Accurate Sensing of Power Transformer Faults From Dissolved Gas Data Using Random Forest Classifier Aided by Data Clustering Method

In this paper, a novel approach for accurate sensing of incipient faults occurring in power transformers is proposed using dissolved gas analysis (DGA) technique. The Duval pentagon method is a popular technique often used to interpret faults occurring in a power transformer based on DGA data. However, one potential limitation of conventional Duval pentagon method is the presence of rigid fault boundaries within the pentagon which often lead to misinterpretations, leading to poor detection accuracy. Considering this issue, in this paper a modification of Duval pentagon method is proposed, where instead of using rigidly separated distinct fault zones, a density-based clustering (DBSCAN) approach is used to increase the resiliency and the accuracy of fault detection technique. At first, DBSCAN is used to form different fault clusters within the Duval pentagon. Following this, the centroid corresponding to each fault cluster within the Duval pentagon is determined. For accurate sensing of incipient transformer faults Euclidean distances between the respective centroids and the fault points of the input DGA data are proposed as new distinguishing features in this work. The proposed distance parameters combined with the relative gas concentration measures are finally served as input features to the random forest (RF) classifier, which returned very high classification accuracy. The performance of the RF classifier is also compared with three benchmark machine classifiers, all of which delivered acceptable results. The proposed method can be used for sensing of power transformer faults using Duval pentagon method with increased accuracy.