Transformer oil serves as a critical insulating medium within electrical transformers, with breakdown voltage acting as a crucial indicator to assess both the quality of the oil and its insulation characteristics. In this study, 175 groups of transformer oil samples were selected for experimentation. Breakdown voltage was measured, and signals were subsequently collected following the propagation of multi-frequency ultrasonic signals through the oil samples. The study examines the relationship between the amplitude-frequency response, phase-frequency response of multi-frequency ultrasonic acoustic parameters, and breakdown voltage in transformer oil samples. A prediction model for oil sample breakdown voltage was established using the grey wolf optimization algorithm to optimize the random forest algorithm (GWO-RF), with ultrasonic parameters as inputs and transformer oil breakdown voltage as the output. The original 175 datasets were divided into 140 training sets, 20 validation sets, and 15 test sets. The predictive model achieved an average percentage error of 4.04% and a prediction accuracy of 95.96% on the test set, surpassing the performance of the established random forest algorithm (RF) and the sparrow search algorithm optimized random forest algorithm (SSA-RF) for predicting breakdown voltage.
Read full abstract