A novel wavelet assisted neural network for transmission line fault analysis

In this modern era, electric power has become the basic need for the business world. The quality and reliability of power needs to be maintained for obtaining optimum performance. Now-a-days power has also become a business commodity. Hence, faultless and lossless transmission and distribution of power is necessary. Power faults must be identified quickly from various sources (eg. information from relays etc.) and corrected as soon as possible. Advanced signal processing tools such as discrete wavelet transform (DWT) can be used very effectively for parameterization and characterization of the fault signals. On the other hand, properly configured neural network (NN) can be utilized for classification of the faults based on the DWT signal. Presently Electromagnetic Transient Program (EMTP) is used for simulation of a model transmission system and DWT and NN is performed using MATLAB. Faults of various types at different locations along the transmission line have been simulated and attempts have been made to correctly identify and locate the fault.