Classification of Cellulosic Insulation State Based on Smart Life Prediction Approach (SLPA)

The state of cellulosic solid kraft paper (CSKP) insulation, to a large extent, is an indication transformer’s health. It not only reflects the condition transformer but also diagnose its residual life. quantity 2-furfuraldehyde (2-FAL), carbon dioxide (CO2), and monoxide (CO) dissolved in oil are useful diagnostic indicators predict CSKP insulation. In this work, current physical determined with help easily measurable parameters, like temperature, moisture, aging time. Here, degree deterioration insulation has been using integrated health assessment system. This technique integrates two-stage system comprising neural network (NN) model followed by Smart Life Prediction Approach (SLPA). A thermo-moisture-aging multi-layer feed-forward NN developed concentrations 2-FAL, CO2, CO, which further correlated estimate Degree Polymerization (DP) values adopting SLPA. advantage proposed that it provides alternative means based on Dissolved Gas Analysis (DGA) without estimating gas oil, thereby avoiding use sophisticated measuring instruments. optimal configuration achieved at minimum iterations average cross-validation mean square error 3.78 × 10−7. avoids destructive offline measurement DP facilitates real-time monitoring oil-immersed transformers. test results show considerable reliability determining parameters. Furthermore, system’s performance compared reported work found provide encouraging outcomes.