A Long Memory Process Based Parametric Modeling and Recognition of PD Signal
We address the problem of recognition and retrieval of relatively weak industrial signal such as Partial Discharges (PD) buried in excessive noise. The major bottleneck being the recognition and suppression of stochastic pulsive interference (PI) which has similar time-frequency characteristics as PD pulse. Therefore conventional frequency based DSP techniques are not useful in retrieving PD pulses. We employ statistical signal modeling based on combination of long-memory process and probabilistic principal component analysis (PPCA). An parametric analysis of the signal is exercised for extracting the features of desired pules. We incorporate a wavelet based bootstrap method for obtaining the noise training vectors from observed data. The procedure adopted in this work is completely different from the research work reported in the literature, which is generally based on deserved signal frequency and noise frequency.
Unable to display preview. Download preview PDF.
- 1.Satish, L., Nazneen, B.: Wavelet denoising of PD signals buried in excessive noise and interference. IEEE Transaction on DEI 10(2), 354–367 (2003)Google Scholar
- 2.Tipping, M.E., Bishop, C.M.: A hierarchical latent variable model for data visualization. IEEE trans. PAMI 20(3), 25–35, 281–293 (1998)Google Scholar
- 3.Hayes, M.H.: Statistical Digital Signal Processing and Modelling, ch. 8, pp. 445–447. John Wiley and Sons inc., West Sussex (1996)Google Scholar
- 5.Wornell, G.: Signal Processing with Fractals: A Wavelet Based Approach, ch. 3, pp. 30–46. Prentice Hall PTR, Newjersy (1996)Google Scholar
- 8.Stone, G.C.: Practical techniques to measure PD in operating equipment. In: Proc. 3rd Int. Conf. on Properties and Application of Dielectric Materials, Tokyo, Japan, pp. 1–17 (1991)Google Scholar
- 9.Kay, S.M.: Fundamentals of Statistical Signal Processing-Estimation Theory, ch. 7,10,11,12, pp. 157–214, 309–415. Prentice Hall PTR, Newjersy (1998)Google Scholar