Journal of Energy Chemistry ›› 2023, Vol. 81 ›› Issue (6): 28-41.DOI: 10.1016/j.jechem.2023.02.027

Previous Articles     Next Articles

Multi-objective optimization of the cathode catalyst layer micro-composition of polymer electrolyte membrane fuel cells using a multi-scale, two-phase fuel cell model and data-driven surrogates

Neil Vaz1, Jaeyoo Choi1, Yohan Cha, Jihoon kong, Yooseong Park, Hyunchul Ju*   

  1. Department of Mechanical Engineering, Inha University, 100 Inha-ro Michuhol-Gu, Incheon 22212, Republic of Korea
  • Received:2022-12-27 Revised:2023-02-03 Accepted:2023-02-08 Online:2023-06-15 Published:2023-06-13
  • Contact: * E-mail address: hcju@inha.ac.kr (H. Ju).
  • About author:1 These authors contributed equally to this work.

Abstract: Polymer electrolyte membrane fuel cells (PEMFCs) are considered a promising alternative to internal combustion engines in the automotive sector. Their commercialization is mainly hindered due to the cost and effectiveness of using platinum (Pt) in them. The cathode catalyst layer (CL) is considered a core component in PEMFCs, and its composition often considerably affects the cell performance (Vcell) also PEMFC fabrication and production Cstack costs. In this study, a data-driven multi-objective optimization analysis is conducted to effectively evaluate the effects of various cathode CL compositions on Vcell and Cstack. Four essential cathode CL parameters, i.e., platinum loading (LPt), weight ratio of ionomer to carbon (wtI/C), weight ratio of Pt to carbon (wtPt/c), and porosity of cathode CL (εcCL), are considered as the design variables. The simulation results of a three-dimensional, multi-scale, two-phase comprehensive PEMFC model are used to train and test two famous surrogates: multi-layer perceptron (MLP) and response surface analysis (RSA). Their accuracies are verified using root mean square error and adjusted R2. MLP which outperforms RSA in terms of prediction capability is then linked to a multi-objective non-dominated sorting genetic algorithm II. Compared to a typical PEMFC stack, the results of the optimal study show that the single-cell voltage, Vcell is improved by 28 mV for the same stack price and the stack cost evaluated through the U.S department of energy cost model is reduced by $5.86/kW for the same stack performance.

Key words: Polymer electrolyte membrane fuel cell, Surrogate modeling, Multi-layer perceptron (MLP), Response surface analysis (RSA), Non-dominated sorting genetic algorithm II (NSGA II)