Share Email Print
cover

Proceedings Paper

Pattern recognition and analysis of short duration disturbance based on neural network
Author(s): Huaying Wang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

For quantitative detection of distortions of voltage waveform, a novel approach based on wavelet transform (WT) to detect and locate the power quality (PQ) disturbances is proposed. Due to expansion of power electronics devices, the wide diffusion of nonlinear and time-variant loads has caused massive serious PQ problems in power system. The signal containing noise is de-noised by WT, and then become input node to the wavelet neural network. The standard genetic algorithm is utilized to complete the network structure, and then the fundamental component of the signal is estimated to extract the mixed information. Therefore the disturbance signal is acquired by subtracting the fundamental component. In processing of disturbances signal, the principle of singularity detection using WT modulus maxima is presented with dyadic WT approach for the detection and localization of the PQ. The simulation results demonstrate that the proposed method is effective.

Paper Details

Date Published: 13 October 2008
PDF: 4 pages
Proc. SPIE 7127, Seventh International Symposium on Instrumentation and Control Technology: Sensors and Instruments, Computer Simulation, and Artificial Intelligence, 71271R (13 October 2008); doi: 10.1117/12.806445
Show Author Affiliations
Huaying Wang, Hebei Univ. of Engineering (China)


Published in SPIE Proceedings Vol. 7127:
Seventh International Symposium on Instrumentation and Control Technology: Sensors and Instruments, Computer Simulation, and Artificial Intelligence

© SPIE. Terms of Use
Back to Top