Abstract
This paper reports our initial development of simulation-informed machine learning algorithms for failure diagnostics in solid oxide fuel cell (SOFC) systems. We used physics-based models to simulate electrochemical impedance spectroscopy (EIS) response of a short SOFC stack under normal conditions and under three different failure modes: fuel maldistribution, delamination, and oxidant gas crossover to the anode channel. These data were used to train a support vector machine (SVM) model, which is able to detect and differentiate these failures in simulated data under various conditions. The SVM model can also distinguish these failures from simulated uniform degradation that often occurs with long-term operation. These encouraging results are guiding our ongoing efforts to apply EIS as a failure diagnostic for real SOFC cells and short stacks.
Publisher
The Electrochemical Society
Subject
Materials Chemistry,Electrochemistry,Surfaces, Coatings and Films,Condensed Matter Physics,Renewable Energy, Sustainability and the Environment,Electronic, Optical and Magnetic Materials
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献