Failure Prognosis Based on Relevant Measurements Identification and Data-Driven Trend-Modeling: Application to a Fuel Cell System

Fuel cells are key elements in the transition to clean energy thanks to their neutral carbon footprint, as well as their great capacity for the generation of electrical energy by oxidizing hydrogen. However, these cells operate under straining conditions of temperature and humidity that favor degradation processes. Furthermore, the presence of hydrogen—a highly flammable gas—renders the assessment of their degradations and failures crucial to the safety of their use. This paper deals with the combination of physical knowledge and data analysis for the identification of health indices (HIs) that carry information on the degradation process of fuel cells. Then, a failure prognosis method is achieved through the trend modeling of the identified HI using a data-driven and updatable state model. Finally, the remaining useful life is predicted through the calculation of the times of crossing of the predicted HI and the failure threshold. The trend model is updated when the estimation error between the predicted and measured values of the HI surpasses a predefined threshold to guarantee the adaptation of the prediction to changes in the operating conditions of the system. The effectiveness of the proposed approach is demonstrated by evaluating the obtained experimental results with prognosis performance analysis techniques.

[1]  Abdelkader Mami,et al.  Modeling and testing of a 1.2‐kW Nexa fuel cell using bond graph methodology , 2015 .

[2]  R. Gudi,et al.  Dynamic modeling of an integrated reformer membrane fuel cell system , 2017 .

[3]  Piero Baraldi,et al.  Differential evolution-based multi-objective optimization for the definition of a health indicator for fault diagnostics and prognostics , 2018 .

[4]  Belkacem Ould-Bouamama,et al.  Particle filter based hybrid prognostics for health monitoring of uncertain systems in bond graph framework , 2016 .

[5]  Hicham Chaoui,et al.  Overview and benchmark analysis of fuel cell parameters estimation for energy management purposes , 2018 .

[6]  Larry A. Rendell,et al.  The Feature Selection Problem: Traditional Methods and a New Algorithm , 1992, AAAI.

[7]  F. Gonzalez-Longatt,et al.  Modeling and simulation of PEM fuel cell with bond graph and 20sim , 2008, 2008 American Control Conference.

[8]  Enrico Zio,et al.  Review on Health Indices Extraction and Trend Modeling for Remaining Useful Life Estimation , 2020 .

[9]  Rongheng Lin,et al.  Review on hydrogen fuel cell condition monitoring and prediction methods , 2019, International Journal of Hydrogen Energy.

[10]  Josef Kittler,et al.  Fast branch & bound algorithms for optimal feature selection , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Marco Sorrentino,et al.  A review on model-based diagnosis methodologies for PEMFCs , 2013 .

[12]  Noureddine Zerhouni,et al.  Proton exchange membrane fuel cell ageing forecasting algorithm based on Echo State Network , 2017 .

[13]  Daniel Hissel,et al.  Diagnostic & health management of fuel cell systems: Issues and solutions , 2016, Annu. Rev. Control..

[14]  Pavle Boškoski,et al.  State of health estimation and remaining useful life prediction of solid oxide fuel cell stack , 2017 .

[15]  Abdel Aitouche,et al.  Structural Diagnosability of Fuel Cell Stack System Based on Bond Graph Tool , 2009 .

[16]  Wolfgang Borutzky,et al.  Bond Graph Modelling of Engineering Systems , 2011 .

[17]  B. Ould Bouamama,et al.  LFT Bond Graph Model-Based Robust Fault Detection and Isolation , 2011 .

[18]  Lei Mao,et al.  Selection of optimal sensors for predicting performance of polymer electrolyte membrane fuel cell , 2016 .

[19]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[20]  Feng Ding,et al.  Model order determination using the Hankel matrix of impulse responses , 2011, Appl. Math. Lett..

[21]  Remi Saisset,et al.  Bond Graph model of a PEM fuel cell , 2006 .

[22]  Jamie B. Coble,et al.  Merging Data Sources to Predict Remaining Useful Life – An Automated Method to Identify Prognostic Parameters , 2010 .

[23]  J. Steinier,et al.  Smoothing and differentiation of data by simplified least square procedure. , 1972, Analytical chemistry.

[24]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[25]  Alan S. Perelson,et al.  System Dynamics: A Unified Approach , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[26]  Xiaojuan Wu,et al.  Fault diagnosis and prognostic of solid oxide fuel cells , 2016 .

[27]  Edwin Lughofer,et al.  Fault diagnosis and prognosis based on physical knowledge and reliability data: Application to MOS Field-Effect Transistor , 2020 .

[28]  Junghui Chen,et al.  Prognostics of PEM fuel cells based on Gaussian process state space models , 2018 .

[29]  Min Han,et al.  Online prediction of noisy time series: Dynamic adaptive sparse kernel recursive least squares from sparse and adaptive tracking perspective , 2020, Eng. Appl. Artif. Intell..

[30]  Belkacem Ould Bouamama,et al.  Signed Bond Graph for health monitoring of PEM fuel cell , 2013 .

[31]  Abdelkader Mami,et al.  Bond graph modeling and control of a single PEM cell , 2015, IREC2015 The Sixth International Renewable Energy Congress.

[32]  Xue-wen Chen.  An improved branch and bound algorithm for feature selection , 2003, Pattern Recognit. Lett..

[33]  R. Gouriveau,et al.  Data-driven Prognostics of Proton Exchange Membrane Fuel Cell Stack with constraint based Summation-Wavelet Extreme Learning Machine. , 2015 .

[34]  Y. H. Hung,et al.  Real-time dynamic modeling of hydrogen PEMFCs , 2008, J. Frankl. Inst..

[35]  Hongye Su,et al.  Data-based short-term prognostics for proton exchange membrane fuel cells , 2017 .

[36]  Lisa M. Jackson,et al.  Component-based modelling of PEM fuel cells with bond graphs , 2017 .

[37]  Xiaowei Fu,et al.  Health state prediction and analysis of SOFC system based on the data-driven entire stage experiment , 2019, Applied Energy.

[38]  Lakhdar Khochemane,et al.  Bond graph modeling approach development for fuel cell PEMFC systems , 2014 .