Certainty Improvement in Diagnosis of Multiple Faults by Using Versatile Membership Functions for Fuzzy Neural Networks
Because the relationship between frequency symptoms and fault causes are different, this study uses fuzzy neural network (FNN) with versatile membership functions to diagnose multiple faults in rotary machinery. According to the frequency symptom values for each fault causes, three kinds of membership functions are used. Besides, the structure of the FNN is large which spend much training time. Thus, when the matrix between frequency symptoms and fault causes can decoupled, the relational matrix decomposed into several sub-matrixes and the structure of the FNN can also divided into several sub-networks. In this study, two above-mention approaches are combined to diagnose multiple faults and compared with neural network (NN), FNN with single/versatile membership functions in two actual cases.
KeywordsMembership Function Induction Motor Fuzzy Neural Network Frequency Symptom Multiple Fault
Unable to display preview. Download preview PDF.
- 3.Goode, P.V., Chow, M.Y.: Neural/Fuzzy Systems for Incipient Fault Detection in Induction Motors. In: Proceedings of IECON, pp. 332–337 (1993)Google Scholar
- 4.Wu, C.Z., Yan, H., Ma, J.F.: Method Research of Noise Diagnosis Based on Fuzzy Neural Network. In: Fourth International Conference on ICSP 1998, vol. 2, pp. 1370–1373 (1998)Google Scholar
- 5.Tang, T., Zhu, Y., Li, J., Chen, B., Lin, R.: A Fuzzy and Neural Network Integrated Intelli-gence Approach for Fault Diagnosing and Monitoring. In: UKACC International Conference on Control 1998, vol. 2, pp. 975–980 (1998)Google Scholar
- 6.Freeman, J.A., Skapura, D.M.: Neural Networks Algorithms, Applications, and Programming Techniques. Addison-Wesley, Reading (1992)Google Scholar
- 7.Rao, J.S.: Vibratory Condition Monitoring of Machines. Alpha Science Int. LTD (2000)Google Scholar