Power Quality Event Recognition using Fisher Discriminant Kernel and Artificial Neural Networks

R. Sureshkumar, G. Bharath Kumar, S. Vasantharathna, and P. Anbalagan (India)


Power Quality, Fisher Discrimination Ratio, Class Dependent Time Frequency Representation, Artificial Neural Networks, Ambiguity Plane.


Identification and classification of voltages and current disturbances in power systems is an important task in power system monitoring and protection. Existing automatic recognition methods need much improvement in terms of their versatility, reliability and accuracy. The objective of this paper is to develop a state of the art signal classification algorithm for classifying different types of power quality disturbances, based on signal processing and pattern recognition techniques. In this algorithm the class dependant time frequency representation (TFR) designed from ambiguity plane is used for extracting features. Fisher's discriminant function, which is deliberately designed for maximizing the separatability between classes helps in designing the class dependent TFR. Classification of the features extracted is done using feedforward neural networks.

Important Links:

Go Back