Data Driven Predictive Maintenance of Distribution Transformers

This paper presents a method for the predictive maintenance of distribution transformers. That is, a method of predicting which transformers are most likely to fail soon. Once predicted, such transformers may be subject to maintenance or replacement. This practice reduces the costs and increases the reliability of power distribution systems. The practice is common in transmission systems. In that domain, physical methods such as dissolved gas analysis see fantastic results. Data-driven techniques utilizing DGA data are also popular. But such methods are cost prohibitive for distribution systems. Instead, this paper proposes to utilize a data driven framework for the task which only uses readily available data. Such data include the transformers' specification, loading, location, and weather-related information. Such data inspire the use of two suitable machine learning algorithms. The first is random forests. The second is the Random Undersampling with AdaBoost (RUSBoost) algorithm. These algorithms are tested on over 700,000 distribution transformers in Southern California. This test finds that both algorithms outperform the current state of practice. Further, it finds that the RUSBoost algorithm performs better than the Random Forest.