An approach based on wavelets and machine learning to build a prediction model for SF6 filling pressure of high-voltage circuit breakers

Abstract

This paper presents the development of a filling pressure prediction model for sulfur hexafluoride (SF6) insulated high-voltage circuit breakers (HVCBs) for predictive maintenance, using actual data from existing HVCBs in operation and machine learning techniques. It is the result of a research project developed with a power transmission utility in Latin America to improve the maintenance procedures while reducing the environmental impact of SF6 leakages. Firstly, the authors use principal component analysis (PCA), neighborhood component analysis (NCA), and Pearson correlation (PC) to indicate the relationship of filling pressure with eleven variables, all collected from fifty HVCBs in use. Secondly, the authors employ discrete wavelet transform (DWT) Daubechies (db), symlets (sym), and coiflets (coif) on the essential variables to create smoothed signals with them. Finally, the authors apply long short-term memory (LSTM), multilayer perceptron (MLP) and extreme technical gradient boosting (XGBoost) algorithms to predict two days and one month of filling pressure and compare the results to the actual filling pressure data. The results indicate that selecting the most relevant variables and setting accordingly the wavelets generate high precision prediction models reaching low mean absolute percentage error (MAPE). The paper also proposes a mathematical approach to building efficient prediction models, which researchers can use in other predictive maintenance applications.