Supervised learning of a regression model based on latent process. Application to the estimation of fuel cell life time
This work addresses predictive maintenance for fuel cells, which is an incremental improvement in a domain-specific application.
The paper tackles the problem of estimating fuel cell lifetime from electrochemical impedance spectroscopy measurements by extracting features from real and imaginary parts of the impedance spectrum and using a linear regression model with different feature subsets. The approach is evaluated on experimental data to demonstrate feasibility, with potential applications in predictive maintenance for fuel cells.
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.