This article presents a neural-fuzzy technology-based classifier for the recognition of power quality disturbances. The classifier adopts neural networks in the architecture of frequency-sensitive competitive leaning and learning vector quantization. With given size of code words, the neural networks are trained to determine the optimal decision boundaries separating different categories of disturbances. To cope with the uncertainties in the involved patten recognition, the neural network outputs, instead of being taken as the final classification, are used to activate the fuzzy-associative-memory recalling for identifying the most possible type that the input waveform may belong to. Furthermore, the input waveforms are preprocessed by the wavelet transform for feature extraction so as to improve the classifier with respect to recognition accuracy and scheme simplicity. Each sub-band of the transform coefficients is then utilized to recognize the associated disturbances.
[1]
S. Mallat.
Multiresolution approximations and wavelet orthonormal bases of L^2(R)
,
1989
.
[2]
Veljko Milutinovic,et al.
Neural Networks: Concepts, Applications, and Implementations
,
1991
.
[3]
Michael Negnevitsky,et al.
Discussion of "Power quality disturbance waveform recognition using wavelet-based neural classifier-Part 1: theoretical foundation" [Closure to discussion]
,
2000
.
[4]
H. Wayne Beaty,et al.
Electrical Power Systems Quality
,
1995
.
[5]
A. K. Ghosh,et al.
The classification of power system disturbance waveforms using a neural network approach
,
1994
.
[6]
Teuvo Kohonen,et al.
Self-Organization and Associative Memory
,
1988
.
[7]
Bart Kosko,et al.
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
,
1991
.