A New Model for Predicting the Remaining Lifetime of Transformer Based on Data Obtained Using Machine Learning

Transformers are one of the most important parts of the electric transmission and distribution networks, and their performance directly affects the reliability and stability of the grid. Maintenance and replacing the faulted transformers could be time-consuming and costly and accordingly, a solution should be proposed to prevent it. This led to studies in the field of transformer lifetime management. As a result, estimating the remaining lifetime of the transformer is a crucial part for the mentioned solution. Therefore, this paper aims to tackle this issue through employing a new algorithm to estimate the lifetime of a transformer by combining selection methods and Artificial Intelligence (AI)-based techniques. The main goal of this method is to reduce the estimation error and estimation time simultaneously. The proposed approach assesses transformers based on environmental conditions, power quality, oil quality, and dissolved gas analysis (DGA). Consideration of additional factors overcomes the disadvantage of traditional methods and gives a meticulous result. In this respect, the collected data from the power transformer of Iran and Iraq as well as regions with different conditions are employed in the studied algorithm. Several combinations of algorithms are investigated to choose the best one. Principal Component Analysis (PCA) is employed in the next step for weighing the various parameters to improve the accuracy and decrease execution time. Results show that the Bayesian neural network provides the best performance in the predicting remaining lifetime of the transformer with an accuracy about 98.4%.