Applications of neural networks to power system fault diagnosis have provided positive results and shown advantages in process speed over conventional approaches. This paper describes the application of a Kohonen neural network to fault detection and classification using the fundamental components of currents and voltages. The Electromagnetic Transients Program is used to obtain fault patterns for the training and testing of neural networks. Accurate classifications are obtained for all types of possible short circuit faults on test systems representing high voltage transmission lines. Short training time makes the Kohonen network suitable for on-line power system fault diagnosis. The method introduced in the paper can be easily extended to any size power system since the only information required for the NN to function are those that are recorded at substation fault recorders. With fast NN hardware now becoming available, on-line implementation is only a question of economics.
B. H. Chowdhury and K. Wang, "Fault Classification Using Kohonen Feature Mapping," Proceedings of the International Conference on Intelligent Systems Applications to Power Systems, 1996, Institute of Electrical and Electronics Engineers (IEEE), Jan 1996.
The definitive version is available at http://dx.doi.org/10.1109/ISAP.1996.501067
International Conference on Intelligent Systems Applications to Power Systems, 1996
Electrical and Computer Engineering
Keywords and Phrases
Electromagnetic Transients Program; Kohonen Feature Mapping; Diagnostic Expert Systems; Digital Simulation; Fault Classification; Fault Detection; Fault Diagnosis; Fault Patterns; High Voltage Transmission Lines; Learning (Artificial Intelligence); Neural Network Testing; Neural Networks; On-Line Implementation; Power System Analysis Computing; Power System Fault Diagnosis; Self-Organizing Feature Maps; Short Circuit Faults; Short-Circuit Currents; Substation Fault Recorders; Training
Article - Conference proceedings
© 1996 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.