Assessment of Power Transformer Paper Ageing Using Wavelet Texture Analysis of Microscopy Images

Abstract

This paper presents a wavelet texture analysis of microscopy images acquired from artificially-aged samples of power transformer winding insulation paper. Oil-impregnated Kraft paper samples are prepared for experimental tests where they are thermally stressed in an oven at temperatures above what would normally occur in operation. This accelerated ageing test arrangement is used to produce a set of paper samples with varying levels of insulation deterioration. From the paper samples, microscopy images of the paper surface are obtained using a standard optical microscope. These microscopic images are analyzed using a texture analysis method that utilizes a two-dimensional wavelet transform to extract detailed information from the wavelet decomposition coefficient matrices. These features are analyzed to assess how the texture of paper changes in response to thermal deterioration and ageing. The results suggest that the texture features are correlated to the commonly-used degree of polymerization test. Additionally, statistical classification is performed on the wavelet texture features using both supervised and unsupervised machine learning methods. The results demonstrate that differentiation between oil-impregnated paper samples with different levels of thermal degradation using wavelet texture analysis is effective.