Designing Machine Learning Models for Predictive Analysis of Pressure Drop and Temperature in Free-Breathing Polymer Electrolyte Membrane Fuel Cell Stacks to find Optimal Fabrication Parameters

Climate change has emerged as one of the most critical problems of the 21st century, driven by the rise in greenhouse gas emissions. The polymer electrolyte membrane fuel cell (PEMFC) is a device that converts chemical energy into clean electricity with zero emissions. The proposed research aims to utilize machine learning algorithms to predict the pressure drop and temperature in PEMFCs by using data sets related to Singapore’s state-of-the-art PEMFCs. By applying different data pre-processing methods, the predictive algorithms will identify optimal fabrication parameters and operating conditions such that these fuel cells operate at their highest efficiency, while reducing cost. As a result, this research will lead to the improvement of PEMFCs such that they can be a competitive alternative to fossil fuel-based energy systems.

Faculty Supervisor:

Arthur Chan

Student:

Partner:

National University of Singapore

Discipline:

Engineering

Sector:

Education

University:

University of Toronto

Program: