New parameters identification of Proton exchange membrane fuel cell stacks based on an improved version of African vulture optimization algorithm

Abstract

Model parameters identification of the fuel cells has several applications in practice. However, due to its nonlinear dynamic and its complicated nature, solving it based on most of the classic methods is too hard. Also, using any kind of methods based on soft computing does not also provide a satisfying result which can be proved based on the no free lunch theorem. In the present study, a new methodology has been proposed for optimum parameters identification of the Proton exchange membrane fuel cell (PEMFC) stacks. Here, an improved version of African vulture optimizer (IAVO) is organized for this purpose. To prove the accuracy of the proposed method, it is applied to three standard test cases and the results have been compared with some five latest techniques. The results showed that the proposed IAVO algorithm with 1.98(±0.49), 0.03(±0.02), and 1.08(±0.47) parameter fitting value for NedStackPS6, BCS 500 W, and SR-12 500 W, respectively, provides the best results with minimum error value. This shows that the efficiency of the proposed IAVO algorithm is too better than the other methods in parameter identification of the PEMFC stacks.

Keywords

• PEMFC
• Parameters identification
• Improved African vulture optimization algorithm
• Convergence profile
• Sum of squared error
• NedStackPS6