Analysis and Diagnosis of Partial Discharge of Power Capacitors Using Extension Neural Network Algorithm and Synchronous Detection Based Chaos Theory

Power capacitors are important equipment of the power systems that are being operated in high voltage levels at high temperatures for long periods. As time goes on, their insulation fracture rate increases, and partial discharge is the most important cause of their fracture. Therefore, fast and accurate methods have great importance to accurately diagnosis the partial discharge. Conventional methods often require multiple sensors and signal parameters, which in turn increases the cost and complexity of the system. In this paper, extension neural network algorithm and synchronous detection based chaos theory is proposed to estimate the partial discharge level of power capacitors. This method uses an error diagnosis system for the power capacitor and extracts the properties of the properties by the synchronous detection based chaos theory method. The prominent advantage of this method is effective compression of the mass data and extracts the feature data to enhance the accuracy of the extension neural network method. The results show that the ENN diagnosis rate was 90% higher than the multi-layer method (79%) and the extension method shows 70% lower diagnosis rate.