Aging Stage Diagnosis of Oil-Paper Insulation Equipment Using Raman Spectrum Based on Multiple screening KNN Algorithms

Rapid identification of aging state of oil-paper insulation is of great significance to the operation safety of power transformers. Raman spectroscopy can rapidly analyze the aging characteristic information dissolved in oil, and it is an effective means for the aging diagnosis of oil-paper insulation. In this paper, Multiple screening KNN Algorithms for Raman spectroscopy analysis of aging oil-paper insulation samples is presented. A large number of aging oil samples were obtained by accelerated thermal aging test. According to the aging days, the samples were divided into 12 categories, and 230 Raman spectra were obtained by Raman spectroscopy. The KNN algorithm is used for classification and regression of Raman Spectra of test samples by Pearson correlation coefficient. Then, based on the traditional KNN algorithm, a multi-screening KNN is proposed according to the actual situation of the aging process of insulating oil Raman spectrum. The prediction of Multiple screening KNN Algorithms accuracy of classification reaches 87.92%, and the RMSE of regression reached 54.28.