Data-driven techniques for fault diagnosis in power generation plants based on solid oxide fuel cells

Abstract The development of fault diagnosis systems able to early detect and identify any malfunctioning is of great importance towards the diffusion of energy conversion plants based on solid oxide fuel cells. Because the traditional model-based schemes for the diagnosis demonstrated a poor fault identification capability (especially when many operating conditions and fault sizes are combined), hybrid schemes were proposed that, incorporating pattern recognition classifiers, achieved significant performance improvements. However, like in the model-based case, the hybrid schemes require the running of the plant model in parallel to the real plant functioning. In this study, a data-driven fault diagnosis scheme is presented, in which the plant model is used only off-line, for the training of the classifier. Both support vector machine and random forest classifiers are proposed and tested. It is demonstrated that, when a support vector machine classifier is deployed, the data-driven system outperforms the hybrid systems in both fault detection and fault identification. High-level performance is achieved despite the large number of combinations among working conditions and fault sizes used for testing the system.

[1]  L. Magistri,et al.  Integrated Planar Solid Oxide Fuel Cell: Steady-State Model of a Bundle and Validation through Single Tube Experimental Data , 2015 .

[2]  Gabriele Moser,et al.  Joint Feature and Model Selection for SVM Fault Diagnosis in Solid Oxide Fuel Cell Systems , 2015 .

[3]  Andreas Ziegler,et al.  ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R , 2015, 1508.04409.

[4]  Bo-Suk Yang,et al.  Support vector machine in machine condition monitoring and fault diagnosis , 2007 .

[5]  Fabio Rinaldi,et al.  Long-term performance analysis of an HT-PEM fuel cell based micro-CHP system: Operational strategies , 2015 .

[6]  Xiao Juan Wu,et al.  Fault Diagnosis of Solid Oxide Fuel Cell Based on a Supervised Self-Organization Map Model , 2015 .

[7]  Michela Gallo,et al.  Life Cycle Assessment and Life Cycle Costing of a SOFC system for distributed power generation , 2015 .

[8]  Gabriele Moser,et al.  Fault diagnosis in fuel cell systems using quantitative models and support vector machines , 2014 .

[9]  Loredana Magistri,et al.  FDI oriented modeling of an experimental SOFC system, model validation and simulation of faulty states , 2014 .

[10]  Christoph Hochenauer,et al.  Towards a practical tool for online monitoring of solid oxide fuel cell operation: An experimental study and application of advanced data analysis approaches , 2018, Applied Energy.

[11]  Daniel Hissel,et al.  Solid oxide fuel cell fault diagnosis and ageing estimation based on wavelet transform approach , 2016 .

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  Marco Sorrentino,et al.  Application of Fault Tree Analysis to Fuel Cell diagnosis , 2012 .

[14]  Gabriele Moser,et al.  A Classification Approach for Model-Based Fault Diagnosis in Power Generation Systems Based on Solid Oxide Fuel Cells , 2016, IEEE Transactions on Energy Conversion.

[15]  Paola Costamagna,et al.  Electrochemical model of the integrated planar solid oxide fuel cell (IP-SOFC) , 2004 .

[16]  Gabriele Moser,et al.  Fault Diagnosis Strategies for SOFC-Based Power Generation Plants , 2016, Sensors.

[17]  Marco Sorrentino,et al.  Model-based development of a fault signature matrix to improve solid oxide fuel cell systems on-site diagnosis , 2015 .

[18]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[19]  Richard D. Braatz,et al.  Fault Detection and Diagnosis in Industrial Systems , 2001 .

[20]  Pravat Kumar Rout,et al.  Detection and classification of faults in a microgrid using wavelet neural network , 2018 .

[21]  Rolf Isermann.  Model-based fault-detection and diagnosis - status and applications § , 2004 .

[22]  Krishna R. Pattipati,et al.  Integrated Model-Based and Data-Driven Diagnosis of Automotive Antilock Braking Systems , 2010, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[23]  Loredana Magistri,et al.  Reformer faults in SOFC systems: Experimental and modeling analysis, and simulated fault maps , 2014 .

[24]  Rolf Isermann,et al.  Supervision, fault-detection and fault-diagnosis methods — An introduction , 1997 .

[25]  Gabriele Moser,et al.  Combining Support Vector Machines and Markov Random Fields in an Integrated Framework for Contextual Image Classification , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Marco Sorrentino,et al.  Improved Fault Isolability for Solid Oxide Fuel Cell Diagnosis Through Sub-system Analysis , 2017 .

[27]  Alberto Traverso,et al.  Modelling of Pressurised Hybrid Systems Based on Integrated Planar Solid Oxide Fuel Cell (IP‐SOFC) Technology , 2005 .

[29]  Lin Ma,et al.  An integrated approach for system functional reliability assessment using Dynamic Bayesian Network and Hidden Markov Model , 2018, Reliab. Eng. Syst. Saf..

[30]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[31]  S. Srinivasan,et al.  Fuel Cells: From Fundamentals to Applications , 2006 .

[32]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[33]  Ethem Alpaydin.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

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

[35]  Marco Sorrentino,et al.  A model-based diagnostic technique to enhance faults isolability in Solid Oxide Fuel Cell systems , 2017 .

[36]  Marco Sorrentino,et al.  On the Use of Neural Networks and Statistical Tools for Nonlinear Modeling and On-field Diagnosis of Solid Oxide Fuel Cell Stacks , 2014 .

[37]  Marco Sorrentino,et al.  A Review on solid oxide fuel cell models , 2011 .

[38]  K. Kendall,et al.  High temperature solid oxide fuel cells : fundamentals, design and applicatons , 2003 .

[39]  Samuel Simon Araya,et al.  Fault detection and isolation of high temperature proton exchange membrane fuel cell stack under the influence of degradation , 2017 .

[40]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

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

[42]  Yupu Yang,et al.  Data-driven simultaneous fault diagnosis for solid oxide fuel cell system using multi-label pattern identification , 2018 .

[43]  Juan José Rodríguez Diez,et al.  Rotation Forest: A New Classifier Ensemble Method , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Linda Barelli,et al.  SOFC direct fuelling with high-methane gases: Optimal strategies for fuel dilution and upgrade to avoid quick degradation , 2016 .

[45]  Andrea Trucco.  Detection of objects buried in the seafloor by a pattern-recognition approach , 2001 .

[46]  Ali Cinar,et al.  Monitoring, fault diagnosis, fault-tolerant control and optimization: Data driven methods , 2012, Comput. Chem. Eng..

[47]  Saeed Jazebi,et al.  A novel application of wavelet based SVM to transient phenomena identification of power transformers , 2011 .

[48]  Yupu Yang,et al.  A General Approach for Fault Identification in SOFC-based Power Generation Systems , 2018, 2018 Annual American Control Conference (ACC).