论文信息 - Development of High-Voltage Discharge Fault Detection System

Development of High-Voltage Discharge Fault Detection System

A high-voltage discharge fault detection system was developed based on ultraviolet (UV) image processing technology. By making use of image processing theory, the interference of noises in ultraviolet images was effectively eliminated. In addition, a fault state recognition method was established and tested for the high-voltage discharge fault detection with the data from the developed system. And an approach based on RBF artificial neural network theory is proposed. According to the results simulated by MATLAB program, the developed system as well as the fault state recognition method could identify device faults and operation conditions accurately,and also they match well. Therefore, the developed high-voltage discharge fault detection system using UV image processing technology has potential for practical use.

[1] Chin-Teng Lin,et al. Neural fuzzy systems , 1994 .

[2] Takashi Nagano,et al. A neural network model for the developmental process of hypercomplex cells , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[3] Chin-Teng Lin,et al. A recurrent self-organizing neural fuzzy inference network , 1999, IEEE Trans. Neural Networks.

[4] Generator Ground Protection. An American National Standard , 1985 .

[5] Noritaka Shigei,et al. Neural Networks Determining Injury by Salt Water for Distribution Lines , 2004, ISNN.

[6] Chen Xiyuan. Modeling random gyro drift by time series neural networks and by traditional method , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[7] Martin Vetterli,et al. Adaptive wavelet thresholding for image denoising and compression , 2000, IEEE Trans. Image Process..

[8] Hiromi Miyajima,et al. A Learning Method of Fuzzy Inference Rules Using Vector Quantization , 1998 .