06-04-2010, 06:11 PM
Transmission Line Fault Detection Using ANN
Introduction
What is ANN?
An artificial neural network(ANN) is an information processing paradigm that is inspired by the way
biological nervous system such as brain process information
Artificial Neural network are powerful in pattern recognition and classification
Salient Feature Of ANN
Fault Type Classifiers
Power Network Simulation
A 230Kv Power system is simulated by using EMTDC electromagnetic transient
program
The proposed Neural Network
Network Input
Pattern Generation and pre processing
Net work structure and Training
Proposed ANN structure
Network Input- The variation of current signal before and after fault incident is used for the fault detection
by ANN
The current wave form is sampled at 20 sample per cycle
The Resultant of 3 superimposed signal are first 3
input to the ANN
Pattern Generation and Preprocessing
Preprocessing significantly reduce the size of ANN and improve the performance and speed of training process
The Three phase current input signals were processed by 2nd order low pass filter
The proposed neural network
The training data set is used to train the ANN based selector Module
The Network has5 normalized input and 4 o/p
Network Evaluation
The proposed Network output for a double phase AB fault ( o/p for fault at 83 km)
Conclusion
In this paper a new approach for fault detection in transmission line is presented and its effective ness
is demonstrated
Introduction
What is ANN?
An artificial neural network(ANN) is an information processing paradigm that is inspired by the way
biological nervous system such as brain process information
Artificial Neural network are powerful in pattern recognition and classification
Salient Feature Of ANN
Fault Type Classifiers
Power Network Simulation
A 230Kv Power system is simulated by using EMTDC electromagnetic transient
program
The proposed Neural Network
Network Input
Pattern Generation and pre processing
Net work structure and Training
Proposed ANN structure
Network Input- The variation of current signal before and after fault incident is used for the fault detection
by ANN
The current wave form is sampled at 20 sample per cycle
The Resultant of 3 superimposed signal are first 3
input to the ANN
Pattern Generation and Preprocessing
Preprocessing significantly reduce the size of ANN and improve the performance and speed of training process
The Three phase current input signals were processed by 2nd order low pass filter
The proposed neural network
The training data set is used to train the ANN based selector Module
The Network has5 normalized input and 4 o/p
Network Evaluation
The proposed Network output for a double phase AB fault ( o/p for fault at 83 km)
Conclusion
In this paper a new approach for fault detection in transmission line is presented and its effective ness
is demonstrated