15-01-2013, 04:53 PM
Artificial Neural Network applications for Power System Protection
Artificial Neural Network.ppt (Size: 529.5 KB / Downloads: 43)
INTRODUCTION*
The most commonly used systems for protecting transmission andsub transmission lines belong to the family of distance relays.* The Artificial Neural Network based designs of distance relays are not able to maintain the integrity of the boundaries of the relay characteristics of generic designs.* This paper presents a methodology that fully exploits the potential of ANNs in designing generic distance relays that retain the integrity of the boundaries of their characteristics.Applications include :* Direction discrimination for protecting transmission lines.* Fault classification for faults on double circuit lines.* ANN based distance relays.* Differential protection of three phase power transformers and faults on generator windings.
Transformer Protection:
* time delay artificial neural network processes the normalized values of samples of currents.* The Discrete Fourier transform filters the fundamental frequency and harmonic components of the currents.* The fundamental and harmonics of second to fifth order are applied to a multi-layer feed forward net work for implementing differential protection .
Proposed Methodology:
Fully exploits the potential of ANNs and makes the whole pro cess simple.
* The processes assigned to the different layers of an ANN are segregated by dividing the network into sub-networks.
* Each sub-network is responsible for performing an assigned protection function.
* Helps in better understanding the internal structure of the ANN.
* Makes the pro cess of modifying the network simpler whenever required
Training the Proposed Network:
* The training conducted by Back-Propagating the errors and maintained the integrity of operation around the boundary of the relay characteristics.
* The inputs used to train the ANN were suitable for detecting faults in zone 1 only i.e. 80 % of the transmission line.
* This approach will be adapted in the future work for designing ANN based systems for protecting zone-2 and zone-3 of the transmission system.