Classification of power quality disturbances using time-frequency ambiguity plane and neural networks

Identification and classification of voltage and current disturbances in power systems is an important task in power system monitoring and protection. This paper presents a new approach for classifying the events that represent or lead to the degradation of power quality. The concept of ambiguity plane together with modified Fisher's Discriminant Ratio Kernel is used for feature extraction. A neural network with feedforward structure is chosen as the classifier. The results of extensive simulations confirm the feasibility of the proposed algorithm. This novel combination of methods shows promise for further development of a fully automated power quality monitoring system. The potential of developing a more powerful fuzzy classification method based on this algorithm is also discussed.

[1]  Electronics Letters , 1965, Nature.

[2]  B. Perunicic,et al.  Power quality disturbance detection and classification using wavelets and artificial neural networks , 1998, 8th International Conference on Harmonics and Quality of Power. Proceedings (Cat. No.98EX227).

[3]  Jo-Won Lee,et al.  Classification of power quality disturbances using orthogonal polynomial approximation and bispectra , 1997 .

[4]  Les E. Atlas,et al.  Class-dependent, discrete time-frequency distributions via operator theory , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Edward J. Powers,et al.  Power quality disturbance waveform recognition using wavelet-based neural classifier. I. Theoretical foundation , 2000 .

[6]  H. Wayne Beaty,et al.  Electrical Power Systems Quality , 1995 .

[7]  A. Y. Chikhani,et al.  Power quality detection and classification using wavelet-multiresolution signal decomposition , 1999 .

[8]  Les E. Atlas,et al.  Optimization of time and frequency resolution for radar transmitter identification , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[9]  F. Hlawatsch,et al.  Linear and quadratic time-frequency signal representations , 1992, IEEE Signal Processing Magazine.

[10]  Les E. Atlas,et al.  Data-driven time-frequency classification techniques applied to tool-wear monitoring , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).