Power Transformer Fault Diagnosis with Intrinsic Time-scale Decomposition and XGBoost Classifier

An intrinsic time-scale decomposition (ITD)-based method for power transformer fault diagnosis is proposed. Dissolved gas analysis (DGA)parameters are ranked according to their skewness, and then ITD based features extraction is performed. An optimal set of PRC features are determined by an XGBoost classifier. For classification purpose, an XGBoost classifier is used to the optimal PRC features set. The proposed method’s performance in classification is studied using publicly available DGA data of 376 power transformers and employing an XGBoost classifier. TheProposed method achieves more than 95% accuracy and high sensitivity and F1-score, better than conventional methods and some recent machine learning-based fault diagnosis approaches. Moreover, it gives better Cohen Kappa and F1-score as compared to the recently introduced EMD-based hierarchical technique for fault diagnosis in power transformers.

[2]  Sherif S. M. Ghoneim,et al.  A new approach of DGA interpretation technique for transformer fault diagnosis , 2016 .

[3]  Jing Jiang,et al.  A novel multi-module neural network system for imbalanced heartbeats classification , 2019, Expert Syst. Appl. X.

[4]  Aamir Saeed Malik,et al.  Comparison of EEG signal decomposition methods in classification of motor-imagery BCI , 2018, Multimedia Tools and Applications.

[5]  Khmais Bacha,et al.  Power transformer fault diagnosis based on dissolved gas analysis by support vector machine , 2012 .

[6]  Alexander Voznesensky,et al.  Adaptive Signal Processing Algorithms Based on EMD and ITD , 2019, IEEE Access.

[7]  Huanyu Dong,et al.  BA-PNN-based methods for power transformer fault diagnosis , 2019, Adv. Eng. Informatics.

[8]  I. Osorio,et al.  Intrinsic time-scale decomposition: time–frequency–energy analysis and real-time filtering of non-stationary signals , 2007, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[9]  M. Duval,et al.  Improving the reliability of transformer gas-in-oil diagnosis , 2005, IEEE Electrical Insulation Magazine.

[10]  Mohammad Pazoki,et al.  A New DC-Offset Removal Method for Distance-Relaying Application Using Intrinsic Time-Scale Decomposition , 2018, IEEE Transactions on Power Delivery.

[11]  Jie Chen,et al.  Application of the intrinsic time-scale decomposition method to fault diagnosis of wind turbine bearing , 2012 .

[12]  Jawad Faiz,et al.  Dissolved gas analysis evaluation in electric power transformers using conventional methods a review , 2017, IEEE Transactions on Dielectrics and Electrical Insulation.

[13]  Atiek Iriany,et al.  Cross-validation Metrics for Evaluating Classification Performance on Imbalanced Data , 2019, 2019 International Conference on Computer, Control, Informatics and its Applications (IC3INA).

[14]  Dongbo Zhao,et al.  Hybrid feature selection approach for power transformer fault diagnosis based on support vector machine and genetic algorithm , 2018, IET Generation, Transmission & Distribution.

[15]  Michel Duval,et al.  Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases , 2001 .

[16]  M. Weedon,et al.  Sleep classification from wrist-worn accelerometer data using random forests , 2021, Scientific reports.

[17]  Jian Wang,et al.  A forecasting method for metering error of electric energy based on intrinsic time-scale decomposition and time series analysis , 2016, 2016 IEEE Innovative Smart Grid Technologies - Asia (ISGT-Asia).