Scholarlink

<p>Hydrogen fuel cells are promising power sources that directly convert chemical energy generated by the chemical reaction of hydrogen and oxygen into electrical energy. However, performance assessment, lifetime management, and integrated management of hydrogen fuel cells are major constraints to their large-scale commercialisation, so this review systematically investigates conventional machine learning and deep learning methods, focusing on their application to performance assessment, lifetime prediction, and integrated management of hydrogen fuel cells. Performance assessment of hydrogen fuel cells is based on two key metrics: voltage and output power. Lifetime prediction involves comparing model predictions with empirical data. Integrated management considers realistic conditions and economic factors to maximise energy efficiency. The accuracy of the model is assessed using metrics such as mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). In addition, the review compares traditional machine learning with deep learning methods and explores their integration in a system management framework.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Review: application of machine learning methods to performance evaluation, lifetime prediction and integrated management of hydrogen fuel cells

  • 期刊论文

  • 发表日期：

    2025年6月11日

查看全文
  • Yingjie Xu,
  • Xiaoke Li,
  • Yang Cao,
  • Kun Liu,
  • Wuyi Ming

摘要

Hydrogen fuel cells are promising power sources that directly convert chemical energy generated by the chemical reaction of hydrogen and oxygen into electrical energy. However, performance assessment, lifetime management, and integrated management of hydrogen fuel cells are major constraints to their large-scale commercialisation, so this review systematically investigates conventional machine learning and deep learning methods, focusing on their application to performance assessment, lifetime prediction, and integrated management of hydrogen fuel cells. Performance assessment of hydrogen fuel cells is based on two key metrics: voltage and output power. Lifetime prediction involves comparing model predictions with empirical data. Integrated management considers realistic conditions and economic factors to maximise energy efficiency. The accuracy of the model is assessed using metrics such as mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). In addition, the review compares traditional machine learning with deep learning methods and explores their integration in a system management framework.