Using clean energy is an important way to reduce air pollution. However, the durability and performance degradation of fuel cells as the mainstream restrict their further development. Effective degradation prediction of fuel cells can provide important theoretical basis and research ideas for improving their maintainability and reliability. Therefore, this paper will predict the life of the fuel cell from the algorithm of mathematical modeling, predicting it from the BP neural network first, and we find local optimization. Considering that the fuel cell has complex physical and chemical processes and environmental conditions, the Relevance Vector Machine (RVM) is further used to improve the high-dimensional operation, avoiding the influence of high dimensions on the gradient descent of the BP neural network algorithm, and verifying the confidence interval. After the theoretical model is established, we bring in our own experimental data for prediction. We use the output current as a quantitative study of the degradation of power supply voltage to reflect the degradation of battery performance. We change different output currents to make experiments in order to ensure that the experimental results are universal and get the common rule of battery degradation. The ideas put forward in this paper can be used for predictive maintenance and abnormal replacement of fuel cells, and also have certain reference significance for similar lithium-ion batteries.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.