Abstract

Small air-cooled proton exchange membrane fuel cell (PEMFC) systems are increasingly relevant for portable and distributed applications, yet practical modeling and monitoring methods remain limited: high-fidelity physics-based models are too costly for real-time use, while purely data-driven models discard physical interpretability. This thesis develops an experimentally grounded gray-box framework for the characterization, reduced-order modeling, and IoT-enabled monitoring of a small hydrogen PEMFC system. A low-order nonlinear state-space model couples an electrochemical voltage layer to a lumped thermal layer, with parameters identified in stages using self-adaptive differential evolution. Identifiability analysis shows that static loss parameters are well constrained, while dynamic parameters are resolved only in combination. The model generalizes to independent data with out-of-sample R² values of 0.91 for voltage and 0.82 for temperature; the electrical layer transfers robustly, whereas the thermal layer remains reliable only within its characterized envelope, providing a practical foundation for future digital-twin development.

Date of publication

2026

Document Type

Thesis

Language

english

Persistent identifier

http://hdl.handle.net/10950/5113

Committee members

Mohammad Biswas, Shih-Feng Chou , Hayder Abdul-Razzak

Degree

Master of Science in Mechanical Engineering

Share

COinS