Supervised learning of a regression model based on latent process. Application to the estimation of fuel cell life time

TL;DR

This paper presents a pattern recognition method using feature extraction and regression models to estimate fuel cell lifetime from impedance spectroscopy data, supporting predictive maintenance.

Contribution

It introduces a novel combination of feature extraction and latent variable regression models for fuel cell lifetime estimation from impedance spectra.

Findings

The approach accurately estimates fuel cell lifetime from experimental data.

Feature extraction from impedance spectra improves prediction accuracy.

The method demonstrates feasibility for predictive maintenance applications.

Abstract

This paper describes a pattern recognition approach aiming to estimate fuel cell duration time from electrochemical impedance spectroscopy measurements. It consists in first extracting features from both real and imaginary parts of the impedance spectrum. A parametric model is considered in the case of the real part, whereas regression model with latent variables is used in the latter case. Then, a linear regression model using different subsets of extracted features is used fo r the estimation of fuel cell time duration. The performances of the proposed approach are evaluated on experimental data set to show its feasibility. This could lead to interesting perspectives for predictive maintenance policy of fuel cell.