Development of a decision support system for assessing the technical condition of power transformers

Reliable and environmentally sound operation of power transformers is a crucial aspect of modern electrical energy systems. The objective of this study is to develop a decision support system that enables a comprehensive assessment of the technical condition of power transformers. We utilized a combination of chromatographic analysis, machine learning techniques, and regression models, including AutoML and ensemble models, to objectively evaluate the remaining lifespan of transformers. The methodology involved gathering data on various individual parameters affecting transformer operations and developing a model to mitigate human factor impacts during expert evaluations. Our results demonstrate that the implementation of the proposed model supports a risk-oriented maintenance approach, thereby reducing operational costs and minimizing the risk of electrical equipment failure. The study was facilitated by a grant from Industrial University of Tyumen, emphasizing the significance of reliable transformer operation in energy systems. The findings contribute to the understanding of transformer maintenance strategies and offer a framework for decision support in assessing transformer conditions. This research ultimately aims at enhancing the reliability and sustainability of power transformer operations.