Data-driven fault diagnosis for PEMFC systems

Aiming at improving the reliability and durability of Polymer Electrolyte Membrane Fuel Cell (PEMFC) systems and promote the commercialization of fuel cell technologies, this thesis work is dedicated to the fault diagnosis study for PEMFC systems. In consideration of the sophistication in establishing the accurate and diagnosis-friendly model for PEMFC systems, data-driven fault diagnosis is the main focus in this thesis. As a main branch of data-driven fault diagnosis, the methods based on pattern classification techniques are firstly studied. Taking individual fuel cell voltages as original diagnosis variables, fault detection and isolation (FDI) is achieved through a two-step procedure. The first step is for feature extraction, while the second one is for classification. According to this framework, several representative methodologies in each step are investigated and compared from the perspectives of diagnosis accuracy and computational cost. Specific to the defects on novel class detection and online adaptation capability of conventional classification based diagnosis methods, a novel diagnosis strategy is proposed for PEMFC system diagnosis. A new classifier named Sphere-shaped Multi-class Support Vector Machine (SSM-SVM) and modified diagnostic rules are utilized to realize the novel fault recognition. While an incremental learning method is extended to achieve the online adaptation. Apart from the pattern classification based diagnosis approach, a so-called partial model-based data-driven approach is introduced to handle PEMFC diagnosis in dynamic processes. With the aid of a subspace identification method (SIM), the model-based residual generation is designed directly from the normal and dynamic operating data. Then, fault detection and isolation are further realized by evaluating the generated residuals. The proposed diagnosis strategies have been verified using the experimental data which cover a set of representative faults and different PEMFC stacks. The preliminary online implementation results with an embedded system are also supplied.

[1]  Si-Zhao Joe Qin,et al.  Survey on data-driven industrial process monitoring and diagnosis , 2012, Annu. Rev. Control..

[2]  Q. Peter He,et al.  A New Fault Diagnosis Method Using Fault Directions in Fisher Discriminant Analysis , 2005 .

[3]  U. Kruger,et al.  Dynamic Principal Component Analysis Using Subspace Model Identification , 2005, ICIC.

[4]  Daniel Hissel,et al.  An analysis of fluidic voltage statistical correlation for a diagnosis of PEM fuel cell flooding , 2013 .

[5]  D. Candusso,et al.  Development of new test instruments and protocols for the diagnostic of fuel cell stacks , 2011 .

[6]  Daniel Hissel,et al.  Characterisation and modelling of a 5 kW PEMFC for transportation applications , 2006 .

[7]  Koan-Yuh Chang,et al.  The optimal design for PEMFC modeling based on Taguchi method and genetic algorithm neural networks , 2011 .

[8]  Keinosuke Fukunaga,et al.  Introduction to statistical pattern recognition (2nd ed.) , 1990 .

[9]  Ping Zhang,et al.  Subspace method aided data-driven design of fault detection and isolation systems , 2009 .

[10]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[11]  J. Quevedo,et al.  Robust LPV model-based sensor fault diagnosis and estimation for a PEM fuel cell system , 2010, 2010 Conference on Control and Fault-Tolerant Systems (SysTol).

[12]  Stephen V. Stehman,et al.  Selecting and interpreting measures of thematic classification accuracy , 1997 .

[13]  F. R. Foulkes,et al.  Fuel Cell Handbook , 1989 .

[14]  Carlos Ocampo-Martinez,et al.  Design and implementation of LQR/LQG strategies for oxygen stoichiometry control in PEM fuel cells based systems , 2011 .

[15]  Jin Wang,et al.  Closed-loop subspace identification using the parity space , 2006, Autom..

[16]  M. Cali,et al.  Experimental analysis of cathode flow stoichiometry on the electrical performance of a PEMFC stack , 2007 .

[17]  Bernhard Schölkopf,et al.  The connection between regularization operators and support vector kernels , 1998, Neural Networks.

[18]  Jason Marcinkoski,et al.  DOE Hydrogen and Fuel Cells Program , 2012 .

[19]  Nigel M. Sammes,et al.  Fuel cell technology : reaching towards commercialization , 2006 .

[20]  Bo-Hyung Cho,et al.  State-of-health diagnosis based on hamming neural network using output voltage pattern recognition for a PEM fuel cell , 2012 .

[21]  Daniel Hissel,et al.  Fault diagnosis and novel fault type detection for PEMFC system based on spherical-shaped multiple-class support vector machine , 2014, 2014 IEEE/ASME International Conference on Advanced Intelligent Mechatronics.

[22]  Daniel Hissel,et al.  Non intrusive diagnosis of polymer electrolyte fuel cells by wavelet packet transform , 2011 .

[23]  Daniel Hissel,et al.  Diagnosis of automotive fuel cell power generators , 2004 .

[24]  Zhi-Bo Zhu,et al.  Fault diagnosis based on imbalance modified kernel Fisher discriminant analysis , 2010 .

[25]  N. Wagner,et al.  Change of electrochemical impedance spectra (EIS) with time during CO-poisoning of the Pt-anode in a membrane fuel cell , 2004 .

[26]  G. Baudat,et al.  Generalized Discriminant Analysis Using a Kernel Approach , 2000, Neural Computation.

[27]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[28]  C. Yoo,et al.  Nonlinear process monitoring using kernel principal component analysis , 2004 .

[29]  Silvio Simani,et al.  Model-Based Fault Diagnosis Techniques , 2003 .

[30]  Daniel Hissel,et al.  A New Modeling Approach of Embedded Fuel-Cell Power Generators Based on Artificial Neural Network , 2008, IEEE Transactions on Industrial Electronics.

[31]  Lijuan Cao,et al.  A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine , 2003, Neurocomputing.

[32]  Ioannis Pitas,et al.  Multiplicative update rules for incremental training of multiclass support vector machines , 2012, Pattern Recognit..

[33]  Daniel Hissel,et al.  Diagnosis methods dedicated to the localisation of failed cells within PEMFC stacks , 2008 .

[34]  D. Candusso,et al.  A review on polymer electrolyte membrane fuel cell catalyst degradation and starvation issues: Causes, consequences and diagnostic for mitigation , 2009 .

[35]  F. Harel,et al.  Impact of power converter current ripple on the durability of a fuel cell stack , 2008, 2008 IEEE International Symposium on Industrial Electronics.

[36]  Biao Huang,et al.  Dynamic Modeling, Predictive Control and Performance Monitoring: A Data-driven Subspace Approach , 2008 .

[37]  Pavel Pudil,et al.  Introduction to Statistical Pattern Recognition , 2006 .

[38]  Jianqiu Li,et al.  Proton exchange membrane fuel cell system diagnosis based on the multivariate statistical method , 2011 .

[39]  Daniel Hissel,et al.  A review on PEM voltage degradation associated with water management: Impacts, influent factors and characterization , 2008 .

[40]  Kodjo Agbossou,et al.  Proton Exchange Membrane Fuel Cell Operation and Degradation in Short‐Circuit , 2014 .

[41]  R. Outbib,et al.  Modeling and Fault Diagnosis of a Polymer Electrolyte Fuel Cell Using Electrical Equivalent Analysis , 2010, IEEE Transactions on Energy Conversion.

[42]  W. Yan,et al.  Effects of operating conditions on cell performance of PEM fuel cells with conventional or interdigitated flow field , 2006 .

[43]  Kazunari Sasaki,et al.  Estimation of flooding in PEMFC gas diffusion layer by differential pressure measurement , 2007 .

[44]  J. Platt.  Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[45]  P. Rodatz,et al.  Operational aspects of a large PEFC stack under practical conditions , 2004 .

[46]  Bart De Moor,et al.  N4SID: Subspace algorithms for the identification of combined deterministic-stochastic systems , 1994, Autom..

[47]  Daniel Hissel,et al.  Identification of failed cells inside PEMFC stacks in two cases: Anode/cathode crossover and anode/cooling compartment leak , 2010 .

[48]  Douglas A. Reynolds,et al.  Gaussian Mixture Models , 2018, Encyclopedia of Biometrics.

[49]  Jian Colin Sun,et al.  AC impedance technique in PEM fuel cell diagnosis—A review , 2007 .

[50]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[51]  BaccariniLane Maria Rabelo,et al.  SVM practical industrial application for mechanical faults diagnostic , 2011 .

[52]  Fabien Harel,et al.  Fuel cell diagnosis method based on multifractal analysis of stack voltage signal , 2014 .

[53]  W. Larimore.  System Identification, Reduced-Order Filtering and Modeling via Canonical Variate Analysis , 1983, 1983 American Control Conference.

[54]  Daniel Hissel,et al.  Study of temperature, air dew point temperature and reactant flow effects on proton exchange membrane fuel cell performances using electrochemical spectroscopy and voltammetry techniques , 2010 .

[55]  Bart De Moor,et al.  Subspace Identification for Linear Systems: Theory ― Implementation ― Applications , 2011 .

[56]  Nello Cristianini,et al.  Large Margin DAGs for Multiclass Classification , 1999, NIPS.

[57]  John M. Noble,et al.  Bayesian Networks: An Introduction , 2009 .

[58]  Stéphane Raël,et al.  An innovating application of PEM fuel cell: Current source controlled by hydrogen supply , 2012 .

[59]  Steve Heath,et al.  Embedded Systems Design , 1997 .

[60]  Xin-Jian Zhu,et al.  A hybrid multi-variable experimental model for a PEMFC , 2007 .

[61]  A. Willsky,et al.  Analytical redundancy and the design of robust failure detection systems , 1984 .

[62]  Bart De Moor,et al.  A unifying theorem for three subspace system identification algorithms , 1995, Autom..

[63]  S. Ding,et al.  Closed-loop subspace identification: an orthogonal projection approach , 2004 .

[64]  Suman Basu,et al.  Modeling two-phase flow in PEM fuel cell channels , 2008 .

[65]  Daniel Hissel,et al.  Online Diagnosis of PEMFC by Combining Support Vector Machine and Fluidic Model , 2014 .

[66]  Daniel Hissel,et al.  Diagnosis of a fuel cell stack using electrochemical impedance spectroscopy and Bayesian Networks , 2010, 2010 IEEE Vehicle Power and Propulsion Conference.

[67]  Marcelo Godoy Simões,et al.  On-line fault diagnostic system for proton exchange membrane fuel cells , 2008 .

[68]  James Larminie,et al.  Fuel Cell Systems Explained , 2000 .

[69]  Yongdong Li,et al.  Fault detection and isolation for Polymer Electrolyte Membrane Fuel Cell systems by analyzing cell voltage generated space , 2015 .

[70]  Pei-Yi Hao,et al.  A New Multi-class Support Vector Machine with Multi-sphere in the Feature Space , 2007, IEA/AIE.

[71]  Daniel Hissel,et al.  Data-driven diagnosis of PEM fuel cell: A comparative study , 2014 .

[72]  Daniel Hissel,et al.  Diagnosis of PEMFC by using statistical analysis , 2012 .

[73]  Belkacem Ould Bouamama,et al.  Fault detection and isolation of PEM fuel cell system by analytical redundancy , 2010, 18th Mediterranean Conference on Control and Automation, MED'10.

[74]  Vicenç Puig,et al.  LPV observer design for PEM fuel cell system: Application to fault detection , 2011 .

[75]  Marco Sorrentino,et al.  A review on non-model based diagnosis methodologies for PEM fuel cell stacks and systems , 2013 .

[76]  D. Depernet,et al.  Online diagnosis of PEM Fuel Cell , 2008, 2008 13th International Power Electronics and Motion Control Conference.

[77]  Adel Haghani Abandan Sari.  Data-Driven Design of Fault Diagnosis Systems , 2014 .

[78]  Daniel Hissel,et al.  Fuzzy-Clustering Durability Diagnosis of Polymer Electrolyte Fuel Cells Dedicated to Transportation Applications , 2007, IEEE Transactions on Vehicular Technology.

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

[80]  Daniel Hissel,et al.  Diagnosis of PEMFC by using data-driven parity space strategy , 2014, 2014 European Control Conference (ECC).

[81]  Xuan Cheng,et al.  A review of PEM hydrogen fuel cell contamination: Impacts, mechanisms, and mitigation , 2007 .

[82]  Rolf Isermann,et al.  Fault-Diagnosis Applications , 2011 .

[83]  Sirish L. Shah,et al.  Fault detection and diagnosis in process data using one-class support vector machines , 2009 .

[84]  Derek B. Ingham,et al.  Performance prediction of a proton exchange membrane fuel cell using the ANFIS model , 2009 .

[85]  Sheng-De Wang,et al.  Choosing the kernel parameters for support vector machines by the inter-cluster distance in the feature space , 2009, Pattern Recognit..

[86]  M. C. Pera,et al.  Diagnosis of a commercial PEM fuel cell stack via incomplete spectra and fuzzy clustering , 2013, IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Society.

[87]  Gert Cauwenberghs,et al.  Incremental and Decremental Support Vector Machine Learning , 2000, NIPS.

[88]  Philip Koopman,et al.  Embedded system design issues (the rest of the story) , 1996, Proceedings International Conference on Computer Design. VLSI in Computers and Processors.

[89]  Jianfei Dong,et al.  Data Driven Fault Detection and Isolation of a Wind Turbine Benchmark , 2011 .

[90]  H. Lilliefors.  On the Kolmogorov-Smirnov Test for Normality with Mean and Variance Unknown , 1967 .

[91]  Biao Zhou,et al.  Diagnosis of PEM fuel cell stack dynamic behaviors , 2008 .

[92]  Jian Yang,et al.  Essence of kernel Fisher discriminant: KPCA plus LDA , 2004, Pattern Recognit..

[93]  Paul M. Frank,et al.  Model-Based Fault Diagnosis , 1992, Concise Encyclopedia of Modelling & Simulation.

[94]  Daniel Hissel,et al.  Diagnosis of polymer electrolyte fuel cells failure modes (flooding & drying out) by neural networks modeling , 2011 .

[95]  Colin Campbell,et al.  Kernel methods: a survey of current techniques , 2002, Neurocomputing.

[96]  Patrick Dewilde,et al.  Subspace model identification Part 1. The output-error state-space model identification class of algorithms , 1992 .

[97]  Jun Shen,et al.  A review of PEM fuel cell durability: Degradation mechanisms and mitigation strategies , 2008 .

[98]  Stefan Giurgea,et al.  Efficiency improvement of a PEMFC power source by optimization of the air management , 2012 .

[99]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[100]  Daniel Hissel,et al.  Diagnosis for PEMFC Systems: A Data-Driven Approach With the Capabilities of Online Adaptation and Novel Fault Detection , 2015, IEEE Transactions on Industrial Electronics.

[101]  Daniel Hissel,et al.  Fuel cell operation under degraded working modes and study of diode by-pass circuit dedicated to multi-stack association , 2008 .

[102]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[103]  Guangyi Cao,et al.  Modeling a PEMFC by a support vector machine , 2006 .

[104]  Daniel Hissel,et al.  Online diagnosis of PEMFC by analyzing individual cell voltages , 2013, 2013 European Control Conference (ECC).

[105]  W. Little,et al.  Measurement of the heat transfer characteristics of gas flow in fine channel heat exchangers used for microminiature refrigerators , 1984 .

[106]  Gary Montague,et al.  Non-linear principal components analysis using genetic programming , 1997 .

[107]  Thomas M. Cover,et al.  Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition , 1965, IEEE Trans. Electron. Comput..