Premium
Parameters determination of proton exchange membrane fuel cell stack electrical model by employing the hybrid water cycle moth‐flame optimization algorithm
Author(s) -
Ben Messaoud Ramzi
Publication year - 2020
Publication title -
international journal of energy research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.808
H-Index - 95
eISSN - 1099-114X
pISSN - 0363-907X
DOI - 10.1002/er.6065
Subject(s) - proton exchange membrane fuel cell , mean squared error , stack (abstract data type) , voltage , algorithm , control theory (sociology) , empirical modelling , mathematics , fuel cells , engineering , biological system , computer science , statistics , simulation , electrical engineering , chemical engineering , control (management) , artificial intelligence , programming language , biology
Summary In order to properly control the operation of a fuel cell (FC), it is essential to have a precise model of the FC. In this paper, we merged the hybrid water cycle moth‐flame optimization (WCMFO) algorithm and the notion of measurement uncertainty to extract the parameters of the proton exchange membrane fuel cell (PEMFC) by using current‐voltage characteristics (I‐V). The integration of the notion of uncertainty made the proposed approach more robust to disturbance. Consequently, a curve (I‐V) of the model estimated more precise and very similar to the real curve. To validate the performance of our approach, three commercial PEMFCs with their empirical data (I‐V) are examined as Ballard, NedSstack PS6, and BCS 500‐W. The problem of PEMFC models with seven parameters was investigated. The performance analysis is carried out by applying the sum of the squared error (SSE) and the root mean squared error (RMSE) to compare the calculated and empirical data, our approach is affirmed by its large superiority (SSE and RMSE are in the order of 10 −29 and 10 −15 , respectively) compared to other methods recently published in Literature (SSE and RMSE are in the order of 10 −2 and 10 −2 , respectively).