High impedance arcing fault detection in MV networks using discrete wavelet transform and Artificial Neural Networks

Arcing faults in transmission networks are caused when a current carrying conductor makes an unwanted electrical contact with ground or is temporarily short circuited with another current carrying conductor through a high impedance medium. High impedance arcing faults restricts the flow of current below the detection level of the protective devices and hence cannot be detected by conventional relays. In this paper a new method is proposed for the detection of arcing faults due to leaning trees in medium voltage (MV) networks. Firstly, an arc model is developed in order to reproduce the fault circumstances. Then based on a fault detection algorithm the fault features are extracted using a signal processing technique called Discrete Wavelet Transform (DWT).The proposed algorithm is implemented in a simple MV network to identify the faulty phase and in a feeder network to identify both the faulty phase and feeder. Further the results obtained using DWT is validated with the help of Artificial Neural Networks (ANN).The results obtained above validate the effectiveness of the proposed methodology.