Fault Diagnosis of Transformer Winding Looseness Based on Vibration Signal and GOA-KELM Model

Abstract

Abstract Aiming at the problem that the latent fault of transformer winding looseness is difficult to identify and the diagnosis accuracy is low, a fault diagnosis method based on vibration signal and grasshopper optimization algorithm (GOA) optimization Kernel Extreme Learning Machine (KELM) is proposed in this paper. The method uses the time-domain and frequency-domain characteristics of the vibration signal. First, the time-frequency features of the vibration signals of multiple sensors are extracted, and a multi-sensor time-frequency feature matrix is constructed. Second, the feature matrix is identified and diagnosed by using GOA to optimize the KELM model. Finally, the feasibility and superiority of the proposed method are verified by the experimental data of 110kV transformer. The experimental results show that the method in this paper can successfully identify the looseness of different degrees of windings and the looseness of different phases, and has a higher diagnostic accuracy than the existing algorithms.