Fault Classification of Three-Phase Transmission Network using Genetic Algorithm

Majid Jamil, Sanjeev Kumar Sharma, D. K. Chaturvedi

The present paper proposes a very simple method for fault sorting of three-phase transmission line, which is based upon the wavelet transform and Genetic Algorithm. Three phase currents of only one end are measured and features are extracted using discrete wavelet transform. These features are then used as inputs to the genetic algorithm. The training data set for genetic algorithm is obtained by simulating the ten different types of faults using various values of fault inception angles and fault resistances, so that the accurate results can be obtained. The proposed genetic algorithm employs twenty inputs and only one output for classifying the faults. The uniqueness of the proposed method is that all the features, inputs used in developing the algorithm are normalized, so that the method can be used for any system without any substantial changes. The simulation of the three-phase transmission line network and wavelet transform analysis are achieved in the tool boxes of MATLAB^® and genetic algorithm codes are also written in MATLAB^®.