An EMD-based Method for the Detection of Power Transformer Faults with a Hierarchical Ensemble Classifier

  title={An EMD-based Method for the Detection of Power Transformer Faults with a Hierarchical Ensemble Classifier},
  author={Shoaib Meraj Sami and Mohammed Imamul Hassan Bhuiyan},
  journal={2020 11th International Conference on Electrical and Computer Engineering (ICECE)},
  • S. Sami, M. Bhuiyan
  • Published 17 December 2020
  • Computer Science, Engineering, Mathematics
  • 2020 11th International Conference on Electrical and Computer Engineering (ICECE)
In this paper, an Empirical Mode Decomposition-based method is proposed for the detection of transformer faults from Dissolve gas analysis (DGA) data. Ratio-based DGA parameters are ranked using their skewness. Optimal sets of intrinsic mode function coefficients are obtained from the ranked DGA parameters. A Hierarchical classification scheme employing XGBoost is presented for classifying the features to identify six different categories of transformer faults. Performance of the Proposed… 
1 Citations

Figures and Tables from this paper

Power Transformer Fault Diagnosis with Intrinsic Time-scale Decomposition and XGBoost Classifier
  • S. Sami, M. Bhuiyan
  • Computer Science, Engineering
    Lecture Notes on Data Engineering and Communications Technologies
  • 2021
The proposed intrinsic time-scale decomposition (ITD)-based method for power transformer fault diagnosis achieves more than 95% accuracy and high sensitivity and F1-score, better than conventional methods and some recent machine learning-based fault diagnosis approaches.


Feature selection in power transformer fault diagnosis based on dissolved gas analysis
Various techniques of feature selection are used, including Student's t-test, Kolmogorov-Smirnov test and Kullback Leibler Divergence test, to rank features' order based on discriminative power of different features.
BA-PNN-based methods for power transformer fault diagnosis
A machine learning-based approach to power transformer fault diagnosis based on dissolved gas analysis (DGA), a bat algorithm (BA), optimizing the probabilistic neural network (PNN), demonstrating that BA is an effective algorithm for optimizing PNN smooth factor and BA-PNN can improve the fault diagnosis performance.
Fault classification in power systems using EMD and SVM
Abstract In recent years, power quality has become the main concern in power system engineering. Classification of power system faults is the first stage for improving power quality and ensuring the
A nearest neighbour clustering approach for incipient fault diagnosis of power transformers
Dissolved gas analysis (DGA) is one of the popular and widely accepted methods for fault diagnosis in power transformers. This paper presents a novel DGA technique to improve the diagnosis accuracy
Transformer Fault Diagnosis Based on Naive Bayesian Classifier and SVR
Because traditional transformer diagnosing approaches are over-rigidity and need almost complete and accurate testing data, a NB (Naive Bayesian) classifier based model to diagnose transformer faults
Transformer Fault Diagnosis Model Based on Iterative Nearest Neighbor Interpolation and Ensemble Learning
A missing value imputation method by iterative k nearest neighbor (KNN), and ensemble learning is used to diagnose the power transformer to improve the accuracy of fault diagnosis of power transformer in the presence of missing values.
Transformer fault diagnosis method using IoT based monitoring system and ensemble machine learning
The proposed EML can usefully remedy the inadequate information of features extracted by individual deep learning method, and its RVM classifier is obviously better than other commonly used classifiers.
A new approach of DGA interpretation technique for transformer fault diagnosis
Abstract Dissolved Gas Analysis (DGA) is one of the most common techniques to detect the incipient faults in the oil-filled power transformers. In this paper, a new approach of DGA technique is
Hybrid feature selection approach for power transformer fault diagnosis based on support vector machine and genetic algorithm
Results indicate that the optimal feature subset obtained by the proposed method can significantly improve the accuracies of power transformer fault diagnosis.
Dissolved gas analysis evaluation in electric power transformers using conventional methods a review
Transformers are the most important equipment in power systems, and their failure can cause serious problems. In order to avoid hazardous operating conditions and reduce outage rates, fault detection