Intelligent fault detection and classification for a power transmission line using power system stabilizer signals

The analysis of how power system stabilizer (PSS) able to stabilize the power system efficiently during the transmission line is an important area of research in power operation and planning. One of the essential works of power system security is to operate and handle information on fault detection effectively. In the proposed thesis, the oscillation for tow machine in “one phase fault”, “Fault with and without PSS”, “Fault with and without SVC”, are recorded at various fault locations. Multi Resolution Analysis (MRA) Wave Transform is used for fault detection. The MRA analyses the signal, where the statistical features for different locations and condition of the fault are extracted efficiently. The features are fed to Probabilistic Neural Network (PNN) to act as a fault classifier. The features are set as input vectors and the locations are set as the target. Graphic User Interface is used to monitor the whole system. When the fault is classified using PNN, its location can be used to generate control signals for PSS, which will be used to improve the stability in the power system. Therefore, this work shows the new techniques in detecting, classifying, and locating faults in a transmission line based on PSS signals as compared to traditional methods