Neural Network-Based Fault Diagnosis of Joints in High Voltage Electrical Lines

In this paper a classification system based on a complex-valued neural network is used to evaluate the health state of joints in high voltage overhead transmission lines. The aim of this method is to prevent breakages on the joints through the frequency response measurements obtained at the initial point of the network. The specific advantage of this kind of measure is to be non-intrusive and therefore safer than other approaches, also considering the high voltage nature of the lines. A feedforward multi-layer neural network with multi-valued neurons is used to achieve the goal. The results obtained for power lines characterized by three and four junction regions show that the system is able to identify the health state of each joint, with an accuracy level greater than 90%.