Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Aging modeling and lifetime prediction of a proton exchange membrane fuel cell using an extended Kalman filter

Serigne Daouda Pene, Antoine Picot, Fabrice Gamboa, Nicolas Savy, Christophe Turpin, Amine Jaafar

TL;DR

The paper addresses aging modeling and lifetime prediction for Proton Exchange Membrane Fuel Cells (PEMFC) by integrating parametric identification, dynamic aging laws, and Extended Kalman Filtering (EKF). It develops a quasi-static electrochemical model, time-evolving parameters, and a Monte Carlo–augmented EKF framework to forecast voltage degradation and estimate Remaining Useful Life (RUL) under fixed operating conditions. A key contribution is the breakpoint-aware modeling of the limiting current density $j_{lim}$ and a change-detection criterion that triggers regime shifts, enabling more accurate long-term predictions. Results on a simulated aging database show accurate voltage forecasts (max MAPE around 0.82%) and precise RUL estimates (max mean APE around 0.22%), with the approach designed to quantify uncertainty and support prognostic health management for automotive PEMFC systems.

Abstract

This article presents a methodology that aims to model and to provide predictive capabilities for the lifetime of Proton Exchange Membrane Fuel Cell (PEMFC). The approach integrates parametric identification, dynamic modeling, and Extended Kalman Filtering (EKF). The foundation is laid with the creation of a representative aging database, emphasizing specific operating conditions. Electrochemical behavior is characterized through the identification of critical parameters. The methodology extends to capture the temporal evolution of the identified parameters. We also address challenges posed by the limiting current density through a differential analysis-based modeling technique and the detection of breakpoints. This approach, involving Monte Carlo simulations, is coupled with an EKF for predicting voltage degradation. The Remaining Useful Life (RUL) is also estimated. The results show that our approach accurately predicts future voltage and RUL with very low relative errors.

Aging modeling and lifetime prediction of a proton exchange membrane fuel cell using an extended Kalman filter

TL;DR

The paper addresses aging modeling and lifetime prediction for Proton Exchange Membrane Fuel Cells (PEMFC) by integrating parametric identification, dynamic aging laws, and Extended Kalman Filtering (EKF). It develops a quasi-static electrochemical model, time-evolving parameters, and a Monte Carlo–augmented EKF framework to forecast voltage degradation and estimate Remaining Useful Life (RUL) under fixed operating conditions. A key contribution is the breakpoint-aware modeling of the limiting current density and a change-detection criterion that triggers regime shifts, enabling more accurate long-term predictions. Results on a simulated aging database show accurate voltage forecasts (max MAPE around 0.82%) and precise RUL estimates (max mean APE around 0.22%), with the approach designed to quantify uncertainty and support prognostic health management for automotive PEMFC systems.

Abstract

This article presents a methodology that aims to model and to provide predictive capabilities for the lifetime of Proton Exchange Membrane Fuel Cell (PEMFC). The approach integrates parametric identification, dynamic modeling, and Extended Kalman Filtering (EKF). The foundation is laid with the creation of a representative aging database, emphasizing specific operating conditions. Electrochemical behavior is characterized through the identification of critical parameters. The methodology extends to capture the temporal evolution of the identified parameters. We also address challenges posed by the limiting current density through a differential analysis-based modeling technique and the detection of breakpoints. This approach, involving Monte Carlo simulations, is coupled with an EKF for predicting voltage degradation. The Remaining Useful Life (RUL) is also estimated. The results show that our approach accurately predicts future voltage and RUL with very low relative errors.
Paper Structure (12 sections, 38 equations, 20 figures, 2 tables, 2 algorithms)

This paper contains 12 sections, 38 equations, 20 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Methodology
  3. Data source
  4. Electrochemical model
  5. Identification of the aging parameters
  6. Governing equations of aging
  7. Extended Kalman Filter
  8. Lifetime prediction framework
  9. Results and discussion
  10. State variables and voltage prediction
  11. RUL estimation
  12. Conclusions and future works

Figures (20)

  • Figure 1: Initial experimental polarization curve.
  • Figure 2: Experimental impedance spectroscopies for different levels of current density.
  • Figure 3: Evolution of the experimental ohmic resistance as a function of current density.
  • Figure 4: Simulated polarization curves (top) and ohmic resistance (bottom) as functions of current density every 500 hours.
  • Figure 5: Simulated voltage over time, with current density fixed at $1A/cm^2$.
  • ...and 15 more figures