Estimation of fuel cell operating time for predictive maintenance strategies

Abstract

One of the limiting factors for the spreading of the fuel cell technology is the durability and researches to extend their lifetime are being done world-widely. We present here a pattern recognition approach aiming to estimate fuel cell operating time based on electrochemical impedance spectroscopy measurements. It consists in first extracting features from the impedance spectrum. For that purpose, two approaches have been investigated. In the first one, particular points of the spectrum are empirically extracted as features. In the second approach, a parametric modelling is performed to extract features from both the real and the imaginary parts of the impedance spectrum. In particular, a latent regression model is used to automatically split the spectrum into several segments that are approximated by polynomials. The number of segments is adjusted taking account the a priori knowledge about the physical behaviour of fuel cell components. Then, a linear regression model using different subsets of extracted features is employed for the estimation of fuel cell operating time. The performances of the proposed approach are evaluated on experimental data set to show its feasibility. Being able to estimate the fuel cell operating time, and consequently its remaining duration life, these results could lead to interesting perspectives for predictive maintenance policy of fuel cells.

A review on fault diagnosis tools of the proton exchange Membrane Fuel Cell

“…Moreover in [25], the authors developed another pattern recognition based approach using both static and dynamic stack information based on polarization curve and EIS to improve the operating time estimation. This improved method was able to estimate the fuel cell's lifetime with a mean error of only 2 hours over a global operating duration of 1000 hours.…”

“…Time impact on the stack's polarization curve[25].The effect of high frequency ripple current on PEMFC aging was studied experimentally in[27] on a 5 cells stack.…”

Discrimination and state-of-health diagnosis based on the discrete wavelet transform for a polymer electrolyte membrane fuel cell

“…The practical implementation of the MRA can be done using a filter bank. (6) In (3) and (4), the scaling , ( ) j k t φ and wavelet ψ j,k (t) functions are associated with the high-pass and low pass filters with filter coefficients h(n) and g(n), respectively. As expressed in (5) and (6), the signal x(t) can be completely decomposed in terms of the approximations A j , provided by scaling function , ( ) j k t φ and the details D j , provided by the wavelet function ψ j,k (t).…”

“…Unfortunately, an accurate stack configuration remains very challenging and problematic due to cell-to-cell variation in the stack [5]. Cell voltages non-uniformity have been detected in cells furthest from intrinsic or extrinsic to the cell properties [6] [7]. The non-uniformity observed in cell voltages may limit the stack's maximum power output.…”

Fuel Cell/ Super-capacitor power management system assessment and Lifetime Cost study in a 500kVA UPS

“…In [7], the author estimated the FC lifetime relying on the Electrochemical Impedance Spectroscopy (EIS) measurements which consequently could help predict the FC maintenance planning.…”