This paper presents a new approach to detection of high impedance faults in distribution systems using artificial neural networks. The proposed neural network, was trained by data from simulation of a distribution system under different faults conditions, and tested by data with different system conditions. The proposed neural network has been implemented on a digital signal processor board and its behavior is investigated on a computer power system model. Details of the design procedure, implementation and the results of performance studies with the proposed relay are given in this paper. Performance studies results show that the proposed algorithm performs very well in detecting a high impedance fault with nonlinear arcing resistance. It is clearly shown that with this integrated approach, the accuracy in fault detection is significantly improved compared to other techniques based on conventional algorithms.
A Universal High Impedance Fault Detection Technique for Distribution System Using S-Transform and Pattern Recognition
