Identification and Extraction of Surface Discharge Acoustic Emission Signals Using Wavelet Neural Network

Abstract

A hybrid model incorporating wavelet and feed forward back propagation neural network (WFFB-NN) is presented which is used to detect, identify and characterize the acoustic signals due to surface discharge (SD) activity and hence differentiate abnormal operating conditions from the normal ones. The tests were carried out on cleaned and polluted high voltage glass insulators by using surface tracking and erosion test procedure of IEC 60587. A laboratory experiment was conducted by preparing the prototypes of the discharges. This study suggests a feature extraction and classification algorithm for SD classification, which when combined together reduced the dimensionality of the feature space to a manageable dimension. Wavelet signal processing toolbox is used to recover the surface discharge acoustic signals by eliminating the noisy portion and to reduce the dimension of the feature input vector. The test results show that the proposed approach is efficient and reliable. The error during training process was acceptable and very low which attained 0.0074 in only 14 iterations.

Self-adaptive Hierarchical Threshold Denoising Based on Parametric Construction of Fixed-length Tight-supported Biorthogonal Wavelets

“…Inspired by wavelet threshold denoising [9][10][11][12][13], this paper sets up the wavelet filter bank suitable for threshold denoising, following the parametric construction of fixed-length tightlysupported (FLTS) biorthogonal wavelet. The obtained wavelets were simulated on Matlab and used to denoise noisy images.…”