IUP Publications Online
Home About IUP Magazines Journals Books Archives
     
Recommend    |    Subscriber Services    |    Feedback    |     Subscribe Online
 
The IUP Journal of Electrical and Electronics Engineering:
Detection and Error Analysis of High Impedance Fault Using Wavelet Transform, Traveling Wave and Support Vector Machine
:
:
:
:
:
:
:
:
:
 
 
 
 
 
 
 

Physical connection between phase conductors with surface below the lines, trees and walls of building leads to High Impedance Fault (HIF). This will cause ignition via arc or heat of substances. Detection of HIF is difficult because occurrence of them leads to a slight increase in load current, and it can be considered as a usual increase in the value of load current incorrectly. Due to HIF, the whole energy produced by a power company is not achieved by the loads. For detecting fault accurately and quickly, a method based on Wavelet Transform (WT) and Support Vector Machine (SVM) has been proposed. WT is used as feature extraction and decomposes current or voltage waveform. Initially, current or voltage waveform is decomposed in the first level and these features are again decomposed in the subsequent level. Sampled data collected by DWT is used as input to SVM. SVM is used as classifier.

 
 

The most challening task in power system is detection of faults. Low impedence fault can be detected with the help of protection relays, since they produce sufficient amount of current for detection. But High Impedance Fault (HIF) cannot be detected by these relays due to insufficient amount of fault current. HIF has fault current in the range of a few mA. Unsuccessful detection of HIF is dangerous for human. HIF occurs if any line is broken and touches the ground or if any line comes in contact with tree branches.

 
 
 

Electrical and Electronics Engineering Journal, Support Vector Machine (SVM), Wavelet Transform (WT), Transmission line, High Impedance Fault (HIF)