Fault Location in Distribution Systems based on Artificial Neural Networks and Application of GIS

1
Fault Location in Distribution Systems based on
Artificial Neural Networks and Application of GIS

• M.Zangiabadi M.R.Haghifam A.Khanbanha
• University of Tehran Tarbiat Modares
  University Kerman Regional Electric Co.

2
Fault Location Estimation

• Off-Line Methods
• Trial and error method with energization the line
  section by section
• On-Line Methods
• High frequency transient signals
• Wavelets
• Pattern recognition
• Neural network

3
Case Study

• Input data for neural network
• Voltage
• Current
• Simulation software
• EMTDC
• MATLAB
• Line model
• Bergeron model

configuration of feeder and simulator output
4
Simulator Output
Single-phase to ground fault in the middle of
feeder
Three-phase to ground fault in the middle of
feeder
5
The Proposed Neural Network Structure

• Three-layer feed forward neural network
• Error back propagation training method
• Input data voltage and current are normalized
• Output layer
• Distance
• Flag which refers to lateral number

6
The results of L-G fault

• Training data is prepared in pitches of 50 meters
• The resistance of fault is changed in steps of 5
  from 0 to 25 ohms

7
Selecting the best structure

• Number of epochs is considered 1000 epochs
• Mean Square Error criterion evaluates the
  structure

Error Percentage of Neural Network for L-G fault
8
Structure of Neural Networks as Fault Locator
Distance
Distance
9
Combination with GIS Software
10
Thanks for your attention

• I would also like to thank University of Tehran
  (UT) and Kerman Regional Electric Company (KREC)
  for their supports