Intelligent diagnosis method for plant machinery using wavelet transform, genetic programming and possibility theory

This paper proposes an intelligent diagnosis method for plant machinery using wavelet transform (WT) genetic programming (GP) and possibility theory. The WT is used to extract feature spectra of each machine state from measured vibration signal for distinguishing faults. Excellent symptom parameters (SP) for detecting fault states are automatically generated by GP. The membership functions of symptom parameters are established using possibility theory for resolving the ambiguous diagnosis problems. The methods proposed in this paper are verified by applying them to the fault diagnosis of gear equipment.

[1]  Peng Chen,et al.  Self-reorganization method of symptom parameters for failure diagnosis by genetic algorithms , 1996, Proceedings of the 1996 IEEE IECON. 22nd International Conference on Industrial Electronics, Control, and Instrumentation.

[2]  Khaled H. Hamed,et al.  Time-frequency analysis , 2003 .

[3]  Peng Chen,et al.  Sequential fuzzy diagnosis method and identification method of membership function by probability and possibility theories , 1996, 1996 IEEE International Conference on Systems, Man and Cybernetics. Information Intelligence and Systems (Cat. No.96CH35929).

[4]  Peng Chen,et al.  Extraction Method of Failure Signal by Genetic Algorithm and the Application to Inspection and Diagnosis Robot , 1995 .

[5]  Peng Chen,et al.  Self-reorganization of symptom parameters in frequency domain for failure diagnosis by genetic algorithms , 1998, J. Intell. Fuzzy Syst..

[6]  Toshio Toyota,et al.  Fuzzy diagnosis and fuzzy navigation for plant inspection and diagnosis robot , 1995, Proceedings of 1995 IEEE International Conference on Fuzzy Systems..