Diagnosis of chaotic ferroresonance phenomena using deep learning

Abstract

Ferroresonance is a non-linear and dangerous resonance phenomenon that can affect power networks and damage electrical equipment. The ferroresonance phenomenon is examined by dividing it into classes, with chaotic ferroresonance being the most dangerous type that causes overvoltage's. Detecting chaotic ferroresonance in a short period of time is of great importance in terms of taking measures and reducing equipment damage. In this study, we explored the application of deep convolutional neural networks (DCNNs) for the identification and classification of chaotic ferroresonance phenomena. Two pre-trained AlexNet models were adapted using transfer learning to perform these tasks. The first model was utilized to identify chaotic ferroresonance, while the second was employed to distinguish between different subtypes of chaotic ferroresonance by dividing voltage curve graphs into different periods and shapes. The training and testing of both DCNN models were conducted using snapshot images extracted from the voltage curves of all phase voltages. The results of the experiments showed high accuracy in both the identification and classification of chaotic ferroresonance phenomena.