Tie Line Fault Detection And Classification In Power System Based On Discrete Wavelet Transform And Total Harmonic Distortion Using Machine Learning

Continuous and smooth power transmission is the major aim of all the power utility corporations, so as a result it is very crucial to detect and classify the fault happening on the tie line. Proper detection of faults on the tie line can protect the generator from getting damaged also it will help to continue the smooth operation of the power system. Thus, this present research gives a novel procedure for the detection and classification of fault on tie lines based on wavelet transform of current, voltage and reactive power near to the generator and generator stator current THD. Here, the voltage, current and reactive power signal is taken under fault conditions and is processed through wavelet along with THD samples of generator stator currents are taken as the features to train the machine learning model. For each different faulty situation, we will get different characteristics of the above signals and hence we can train the model accordingly and can distinguish the situation efficiently. This proposed method is found efficient to detect and classify faults. The fault simulation procedure is done by simulating the model of a power system network using MATLAB Simulink and the features are extracted from the model for various situations and the extracted features are used to train the machine learning model using python to identify and classify the fault occurring on the tie line.