Title :
Identification of the shaft orbits for turbine rotor by modified Fourier descriptors
Author :
Fu, Bo ; Zhou, Jian-zhong ; Chen, Wen-Qing ; Yu, Bing-Hui
Author_Institution :
Coll. of Hydropower Eng., Huazhong Univ. of Sci. & Technol., Wuhan, China
Abstract :
A novel method based on modified Fourier descriptors is proposed to recognize the shaft orbits of turbine rotor. The principle, invariants and applications of modified Fourier descriptors are discussed in detail. The back-propagation (BP) neural network and modified Fourier descriptors are combined to classify the shaft orbits for the fault diagnosis for turbine rotor. The simulation results of automatic identification for three typical shaft orbits indicate that the proposed method is accurate and practicable.
Keywords :
Fourier analysis; backpropagation; fault diagnosis; neural nets; pattern recognition; rotors; shafts; turbines; Fourier descriptors; backpropagation neural network; fault diagnosis; shaft orbits identification; shape recognition; turbine rotor; Discrete Fourier transforms; Discrete transforms; Fault diagnosis; Image recognition; Machinery; Neural networks; Orbits; Shafts; Shape; Turbines;
Conference_Titel :
Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on
Print_ISBN :
0-7803-8403-2
DOI :
10.1109/ICMLC.2004.1382365
