Accuracy Improvement of Data-Driven Algorithms in Power Transformer Assessment Using Hyperparameter Optimization on DGA Data
Subject Areas : International Journal of Smart Electrical Engineering
1 -
Keywords: Optimization, Power Transformer, Decision Tree, Machine Learning, Fault Diagnosis,
Abstract :
Transformers are critical components in power systems. Faults within these devices can lead to substantial repair costs and prolonged service interruptions. Dissolved Gas Analysis (DGA) of transformer oil is widely used for monitoring transformer health. This research leverages data-driven algorithms, employing the Duval-Pentagon (DP) method and hyperparameter optimization, to enhance fault diagnosis accuracy in power transformers. After preprocessing the DGA dataset, it was split into training and testing sets in an 80:20 ratio. Subsequently, several data-driven algorithms, including Support Vector Machines Algorithm (SVMA), Decision Trees Algorithm (DTA), Logistic Regression Algorithm (LRA), and Naive Bayes Algorithm (NBA), were employed on the dataset. To further improve fault diagnosis accuracy, a hyperparameter optimization technique was implemented by leveraging random search. Evaluation metrics such as accuracy, F1-measure, recall, precision, and Matthews Correlation Coefficient (MCC) were used to assess impact of hyperparameter optimization. The findings demonstrate that hyperparameter optimization consistently enhances the performance of data-driven algorithms. Among the algorithms proposed in this research, DTA with hyperparameter optimization achieved the highest accuracy with an accuracy rate of 93.37% in transformer fault diagnosis. The algorithms were implemented based on Python.
[1] X. Zheng, “Intelligent Fault Diagnosis of Power Transformer base on Fuzzy Logic and Rough Set Theory,” 7th World Congress on Intelligent Control and Automation, pp. 6858 - 6862, 2008.
[2] E. Moradi, “A Data-Driven based Robust Multilayer Perceptron Approach for Fault Diagnosis of Power Transformers,” 20th CSI International Symposium on Artificial Intelligence and Signal Processing (AISP), Feb. 2024.
[3] M. M. Islam, G. Lee, and S. N. Hettiwatte, “Application of a general regression neural network for health index calculation of power transformers,” International Journal of Electrical Power & Energy Systems, vol. 93, pp. 308–315, 2017.
[4] D.-E. A. Mansour, “Development of a new graphical technique for dissolved gas analysis in power transformers based on the five combustible gases,” IEEE Transactions on Dielectrics and Electrical Insulation, vol. 22, no. 5, 2015.
[5] Y. Benmahamed, M. Teguar, and A. Boubakeur, “Application of SVM and KNN to Duval Pentagon 1 for transformer oil diagnosis,” IEEE Transactions on Dielectrics and Electrical Insulation, vol. 24, no. 6, 2017.
[6] A.-M. Aciu, S. Enache, and M.-C. Nițu, “A Reviewed Turn at of Methods for Determining the Type of Fault in Power Transformers Based on Dissolved Gas Analysis,” Energies, vol. 17, no. 10, May 2024.
[7] R. Soni and B. Mehta, “Diagnosis and prognosis of incipient faults and insulation status for asset management of power transformer using fuzzy logic controller & fuzzy clustering means,” Electric Power Systems Research, vol. 220, 2023.
[8] M. S. Ali, A. H. A. Bakar, A. Omar, A. S. A. Jaafar, and S. H. Mohamed, “Conventional methods of dissolved gas analysis using oil-immersed power transformer for fault diagnosis: A review,” Electric Power Systems Research, vol. 216, 2023.
[9] Y. Jin, H. Wu, J. Zheng, J. Zhang, and Z. Liu, “Power Transformer Fault Diagnosis Based on Improved BP Neural Network,” Electronics, vol. 12, no. 16, 2023.
[10] Y. Zhang, Y. Tang, Y. Liu, and Z. Liang, “Fault diagnosis of transformer using artificial intelligence: A review,” Frontiers in Energy Research, vol. 10, 2022.
[11] S. A. Gamel, S. S. M. Ghoneim, and Y. A. Sultan, “Improving the accuracy of diagnostic predictions for power transformers by employing a hybrid approach combining SMOTE and DNN,” Computers & Electrical Engineering, vol. 117, 2024.
[12] L. Wang, T. Littler, and X. Liu, “Hybrid AI model for power transformer assessment using imbalanced DGA datasets,” IET Renewable Power Generation, vol. 17, no. 8, 2023.
[13] A. Kirkbas, A. Demircali, S. Koroglu, and A. Kizilkaya, “Fault diagnosis of oil-immersed power transformers using common vector approach,” Electric Power Systems Research, vol. 184, 2020.
[14] D. Zou et al., “Transformer fault classification for diagnosis based on DGA and deep belief network,” Energy Reports, vol. 9, pp. 250–256, 2023.
[15] N. Poonnoy, C. Suwanasri, and T. Suwanasri, “Fuzzy Logic Approach to Dissolved Gas Analysis for Power Transformer Failure Index and Fault Identification,” Energies, vol. 14, no. 1, 2020.
[16] I. B. M. Taha, S. Ibrahim, and D.-E. A. Mansour, “Power Transformer Fault Diagnosis Based on DGA Using a Convolutional Neural Network With Noise in Measurements,” IEEE Access, vol. 9, 2021.
[17] S. S. M. Ghoneim and I. B. M. Taha, “A new approach of DGA interpretation technique for transformer fault diagnosis,” International Journal of Electrical Power & Energy Systems, vol. 81, pp. 265–274, Oct. 2016.
[18] V. N. G. Raju, K. P. Lakshmi, V. M. Jain, A. Kalidindi, and V. Padma, “Study the Influence of Normalization/Transformation Process on the Accuracy of Supervised Classification,” 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT), Aug. 2020.
[19] K. Bacha, S. Souahlia, and M. Gossa, “Power transformer fault diagnosis based on dissolved gas analysis by support vector machine,” Electric Power Systems Research, vol. 83, no. 1, pp. 73–79, 2012.
[20] Y. Y. Song, and Y. Lu, “Decision tree methods: applications for classification and prediction”, Shanghai Archives of Psychiatry, vol. 27, no. 2, 2015.
[21] Y. D. Almoallem, I. B. M. Taha, M. I. Mosaad, L. Nahma, and A. Abu-Siada, “Application of Logistic Regression Algorithm in the Interpretation of Dissolved Gas Analysis for Power Transformers,” Electronics, vol. 10, no. 10, 2021.
[22] M. Demirci, H. Gözde, and M. C. Taplamacioglu, “Improvement of power transformer fault diagnosis by using sequential Kalman filter sensor fusion,” International Journal of Electrical Power & Energy Systems, vol. 149, 2023.
[23] A. A. Yaghoubi, P. Karimi, E. Moradi, and R. Gavagsaz-Ghoachani, “Implementing Engineering Education Based on Posing a Riddle in Field of Instrumentation and Artificial Intelligence,” 9th International Conference on Control, Instrumentation and Automation (ICCIA), Dec. 2023.
