Failure Rate Prediction of a Power Transformer: A Decomposition-Based Bayesian Deep Learning Method

Power transformers, as essential equipment for electricity transmission, may fail due to insulation degradation. Predicting the failure rate of power transformers precisely is beneficial to decision-making. Currently, uncertainties of the prediction have not been deeply discussed. Besides, prediction accuracy is not high enough. This paper proposes a decomposition-based Bayesian deep learning (BDL) method to predict the failure rate of power transformers. Both the model uncertainty related to distribution of the model's weights and the inherent uncertainty associated with random noise can be captured by BDL. Uncertainties of prediction results are depicted with confidence intervals. Moreover, prediction accuracy is improved using variational mode decomposition (VMD). Numerical experiments have been carried out based on oil chromatographic data of power transformers from the Chongqing grid to validate effectiveness of the proposed method.