论文信息 - Implementation of neural network and genetic algorithms for novelty filters for fault detection

Implementation of neural network and genetic algorithms for novelty filters for fault detection

In this paper a method of detecting shorted turns in rotating machines using computational intelligence techniques (neural network and genetic algorithm) is presented. The methods of signal processing and detection of faults in operating machines is discussed. The use of novelty filters for the detection of shorted turns and mechanical failures in operating machines is described. Genetic algorithm have been used to train the neural network to enhance the capabilities of the novelty detector neural network. The proposed techniques have been applied on an induction machine and the simulation results have been presented to show the effectiveness of the proposed technique.

H. Elsimary

[1] M. Arozullah,et al. Neural network based novelty filtering for signal detection enhancement , 1992, [1992] Proceedings of the 35th Midwest Symposium on Circuits and Systems.

[2] Mo-Yuen Chow,et al. On the application and design of artificial neural networks for motor fault detection. II , 1993, IEEE Trans. Ind. Electron..

[3] Stephen Jose Hanson,et al. A Neural Network Autoassociator for Induction Motor Failure Prediction , 1995, NIPS.

[4] Teuvo Kohonen,et al. Associative memory. A system-theoretical approach , 1977 .

[5] Mo-Yuen Chow,et al. Methodology for on-line incipient fault detection in single-phase squirrel-cage induction motors using artificial neural networks , 1991 .