Study on the aging diagnosis of oil-paper insulation based on ultrasonic time-frequency characteristics

Timely and effective identification of transformer aging is of great importance to the safety and stability of the power system. In this paper, a method for diagnosing the aging of oil-paper insulation based on ultrasonic time-frequency characteristics is proposed. First, the prepared aged oil samples were subjected to ultrasonic testing. Then, the Pearson correlation coefficient method was used to screen 8 ultrasonic features that were strongly correlated with the aging of oilpaper insulation. Finally, a transformer aging diagnostic model is established based on the above features and combined with radial basis function neural network. The results show that the diagnostic accuracy of the model proposed in this paper exceeds 90%. The method proposed in this paper has the potential of on-line evaluation of aging state of transformer.