Fault Detection and Classification of Faults in Hydropower plants

The hydropower plants are crucial for safeguarding the consistency and the safety of the power generation systems.This research work presents a extensive study onthe classification of the electrical faults and the fault detection techniques in the hydropower plants. As hydropower systems become more sophisticated, the importance of being able to correctly identify and classify electrical faults has gained ever more significance. The main objective is to devise accurate methods for the identification and classification of the large diversity of electrical faults occurring in hydropower plants. The importance of effective classification and fault detection has increased manifold due to increased complexities of the modern power system coupled with the critical need to ensure reliable operational performance.The classification approach leverages the advanced machine learning algorithms which includes Support Vector Machine (SVM), Random Forest and Radial Basis Function Network (RBFN) to analyze the electrical signals and patterns associated with the different fault conditions. These techniques would be effective to identify the faults by considering the voltage and current evolved by the different phases of the hydropower plants. Comparisons of accuracy by SVM and Random Forest are made out and thus relate to the classification of fault detection of these hydropower plants. This paper presents a knowledge-based approach for fault diagnosis in hydroelectric power systems.