An Efficient Method to Localize and Quantify Axial Displacement in Transformer Winding Using Support Vector Machines

In power systems, power transformers are critical components that play a key role in delivering electricity to consumers. However, transformers are also vulnerable to various faults, such as winding faults, insulation failures, and internal short circuits, which can cause significant disruptions and lead to costly downtime. It is needless to emphasize that the early detection of mechanical faults in the transformer winding is inevitable for its continuous operation. Among the different condition monitoring and diagnostic techniques, Frequency Response Analysis(FRA) has the potential to detect even incipient mechanical displacements/deformations. In the present analysis, support vector Machine (SVM), a supervised machine learning technique is used to locate and quantify the axial displacement with the help of features extracted from the FRA traces of the transformers. In the training phase, a series of axial displacements is simulated in finite element software, and corresponding equivalent circuit parameters are used to generate FRA traces. Furthermore, features are extracted from these FRA traces to train the SVM model to enable it to predict the location and quantity of axial displacement accurately. Finally, the accuracy of this SVM model is tested through randomly created axial displacement data on a practical 3.3 MVA transformer winding. The result indicates the ability of this technique to be used as an intelligent and accurate diagnostic to locate and quantify axial displacements in the transformer winding.