A modular methodology for fast fault detection and classification in power systems

This paper presents a modular yet integrated approach to the problem of fast fault detection and classification. Although the specific application example studied here is a power system, the method would be applicable to arbitrary dynamic systems. The approach is quite flexible in the sense that it can be model-based or model-free. In the model-free case, we emphasize the use of concepts from signal processing and wavelet theory to create fast and sensitive fault indicators. If a model is available then conventionally generated residuals can serve as fault indicators. The indicators can then be analyzed by standard statistical hypothesis testing or by artificial neural networks to create intelligent decision rules. After a detection, the fault indicator is processed by a Kohonen network to classify the fault. The approach described here is expected to be of wide applicability. Results of computer experiments with simulated faulty transmission lines are included.

[1]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[2]  Kazuo Nishimura,et al.  Power system state evaluation by structured neural network , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[3]  P. Crossley,et al.  Distance Protection Based on Travelling Waves , 1983, IEEE Transactions on Power Apparatus and Systems.

[4]  Helge J. Ritter,et al.  Neural computation and self-organizing maps - an introduction , 1992, Computation and neural systems series.

[5]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[6]  J. L. Aravena,et al.  Power system fault detection and state estimation using Kalman filter with hypothesis testing , 1991 .

[7]  Adly A. Girgis,et al.  Application of adaptive Kalman filtering in fault classification, distance protection, and fault location using microprocessors , 1988 .

[8]  Masahiro Fujita,et al.  Analysis of neighborhood interaction in Kohonen neural networks , 1991, [1991] Proceedings. The Fifth International Parallel Processing Symposium.

[9]  Mark W. White,et al.  A neural network approach to the detection of incipient faults on power distribution feeders , 1990 .

[10]  D. L. Lubkeman,et al.  Unsupervised learning strategies for the detection and classification of transient phenomena on electric power distribution systems , 1991, Proceedings of the First International Forum on Applications of Neural Networks to Power Systems.

[11]  P. P. Vaidyanathan,et al.  On orthonormal wavelets and paraunitary filter banks , 1993, IEEE Trans. Signal Process..

[12]  T. T. Lie,et al.  ANN based pattern classification of synchronous generator stability and loss of excitation , 1994 .

[13]  Marios M. Polycarpou,et al.  Learning methodology for failure detection and accommodation , 1995 .

[14]  Fahmida N. Chowdhury.  On-line fault detection in multi-output systems using Kalman filter and neural network , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[15]  Stéphane Mallat,et al.  Singularity detection and processing with wavelets , 1992, IEEE Trans. Inf. Theory.

[16]  Hong-Tzer Yang,et al.  On-line fault diagnosis of power substation using connectionist expert system , 1995 .

[17]  J.L. Pinto de Sa,et al.  Modal Kalman Filtering Based Impedance Relaying , 1991, IEEE Power Engineering Review.

[18]  H. S. Chandrasekharaiah,et al.  Fault detection and diagnosis of power systems using artificial neural networks , 1991, Proceedings of the First International Forum on Applications of Neural Networks to Power Systems.

[19]  Octavia Camps,et al.  Wavelets and power system transients: feature detection and classification , 1994, Defense, Security, and Sensing.

[20]  Alessandro Ferrero,et al.  A fuzzy-set approach to fault-type identification in digital relaying , 1994 .

[21]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[22]  Magdy M. A. Salama,et al.  Neural network system using the multi-layer perceptron technique for the recognition of PD pulse shapes due to cavities and electrical trees , 1995 .