Detection and Classification of Faults in High Voltage Transmission Lines Using Artificial Neural Networks

There is a possibility that errors in the transmission line will be difficult to identify and categorize. Since the beginning of time, this issue has been present. This was one of the most difficult obstacles that the power had to face. For the most part, the protective relay device, tape, and management and security software systems are utilized for the purpose of detecting the problem and disconnecting the damaged unit of the system from the other units. The identification and classification of flaws is the primary subject of this paper, when it comes to transmission cables that support high voltage the detection of faults is also included. The categorizing process involves the utilization of artificial neural networks (ANN). The back-propagation algorithm makes use of a network of computers in order to direct the distribution for each of the three steps that comprise the fault process. The process of identifying and classifying research into neural networks by employing many buried layers of neurons, each of which had a unique sum, was subject to the necessity that the choice of neural network at each step be made. Using this concept as the foundation for a conventional transmission, the creation of a line for producing the voltage and current settings was carried out. MATLAB/SIMULINK network is used whose simplification was selected as the choice Carry out simulations of every feasible scenario involving the development of defects and tests. Using recently developed test data sets, the Ann is trained and then put through a series of tests to identify any errors. Mistakes in classification and detection occurred. The results of the simulation demonstrated that such models, which are based on artificial neural networks, can achieve performance fulfillment. These models are designed to facilitate the efficient organization and identification of defects on transmission lines.