Machinery fault diagnostics based on fuzzy measure and fuzzy integral data fusion techniques

With growing demands for reliability, availability, safety and cost efficiency in modern machinery, accurate fault diagnosis is becoming of paramount importance so that potential failures can be better managed. Although various methods have been applied to machinery condition monitoring and fault diagnosis, the diagnostic accuracy that can be attained is far from satisfactory. As most machinery faults lead to increases in vibration levels, vibration monitoring has become one of the most basic and widely used methods to detect machinery faults. However, current vibration monitoring methods largely depend on signal processing techniques. This study is based on the recognition that a multi-parameter data fusion approach to diagnostics can produce more accurate results. Fuzzy measures and fuzzy integral data fusion theory can represent the importance of each criterion and express certain interactions among them. This research developed a novel, systematic and effective fuzzy measure and fuzzy integral data fusion approach for machinery fault diagnosis, which comprises feature set selection schema, feature level data fusion schema and decision level data fusion schema for machinery fault diagnosis. Different feature selection and fault diagnostic models were derived from these schemas. Two fuzzy measures and two fuzzy integrals were employed: the 2-additive fuzzy measure, the fuzzy measure, the Choquet fuzzy integral and the Sugeno fuzzy integral respectively. The models were validated using rolling element bearing and electrical motor experiments. Different features extracted from vibration signals were used to validate the rolling element bearing feature set selection and fault diagnostic models, while features obtained from both vibration and current signals were employed to assess electrical motor fault diagnostic models. The results show that the proposed schemas and models perform very well in selecting feature set and can improve accuracy in diagnosing both the rolling element bearing and electrical motor faults.

[1]  Pavel Pudil,et al.  Feature selection toolbox software package , 2002, Pattern Recognit. Lett..

[2]  Paul D. Gader,et al.  Feature and decision level sensor fusion of electromagnetic induction and ground penetrating radar sensors for landmine detection with hand-held units , 2002, Inf. Fusion.

[3]  Paul D. Gader,et al.  Generalized Choquet fuzzy integral fusion , 2002, Inf. Fusion.

[4]  Kwong-Sak Leung,et al.  Determining nonnegative monotone set functions based on Sugeno's integral: an application of genetic algorithms , 2000, Fuzzy Sets Syst..

[5]  James C. Bezdek,et al.  Decision templates for multiple classifier fusion: an experimental comparison , 2001, Pattern Recognit..

[6]  Lin Ma,et al.  Integrated Machine Fault Diagnosis Using Wavelet Packet Transform and Probabilistic Neural Networks , 2003 .

[7]  W. Pieczynski,et al.  Unsupervised Image Segmentation Using Dempster- Shafer Fusion in a Markov Fields Context , 1998 .

[8]  Michel Grabisch,et al.  A new algorithm for identifying fuzzy measures and its application to pattern recognition , 1995, Proceedings of 1995 IEEE International Conference on Fuzzy Systems..

[9]  L. J. Kangas,et al.  TEDANN: Turbine engine diagnostic artificial neural network , 1994 .

[10]  Jesús Manuel Fernández Salido,et al.  A comparison of two learning mechanisms for the automatic design of fuzzy diagnosis systems for rotating machinery , 2004, Appl. Soft Comput..

[11]  T. J. Holroyd.  The application of AE in condition monitoring : Condition Monitoring , 2005 .

[12]  James M. Keller,et al.  Training the fuzzy integral , 1996, Int. J. Approx. Reason..

[13]  Lin Ma,et al.  Vibration feature extraction techniques for fault diagnosis of rotating machinery : a literature survey , 2003 .

[14]  G. Klir,et al.  Fuzzy Measure Theory , 1993 .

[15]  M. Guillot,et al.  On-line prediction of surface finish and dimensional deviation in turning using neural network based sensor fusion , 1997 .

[16]  Lin Ma,et al.  Feature group optimisation for machinery fault diagnosis based on fuzzy measures , 2008, WCE 2008.

[17]  Jack Mineo.  Advanced Command, Control, Communications, & Intelligence (C3I) Systems Analysis and Trade-Offs , 2004 .

[18]  Mostefa Mesbah,et al.  Diagnosis of Faulty Ball Bearing Using Wavelet Decomposition , 2003 .

[19]  Robert Milne,et al.  TIGER with model based diagnosis: initial deployment , 2001, Knowl. Based Syst..

[20]  Stephen E. Levinson,et al.  Development of an acoustic-phonetic hidden Markov model for continuous speech recognition , 1991, IEEE Trans. Signal Process..

[21]  M. Grabisch.  The application of fuzzy integrals in multicriteria decision making , 1996 .

[22]  Paul D. Gader,et al.  Fusion of handwritten word classifiers , 1996, Pattern Recognit. Lett..

[23]  K. Shima,et al.  SVM-based feature selection of latent semantic features , 2004, Pattern Recognit. Lett..

[24]  Marios M. Polycarpou,et al.  Neural-network-based robust fault diagnosis in robotic systems , 1997, IEEE Trans. Neural Networks.

[25]  Ming Rao,et al.  Integrated distributed intelligent system architecture for incidents monitoring and diagnosis , 1998 .

[26]  Ren C. Luo,et al.  Multisensor integration and fusion for intelligent machines and systems , 1995 .

[27]  M. Bao,et al.  Classification of Multi-temporal Sar Images and Insar Coherence Images Using Adaptive Neighborhood Model and Simulated Annealing Approach , 1999 .

[28]  D. Wroblewski,et al.  A testbed for data fusion for engine diagnostics and prognostics , 2002, Proceedings, IEEE Aerospace Conference.

[29]  M.J. Roemer,et al.  Upgrading engine test cells for improved troubleshooting and diagnostics , 2002, Proceedings, IEEE Aerospace Conference.

[30]  Francesco Marcelloni,et al.  Feature selection based on a modified fuzzy C-means algorithm with supervision , 2003, Inf. Sci..

[31]  Jie Yang,et al.  Sensor Fusion Using Dempster-Shafer Theory , 2002 .

[32]  Ray S. Beebe,et al.  Condition monitoring of steam turbines by performance analysis , 2003 .

[33]  R. Friend,et al.  A testbed for data fusion for helicopter diagnostics and prognostics , 2003, 2003 IEEE Aerospace Conference Proceedings (Cat. No.03TH8652).

[34]  Carlo S. Regazzoni,et al.  Distributed data fusion for real-time crowding estimation , 1996, Signal Process..

[35]  Junbin Gao,et al.  Some remarks on Kalman filters for the multisensor fusion , 2002, Inf. Fusion.

[36]  Philip Wolfe,et al.  Contributions to the theory of games , 1953 .

[37]  Stephen Grossberg,et al.  A What-and-Where fusion neural network for recognition and tracking of multiple radar emitters , 2001, Neural Networks.

[38]  Majid Mirmehdi,et al.  Automatic Recognition of Exudative Maculopathy using Fuzzy C- Means Clustering and Neural Networks , 2001 .

[39]  Kurt Kubik,et al.  EVALUATION OF A METHOD FOR FUSING LIDAR DATA AND MULTISPECTRAL IMAGES FOR BUILDING DETECTION , 2005 .

[40]  Baozong Yuan,et al.  A more efficient branch and bound algorithm for feature selection , 1993, Pattern Recognit..

[41]  Alain Chateauneuf,et al.  Some Characterizations of Lower Probabilities and Other Monotone Capacities through the use of Möbius Inversion , 1989, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[42]  Michael J. Roemer,et al.  A Prognostic Modeling Approach for Predicting Recurring Maintenance for Shipboard Propulsion Systems , 2001 .

[43]  Hong Yan,et al.  Human Face Image Recognition: An Evidence Aggregation Approach , 1998, Comput. Vis. Image Underst..

[44]  Huan Liu,et al.  A selective sampling approach to active feature selection , 2004, Artif. Intell..

[45]  F. Chu,et al.  Using genetic algorithms and finite element methods to detect shaft crack for rotor-bearing system , 2001 .

[46]  Ken Maynard,et al.  Application of sensor fusion and signal classification techniques in a distributed machinery condition monitoring system , 2000, SPIE Defense + Commercial Sensing.

[47]  Chris K. Mechefske,et al.  OBJECTIVE MACHINERY FAULT DIAGNOSIS USING FUZZY LOGIC , 1998 .

[48]  Jing Lin,et al.  A difference resonator for detecting weak signals , 1999 .

[49]  Frank L. Lewis,et al.  Intelligent Fault Diagnosis and Prognosis for Engineering Systems , 2006 .

[50]  Andrzej Skowron,et al.  Rough set methods in feature selection and recognition , 2003, Pattern Recognit. Lett..

[51]  Bilge Yildiz,et al.  DEVELOPMENT OF A HYBRID INTELLIGENT SYSTEM FOR ON-LINE MONITORING OF NUCLEAR POWER PLANT OPERATIONS , 2002 .

[52]  Kenneth J. Hintz,et al.  Sensor management in a sensor-rich environment , 2000, SPIE Defense + Commercial Sensing.

[53]  Lin Ma,et al.  Rotating machinery fault diagnosis based on fuzzy data fusion techniques , 2007 .

[54]  Tom Brotherton,et al.  Symposium iTEDS : the intelligent Turbine Engine Diagnostic System , 2002 .

[55]  Joseba Quevedo,et al.  TIGER: Knowledge Based Gas Turbine Condition Monitoring , 1996, AI Commun..

[56]  Hsu-Pin Wang,et al.  Performance analysis of rotating machinery using enhanced cerebellar model articulation controller (E-CMAC) neural networks , 1996 .

[57]  Vladimir Gorodetski,et al.  Multi-agent Data Fusion Systems : Design and Implementation Issues , 2002 .

[58]  Andrew Starr,et al.  A systematic approach to integrated fault diagnosis of flexible manufacturing systems , 2000 .

[59]  William A. Maul,et al.  Hybrid diagnostic system: beacon-based exception analysis for multimissions - Livingstone integration , 2004 .

[60]  Amiya R Mohanty,et al.  Monitoring gear vibrations through motor current signature analysis and wavelet transform , 2006 .

[61]  Stephen Ogaji,et al.  Gas-turbine fault diagnostics: a fuzzy-logic approach , 2005 .

[62]  P. D. McFadden,et al.  APPLICATION OF WAVELETS TO GEARBOX VIBRATION SIGNALS FOR FAULT DETECTION , 1996 .

[63]  Qiang Shen,et al.  Selecting informative features with fuzzy-rough sets and its application for complex systems monitoring , 2004, Pattern Recognit..

[64]  Isabelle Bloch.  Information combination operators for data fusion: a comparative review with classification , 1996, IEEE Trans. Syst. Man Cybern. Part A.

[65]  A. K. Sen,et al.  Parallel processing application in traction motor fault diagnosis , 1999 .

[66]  Robert J. Abrahart,et al.  Multi-model data fusion for hydrological forecasting , 2001 .

[67]  Niaoqing Hu,et al.  APPLICATION OF STOCHASTIC RESONANCE THEORY FOR EARLY DETECTING RUB-IMPACT FAULT OF ROTOR SYSTEM , 2001 .

[68]  Songul Albayrak,et al.  FUZZY C-MEANS CLUSTERING ON MEDICAL DIAGNOSTIC SYSTEMS , 2003 .

[69]  Dimitrios T. Hountalas,et al.  Development and application of a fully automatic troubleshooting method for large marine diesel engines , 1999 .

[70]  C. James Li,et al.  Acoustic emission analysis for bearing condition monitoring , 1995 .

[71]  Fritz Albregtsen,et al.  Many are called, but few are chosen. Feature selection and error estimation in high dimensional spaces , 2004, Comput. Methods Programs Biomed..

[72]  Pramod K. Varshney,et al.  Distributed Detection and Data Fusion , 1996 .

[73]  Gang Niu,et al.  Multi-agent decision fusion for motor fault diagnosis , 2007 .

[74]  I Abstract,et al.  A System Approach to Machinery Condition Monitoring and Diagnostic , 2001 .

[75]  Zheru Chi,et al.  Image coding quality assessment using fuzzy integrals with a three-component image model , 2004, IEEE Transactions on Fuzzy Systems.

[76]  Sung-Bae Cho,et al.  Multiple network fusion using fuzzy logic , 1995, IEEE Trans. Neural Networks.

[77]  Yunfeng Wu,et al.  Fusing output information in neural networks: ensemble performs better , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[78]  Jyh-Cheng Chen,et al.  PET-MRI IMAGE REGISTRATION AND FUSION USING ARTIFICIAL NEURAL NETWORKS , 2003 .

[79]  Dimitrios T. Hountalas,et al.  Prediction of marine diesel engine performance under fault conditions , 2000 .

[80]  Lai-bin Zhang,et al.  Short-term fault prediction of mechanical rotating parts on the basis of fuzzy-grey optimising method , 2007 .

[81]  Mo-Yuen Chow,et al.  Neural-network-based motor rolling bearing fault diagnosis , 2000, IEEE Trans. Ind. Electron..

[82]  Sylvie Le Hégarat-Mascle,et al.  Multi-scale data fusion using Dempster-Shafer evidence theory , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[83]  Doris Schmitt-Landsiedel,et al.  Improved SRAM failure diagnosis for process monitoring via current signature analysis , 1999 .

[84]  L. Shapley.  A Value for n-person Games , 1988 .

[85]  Joseph Mathew,et al.  USING THE CORRELATION DIMENSION FOR VIBRATION FAULT DIAGNOSIS OF ROLLING ELEMENT BEARINGS—I. BASIC CONCEPTS , 1996 .

[86]  Jingjing He,et al.  Neural network fusion strategies for identifying breast masses , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[87]  B. D. Netten,et al.  Enhancing off-line and on-line condition monitoring and fault diagnosis , 1995 .

[88]  Fulei Chu,et al.  RETRACTED: Using genetic algorithms to detect and configure shaft crack for rotor-bearing system , 2001 .

[89]  Hongyu Yang,et al.  A New Sensor Fault Diagnosis Technique Based Upon Subspace Identification and Residual Filtering , 2006, ICIC.

[90]  Gerald M. Knapp,et al.  A fuzzy neural network approach to machine condition monitoring , 2003, Comput. Ind. Eng..

[91]  C. James Li,et al.  FLIGHT REGIME MAPPING FOR AIRCRAFT ENGINE FAULT DIAGNOSIS , 2004 .

[92]  Michel Grabisch,et al.  The representation of importance and interaction of features by fuzzy measures , 1996, Pattern Recognit. Lett..

[93]  L S.K.,et al.  HIGHER-ORDER TIME–FREQUENCY ANALYSIS AND ITS APPLICATION TO FAULT DETECTION IN ROTATING MACHINERY , 1997 .

[94]  Nariman Sepehri,et al.  Neural network classifiers applied to condition monitoring of a pneumatic process valve actuator , 2002 .

[95]  C. J. Li,et al.  Bearing Condition Monitoring by Pattern Recognition Based on Bicoherence Analysis of Vibrations , 1996 .

[96]  Lin Ma,et al.  Machinery Fault Diagnosis Based on Feature Level Fuzzy Integral Data Fusion Techniques , 2006, 2006 4th IEEE International Conference on Industrial Informatics.

[97]  Bilge Yildiz,et al.  Development of Expert System with Bayesian Networks for Application in Nuclear Power Plants , 2002 .

[98]  Michael J. Roemer,et al.  Advanced diagnostics and prognostics for gas turbine engine risk assessment , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[99]  Hans-Jürgen Zimmermann,et al.  Improved feature selection and classification by the 2-additive fuzzy measure , 1999, Fuzzy Sets Syst..

[100]  Joseph Mathew,et al.  Machinery Fault Diagnosis Schemas Based on Fuzzy Integral Theory , 2005 .

[101]  Charles Witt.  AIR 1839 - A Guide to Aircraft Turbine Engine Vibration Monitoring Systems , 1984 .

[102]  Michel Grabisch,et al.  K-order Additive Discrete Fuzzy Measures and Their Representation , 1997, Fuzzy Sets Syst..

[103]  Malur K. Sundareshan,et al.  Neural network fusion capabilities for efficient implementation of tracking algorithms , 1996 .

[104]  Jiangping Wang,et al.  Vibration-based fault diagnosis of pump using fuzzy technique , 2006 .

[105]  LiJie Yu,et al.  A novel approach to aircraft engine anomaly detection and diagnostics , 2004, 2004 IEEE Aerospace Conference Proceedings (IEEE Cat. No.04TH8720).

[106]  Amir F. Atiya,et al.  Multi-step-ahead prediction using dynamic recurrent neural networks , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[107]  George J. Klir,et al.  Constructing fuzzy measures in expert systems , 1997, Fuzzy Sets Syst..

[108]  Jeong-Du Kim,et al.  Development of a tool failure detection system using multi-sensors , 1996 .

[109]  菅野 道夫,et al.  Applied fuzzy systems , 1994 .

[110]  Huan Liu,et al.  Consistency-based search in feature selection , 2003, Artif. Intell..

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

[112]  Bo-Suk Yang,et al.  Application of Dempster–Shafer theory in fault diagnosis of induction motors using vibration and current signals , 2006 .

[113]  H. Yan,et al.  Color image segmentation using fuzzy integral and mountain clustering , 1999, Fuzzy Sets Syst..

[114]  Representation of preferences on fuzzy measures by a fuzzy integral , 1996 .

[115]  Agnar Aamodt,et al.  Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches , 1994, AI Commun..

[116]  Lin Ma,et al.  Common Best Basis Selection of Wavelet Packets for Machine Fault Diagnosis , 2003 .

[117]  Nikos G. Pantelelis,et al.  Neural networks and simple models for the fault diagnosis of naval turbochargers , 2000 .

[118]  Tom Warwick.  Overview of ARP 1587 Aircraft Gas Turbine Engine Monitoring System Guide , 1980 .

[119]  Desire L. Massart,et al.  Feature selection in principal component analysis of analytical data , 2002 .

[120]  Takahisa Kobatashi,et al.  A Hybrid Neural Network-Genetic Algorithm Technique for Aircraft Engine Performance Diagnostics , 2001 .

[121]  Paul R. White,et al.  THE ENHANCEMENT OF IMPULSIVE NOISE AND VIBRATION SIGNALS FOR FAULT DETECTION IN ROTATING AND RECIPROCATING MACHINERY , 1998 .

[122]  Trevor J. Holroyd.  THE APPLICATION OF AE IN CONDITION MONITORING , 2008 .

[123]  Nong Zhang,et al.  Powertrain Vibration Analysis Using Torsional Finite Elements , 2003 .

[124]  W. T. Thomson,et al.  Motor Current Signature Analysis To Detect Faults In Induction Motor Drives - Fundamentals, Data Interpretation, And Industrial Case Histories. , 2003 .

[125]  Bouchra Senadji,et al.  Bearing Fault Detection Using Blind Deconvolution and Time Interval Averaging , 2003 .

[126]  Witold Pedrycz,et al.  Face recognition using fuzzy Integral and wavelet decomposition method , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[127]  Risto Korhonen,et al.  Intelligent Techniques for Condition Monitoring of Rolling Mill , 2000 .

[128]  Michael J. Roemer,et al.  A Comprehensive Prognostics Approach for Predicting Gas Turbine Engine Bearing Life , 2004 .