An accurate voltage prediction associated with uncertainty quantification is of great importance to predict the remaining useful life for proton exchange membrane fuel cell in automobile applications. This paper achieves the remaining useful life prediction using deep neural networks, with an emphasis on uncertainty quantification in voltage prognostics for proton exchange membrane fuel cell systems. The trend and pattern of voltage degradation data was investigated by using long-short term memory and the voltage prediction trend was represented with prediction interval. The experimental results show that the deep learning model with corresponding uncertainty techniques can achieve prediction root mean square error values within 0.02 and represent the voltage prediction with a prediction interval.
Deep Uncertainty Quantification of Prognostic Techniques for Proton Exchange Membrane Fuel Cell
Sae Technical Papers
Vehicle Electrification and Powertrain Diversification Technology Forum Part II ; 2021
2022-02-14
Conference paper
English
Deep Uncertainty Quantification of Prognostic Techniques for Proton Exchange Membrane Fuel Cell
British Library Conference Proceedings | 2022
|Prognostic methods for proton exchange membrane fuel cell under automotive load cycling: a review
IET | 2020
|Proton Exchange Membrane Fuel Cell Performance Modeling
British Library Conference Proceedings | 1998
|Internally Humidified Proton Exchange Membrane Fuel Cell
British Library Conference Proceedings | 1994
|Internally humidified proton exchange membrane fuel cell
AIAA | 1994
|