Framework for Unifying Model-based and Data-driven Fault Diagnosis

Model-based diagnosis methods rely on a model that defines nominal behavior of a dynamic system to detect abnormal behaviors and isolate faults. On the other hand, data-driven diagnosis algorithms detect and isolate system faults by operating exclusively on system measurements and using very little knowledge about the system. Recently, several researchers have combined model-based diagnosis techniques with datadriven approaches to propose hybrid1solutions for fault diagnosis. Many researchers have proposed methods to integrate specific approaches. In this paper, we demonstrate that data-driven and model-based diagnosis methods follow a similar procedure and can be represented by a general unifying framework. This unifying framework for fault detection and isolation can be used to integrate different methodologies developed by two communities. As a case study, we use the proposed framework to build a crossover solution for fault diagnosis in a wind turbine benchmark. In this case study, we show that it is possible to achieve a better diagnosis performance by using a hybrid method that follows the proposed framework.

[1]  T. Caliński,et al.  A dendrite method for cluster analysis , 1974 .

[2]  P. Frank,et al.  Deterministic nonlinear observer-based approaches to fault diagnosis: A survey , 1997 .

[3]  Urko Leturiondo,et al.  Hybrid modelling in condition monitoring , 2016 .

[4]  Gautam Biswas,et al.  A Common Framework for Compilation Techniques Applied to Diagnosis of Linear Dynamic Systems , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[5]  Maxime Gariel,et al.  Anomaly detection in onboard-recorded flight data using cluster analysis , 2011, 2011 IEEE/AIAA 30th Digital Avionics Systems Conference.

[6]  A. M. Benkouider,et al.  A hybrid approach to faults detection and diagnosis in batch and semi-batch reactors by using EKF and neural network classifier , 2012 .

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

[8]  Heidar Ali Talebi,et al.  Neural Network-Based State Estimation of Nonlinear Systems: Application to Fault Detection and Isolation , 2009 .

[9]  Victoria J. Hodge,et al.  A Survey of Outlier Detection Methodologies , 2004, Artificial Intelligence Review.

[10]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Rolf Isermann,et al.  Fault diagnosis of machines via parameter estimation and knowledge processing - Tutorial paper , 1991, Autom..

[12]  Weihua Li,et al.  Isolation enhanced principal component analysis , 1999 .

[13]  Sami Othman,et al.  Support Vector Machines for Fault Detection in Wind Turbines , 2011 .

[14]  Janos Gertler,et al.  Fault detection and diagnosis in engineering systems , 1998 .

[15]  Brian C. Williams,et al.  Hybrid estimation of complex systems , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[16]  Erik Frisk,et al.  A combined diagnosis system design using model-based and data-driven methods , 2016, 2016 3rd Conference on Control and Fault-Tolerant Systems (SysTol).

[17]  Gautam Biswas,et al.  A combined model-based and data-driven approach for monitoring smart buildings , 2017, DX.

[18]  Giorgio Rizzoni,et al.  Comparison of Model-based Vs . Data-driven Methods for Fault Detection and Isolation in Engine Idle Speed Control System , 2016 .

[19]  Qi Zhang,et al.  Fault Detection and Isolation of the Wind Turbine Benchmark: an Estimation-based Approach , 2011 .

[20]  Steven X. Ding,et al.  Frequency domain approach to optimally robust residual generation and evaluation for model-based fault diagnosis , 1994, Autom..

[21]  Daniel Eriksson,et al.  A sequential test selection algorithm for fault isolation , 2012 .

[22]  Sylvain Verron,et al.  Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: A review of researches and future challenges , 2016, Annu. Rev. Control..

[23]  Sriram Narasimhan,et al.  Combining Model-Based and Feature-Driven Diagnosis Approaches - A Case Study on Electromechanical Actuators , 2010 .

[24]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[25]  Sami Othman,et al.  Support vector machines combined to observers for fault diagnosis in chemical reactors , 2014 .

[26]  Gautam Biswas,et al.  Learning Bayesian Network Structures to Augment Aircraft Diagnostic Reference Models , 2017, IEEE Transactions on Automation Science and Engineering.

[27]  Gautam Biswas,et al.  Robust residual selection for fault detection , 2014, 53rd IEEE Conference on Decision and Control.

[28]  Pieter J. Mosterman,et al.  Diagnosis of continuous valued systems in transient operating regions , 1999, IEEE Trans. Syst. Man Cybern. Part A.

[29]  Kamal Medjaher,et al.  Diagnostic bond graphs for online fault detection and isolation , 2006, Simul. Model. Pract. Theory.

[30]  Gabor Karsai,et al.  A robust method for hybrid diagnosis of complex systems , 2003 .

[31]  Pascal Vincent,et al.  Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives , 2012, ArXiv.

[32]  Peter Fogh Odgaard,et al.  Fault tolerant control of wind turbines: a benchmark model , 2009 .

[33]  P. Frank,et al.  Survey of robust residual generation and evaluation methods in observer-based fault detection systems , 1997 .

[34]  Marios M. Polycarpou,et al.  Design and analysis of a fault isolation scheme for a class of uncertain nonlinear systems , 2008, Annu. Rev. Control..