differential Evolution algorithm

Simulation proton exchange membrane fuel cell (PEMFC) performance accurately is a challenging process. Many mathematical models have been existed, yet due to lack of accurate parameter estimations, considerable errors might occur. Nowadays, meta-heuristic optimization algorithms have been successfully applied for parameter identification of PEMFC models. In this study, Teaching Learning Based Optimization method (TLBO) is hybridized with Differential Evolution (DE) algorithm for successful estimation of unknown PEMFC model parameters. Efficiency of the proposed algorithm is tested with several benchmark problems. A case study taken from the literature has been performed by hybrid TLBO–DE algorithm and other optimization methods such as Melody Search (MS), Backtracking Search (BS), Artificial Cooperative Search (ACS), Quantum behaved Particle Swarm Optimization (QPSO), Bat algorithm (BAT), Intelligent Tuned Harmony Search (ITHS) and Cuckoo Search (CS). TLBO–DE algorithm surpasses all these optimizers in terms of solution quality and accuracy.