Real-time condition monitoring and fault diagnosis in switched reluctance motors with Kohonen neural network

The faults in switched reluctance motors (SRMs) were detected and diagnosed in real time with the Kohonen neural network. When a fault happens, both financial losses and undesired situations may occur. For these reasons, it is important to detect the incipient faults of SRMs and to diagnose which faults have occurred. In this study, a test rig was realized to determine the healthy and faulty conditions of SRMs. A data set for the Kohonen neural network was created with implemented measurements. A graphical user interface (GUI) was created in Matlab to test the performance of the Kohonen artificial neural network in real time. The data of the SRM was transferred to this software with a data acquisition card. The condition of the motor was monitored by marking the data measured in real time on the weight position graph of the Kohonen neural network. This test rig is capable of real-time monitoring of the condition of SRMs, which are used with intermittent or continuous operation, and is capable of detecting and diagnosing the faults that may occur in the motor. The Kohonen neural network used for detection and diagnosis of faults of the SRM in real time with Matlab GUI was embedded in an STM32 processor. A prototype with the STM32 processor was developed to detect and diagnose the faults of SRMs independent of computers.

[1]  Ebrahim Afjei,et al.  Magnetostatic Field Analysis and Diagnosis of Mixed Eccentricity Fault in Switched Reluctance Motor , 2011 .

[2]  B. Samanta,et al.  ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROLLING ELEMENT BEARINGS USING TIME-DOMAIN FEATURES , 2003 .

[3]  Xiao Zhi Gao,et al.  Soft computing methods in motor fault diagnosis , 2001, Appl. Soft Comput..

[4]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[5]  W. R. Finley,et al.  Trouble shooting motor problems , 1993, Industry Applications Society 40th Annual Petroleum and Chemical Industry Conference.

[6]  Mo-Yuen Chow.  Methodologies of Using Neural Network and Fuzzy Logic Technologies for Motor Incipient Fault Detection , 1998 .

[7]  Teresa Orlowska-Kowalska,et al.  Neural networks application for induction motor faults diagnosis , 2003, Math. Comput. Simul..

[8]  Young-Seuk Park,et al.  Self-Organizing Map , 2008 .

[9]  Jing Yang,et al.  Fault detection and diagnosis of permanent-magnet DC motor based on parameter estimation and neural network , 2000, IEEE Trans. Ind. Electron..

[10]  Peter Vas,et al.  Artificial-Intelligence-Based Electrical Machines and Drives: Application of Fuzzy, Neural, Fuzzy-neural, and Genetic-Algorithm-based Techniques , 1999 .

[11]  Mo-Yuen Chow.  DESIGN AND TRAINING OF FEEDFORWARD NEURAL NETWORKS FOR MOTOR FAULT DETECTION , 1997 .

[12]  E. Afjei,et al.  Misalignment fault analysis and diagnosis in switched reluctance motor , 2011 .

[13]  E. Afjei,et al.  Sensorless Method for Eccentricity Fault Monitoring and Diagnosis in Switched Reluctance Machines Based on Stator Voltage Signature , 2013, IEEE Transactions on Magnetics.

[14]  Hao Chen,et al.  Fault Diagnosis Digital Method for Power Transistors in Power Converters of Switched Reluctance Motors , 2013, IEEE Transactions on Industrial Electronics.

[15]  Tao Han,et al.  ART–KOHONEN neural network for fault diagnosis of rotating machinery , 2004 .

[16]  Erkki Oja,et al.  Engineering applications of the self-organizing map , 1996, Proc. IEEE.

[17]  J. Penman,et al.  Feasibility of using unsupervised learning, artificial neural networks for the condition monitoring of electrical machines , 1994 .

[18]  A. Michaelides,et al.  Switched reluctance drives: a comparative evaluation , 1995 .

[19]  J. Penman,et al.  Using Kohonen Feature Maps To Monitor The Condition Of Synchronous Generators , 1993, Workshop on Neural Network Applications and Tools.

[20]  N. Selvaganesan,et al.  FUZZY BASED FAULT DETECTION AND CONTROL FOR 6/4 SWITCHED RELUCTANCE MOTOR , 2007 .

[21]  N. C. Chauhan,et al.  Soft Computing Methods , 2012 .

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

[23]  Xiao Zhi Gao,et al.  Genetic Algorithm Training of Elman Neural Network in Motor Fault Detection , 2002, Neural Computing & Applications.

[24]  Lorand Szabo,et al.  Fault tolerance study of switched reluctance machines by means of advanced simulation techniques , 2009 .

[25]  Marcelo Lubaszewski,et al.  Fault Detection, Diagnosis and Prediction in Electrical Valves Using Self-Organizing Maps , 2011, J. Electron. Test..

[26]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1993 .

[27]  N. Selvaganesan,et al.  Neural Control and Fault Diagnosis for 6/4 Switched Reluctance Motor , 2006, 2006 IEEE International Conference on Industrial Technology.

[28]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[29]  Raif Bayir,et al.  KOHONEN NETWORK BASED FAULT DIAGNOSIS AND CONDITION MONITORING OF PRE-ENGAGED STARTER MOTORS , 2005 .

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

[31]  Peter Vas,et al.  Parameter Estimation, Condition Monitoring, and Diagnosis of Electrical Machines , 1993 .

[32]  A. Murray,et al.  Extracting useful higher order features for condition monitoring using artificial neural networks , 1997, IEEE Trans. Signal Process..

[33]  Hamid A. Toliyat,et al.  Condition monitoring and fault diagnosis of electrical machines-a review , 1999, Conference Record of the 1999 IEEE Industry Applications Conference. Thirty-Forth IAS Annual Meeting (Cat. No.99CH36370).

[34]  E. Afjei,et al.  Static, Dynamic, and Mixed Eccentricity Faults Diagnosis in Switched Reluctance Motors Using Transient Finite Element Method and Experiments , 2012, IEEE Transactions on Magnetics.

[35]  C. Cossar,et al.  A Vibration-Based Condition Monitoring System for Switched Reluctance Machine Rotor Eccentricity Detection , 2008, IEEE Transactions on Magnetics.

[36]  O.F. Bay,et al.  Serial wound starter motor faults diagnosis using artificial neural network , 2004, Proceedings of the IEEE International Conference on Mechatronics, 2004. ICM '04..

[37]  A. J. Hoffman,et al.  The application of neural networks to vibrational diagnostics for multiple fault conditions , 2002, Comput. Stand. Interfaces.