Motor Fault Detection Using Fuzzy Logic
TSINGHUA SCIENCE AND TECHNOLOGY ISSNll1007-0214ll12/18llpp225-233 Volume 14, Number 2, April 2009
On-Line Fast Motor Fault Diagnostics Based on Fuzzy Neural Networks*
DONG Mingchui (董名垂)**, CHEANG Takson (郑德信)†, CHAN Sileong (陈思亮)†
Department of Automation, Tsinghua University, Beijing 100084, China; † Faculty of Science and Technology, University of Macau, Macau, China Abstract: An on-line method was developed to improve diagnostic accuracy and speed for analyzing running motors on site. On-line pre-measured data was used as the basis for constructing the membership functions used in a fuzzy neural network (FNN) as well as for network training to reduce the effects of various static factors, such as unbalanced input power and asymmetrical motor alignment, to increase accuracy. The preprocessed data and fuzzy logic were used to find the nonlinear mapping relationships between the data and the conclusions. The FNN was then constructed to carry motor fault diagnostics, which gives fast accurate diagnostics. The on-line fast motor fault diagnostics clearly indicate the fault type, location, and severity in running motors. This approach can also be extended to other applications. Key words: fault detection and isolation; gravity-average method; supervisory learning; fuzzy neural networks
Introduction
Benbouzid[1] lists 365 books, conferences, and journal papers related to fault diagnostics of induction motors with stator winding inter-turn short circuits and failed rotor bars as the major causes of motor failures. The early math-model-based diagnostics, such as parameter estimation[2], finite element analyses[3], and adaptive observer schemes[4], had the drawbacks of relying upon accurate mathematical models and a detailed understanding of the motors. Later approaches, such as motor current signature analysis (MCSA)[5,6] and wavelet analyses[7,8], require complicated signal preprocessing like fast Fourier transform (FFT) or wavelet transform (WT). However,
On-Line Fast Motor Fault Diagnostics Based on Fuzzy Neural Networks*
DONG Mingchui (董名垂)**, CHEANG Takson (郑德信)†, CHAN Sileong (陈思亮)†
Department of Automation, Tsinghua University, Beijing 100084, China; † Faculty of Science and Technology, University of Macau, Macau, China Abstract: An on-line method was developed to improve diagnostic accuracy and speed for analyzing running motors on site. On-line pre-measured data was used as the basis for constructing the membership functions used in a fuzzy neural network (FNN) as well as for network training to reduce the effects of various static factors, such as unbalanced input power and asymmetrical motor alignment, to increase accuracy. The preprocessed data and fuzzy logic were used to find the nonlinear mapping relationships between the data and the conclusions. The FNN was then constructed to carry motor fault diagnostics, which gives fast accurate diagnostics. The on-line fast motor fault diagnostics clearly indicate the fault type, location, and severity in running motors. This approach can also be extended to other applications. Key words: fault detection and isolation; gravity-average method; supervisory learning; fuzzy neural networks
Introduction
Benbouzid[1] lists 365 books, conferences, and journal papers related to fault diagnostics of induction motors with stator winding inter-turn short circuits and failed rotor bars as the major causes of motor failures. The early math-model-based diagnostics, such as parameter estimation[2], finite element analyses[3], and adaptive observer schemes[4], had the drawbacks of relying upon accurate mathematical models and a detailed understanding of the motors. Later approaches, such as motor current signature analysis (MCSA)[5,6] and wavelet analyses[7,8], require complicated signal preprocessing like fast Fourier transform (FFT) or wavelet transform (WT). However,
References: [1] Benbouzid M E H. Bibliography on induction motors DONG Mingchui (董名垂) et al：On-Line Fast Motor Fault Diagnostics Based on … [9] Harihara P P, Kim K A. Signal-based versus model-based fault diagnosis ― A trade-off in complexity and performance. In: Proceedings of the SPEMPED 2003 Symposium on Diagnostics for Electric Machines, Power Electronics and Drives. Atlanta, USA, 2003: 277-282. [10] Ayhan B, Chow M Y, Song M H. Multiple discriminate analysis and neural-network-based monolith and partition fault-detection schemes for broken rotor bar in induction motors. IEEE Transactions on Industrial Electronics, 2006, 53(4): 1298-1308. [11] Lehtoranta J, Koivo H N. Fault diagnosis of induction motors with dynamical neural networks. In: Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Hawaii, USA, 2005, 3: 2979-2984. [12] Filippetti F, Grellet G, Salles G, et al. An approach to the knowledge representation about induction machine diagnostics in expert systems. In: Proceedings of the International Conference on Electrical Machines. Pisa, Italy, 1988, 3: 289-296. [13] Ritchie E, Pedersen J K. Diagnosis of rotor faults in squirrel cage induction motors using a fuzzy logic approach. In: Proceedings of the International Conference on Electrical Machines. Paris, France, 1994, 2: 348-352. [14] Tan Woei, Huo Hong. A generic neurofuzzy model-based 233 approach for detecting faults in induction motors. IEEE Transactions on Industrial Electronics, 2005, 52(5): 234-240. [15] Chow Mo-Yuen. Methodologies of Using Neural Network and Fuzzy Logic Technologies for Motor Incipient Fault Detection. Singapore: World Scientific Publishing Co. Pte. Ltd., 1997. [16] Giarratano J C, Riley G D. Expert System Principles and Programming. Fourth Edition. Beijing, China: Thomson Learning, Inc., 2005. [17] Zhang Linzheng, Cheang Tak Son. Improvement on analysis of internal faults of three-phase induction motors. In: Proceedings of the 6th International Conference on Education and Practice of Computational Methods in Engineering and Science. Guangzhou, China, 1997: 804-809. [18] Zhang Linzheng, Cheang Tak Son. Two new approaches to analysis of inner-fault of squirrel-cage rotor for three-phase induction motors. In: Proceedings of the International Conference on Electrical Machines and Systems. Shenyang, China, 2001: 51-55. [19] Dong M, Cheang T, Sekar B D, et al. Fuzzy-expert diagnostics for detecting and locating internal faults in three phase induction motors. Tsinghua Science and Technology, 2008, 13(6): 817-822.