International Journal of Applied Science and Engineering
Published by Chaoyang University of Technology

Kristoko Dwi Hartomo 1, Yessica Nataliani 1*, Denny Indrajaya 2, Nur Haliza Abdul Wahab 3, Untung Rahardja 4, Christine Dewi 5

1 Department of Information System, Faculty of Information Technology, Satya Wacana Christian University, Salatiga, Indonesia

2 Master of Data Science, Faculty of Science and Mathematics, Satya Wacana Christian University, Salatiga, Indonesia

3 Faculty of Computing, Universiti Teknologi Malaysia, Johor, Malaysia

4 Faculty of Economics and Business, University of Raharja, Tangerang, Indonesia

5 Department of Informatics, Faculty of Information Technology, Satya Wacana Christian University, Salatiga, Indonesia


 

Download Citation: |
Download PDF


ABSTRACT


A transformer is a device used for electricity-related purposes, one of which is to distribute electricity from a supplier, in this case the State Electricity Company (PLN), to customers or the community. Considering the transformer’s essential role, it is crucial to conduct research to minimize damage to this device, which can be caused by a variety of factors, where gas and electrical conditions of the transformer, among other things, can be used as indicators of damage. Therefore, this study focused on creating models using Artificial Neural Network (ANN) algorithms to assess transformer conditions based on data obtained from transformers. In this study, correlation analysis was used to determine six features that served as leading indicators in evaluating the condition of the transformer. The six features were dibenzyl disulfide (DBDS), interfacial voltage, hydrogen, methane, ethylene, and water content. In modelling and testing, 80% of the data was distributed for the training dataset and 20% was for the testing dataset, with a total of 470 data points. This study also applied the Synthetic Minority Oversampling Technique-Rechecked, Reused, and Edited (SMOTE-R2E) method, which is an improvement of the SMOTE method. SMOTE-R2E is proposed in this study to overcome the limitations of unbalanced transformer data. In this study, model training was carried out using three approaches, i.e., model training using a training dataset obtained without the SMOTE method, model training using a training dataset obtained with the SMOTE method, and model training using a training dataset obtained with the SMOTE-R2E method. Each training approach was performed 100 times. Based on model testing on the testing dataset, the best model was the model obtained by applying the SMOTE-R2E method, with average accuracy and F1-score obtained from 100 iterations of 83.04% and 81.96%, respectively.


Keywords: Artificial Neural Network, SMOTE, SMOTE-R2E, Transformer


Share this article with your colleagues

 


REFERENCES


  1. Abdullah, A.M., Ali, R., Yaacob, S.B., Mansur, T., Baharudin, N.H. 2021. Prediction of transformer health index using condition situation monitoring (csm) diagnostic techniques. Journal of Physics: Conference Series, 1878(1), 1–9.

  2. Almajid, A.S. 2022. Multilayer perceptron optimization on imbalanced data using svm-smote and one-hot encoding for credit card default prediction. Journal of Advances in Information Systems and Technology, 3(2), 67–74.

  3. Alqudsi, A., El-Hag, A. 2019. Application of machine learning in transformer health index prediction. Energies, 12(14), 1–13.

  4. Bingham, G., Miikkulainen, R. 2021. AutoInit: analytic signal-preserving weight initialization for Neural Networks. The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI-23), 6823–6833.

  5. Bohatyrewicz, P., Banaszak, S. 2022. Assessment criteria of changes in health index values over time—A transformer population study. Energies, 15(16), 1–15.

  6. Bustamante, S., Manana, M., Arroyo, A., Castro, P., Laso, A., Martinez, R. 2019. Dissolved gas analysis equipment for online monitoring of transformer oil: A review. Sensors, 19(19), 4057.

  7. Das, S., Adhikary, A., Laghari, A.A., Mitra, S. 2023. Eldo-care: EEG with kinect sensor based telehealthcare for the disabled and the elderly. Neuroscience Informatics, 3(2), 1–6.

  8. El-Harbawi, M. 2022. Fire and explosion risks and consequences in electrical substations—a transformer case study. ASME Open Journal of Engineering, 1, 1–27.

  9. Gorunescu, F. 2011. Data Mining Concepts, Models and Techniques. Springer-Verlag Berlin Heidelberg. New York. USA.

  10. Hernanda, I.G.N.S., Mulyana, A.C., Asfani, D.A., Negara, I. M.Y., Fahmi, D. 2014. Application of health index method for transformer condition assessment. TENCON 2014 - 2014 IEEE Region 10 Conference.

  11. Ho, Y., Wookey, S. 2020. The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabeling. IEEE Access, 8, 4806–4813.

  12. Hoole, P.R.P., Anak, S., Izzati, N., Hafiez, M. 2017. Power transformer fire and explosion : causes and control. International Journal of Control Theory and Applications, 10(16), 211–220.

  13. Indrajaya, D., Setiawan, A., Susanto, B. 2022. Comparison of k-Nearest Neighbor and Naive Bayes Methods for SNP Data Classification. Matrik: Jurnal Manajemen, Teknik Informatika, Dan Rekayasa Komputer, 22(1), 149–164.

  14. Jais, I.K.M., Ismail, A.R., Nisa, S.Q. 2019. Adam optimization algorithm for wide and deep neural network. Knowledge Engineering and Data Science, 2(1), 41–46.

  15. Jamal, P., Ali, M., Faraj, R.H., Ali, P.J.M., Faraj, R.H. 2014. Data normalization and standardization: A Technical Report. Machine Learning Technical Reports, 1(1), 1–6.

  16. Laghari, A.A., Estrela, V.V., Li, H., Shoulin, Y., Khan, A.A., Anwar, M.S., Wahab, A., Bouraqia, K. 2024. Quality of experience assessment in virtual/augmented reality serious games for healthcare: A systematic literature review. Technology and Disability, Pre-press, 1–12.

  17. Laghari, A.A., Estrela, V.V, Yin, S. 2024. How to collect and interpret medical pictures captured in highly challenging environments that range from nanoscale to hyperspectral imaging. Current Medical Imaging, 20, 1–10.

  18. Laghari, A.A., Shahid, S., Yadav, R., Karim, S., Khan, A., Li, H., Shoulin, Y. 2023. The state of art and review on video streaming. Journal of High Speed Networks, 29(3), 211–236.

  19. Laghari, A.A., Sun, Y., Alhussein, M., Aurangzeb, K., Anwar, M.S., Rashid, M. 2023. Deep residual-dense network based on bidirectional recurrent neural network for atrial fibrillation detection. Scientific Reports, 13, 1–12.

  20. Liu, D., Chen, X., Guo, Z., Yuan, J., Yin, S. 2023. Research on the online parameter identification method of train driving dynamic model. International Journal of Computational Vision and Robotics, 13(5), 497–509.

  21. Lopo, J.A., Hartomo, K.D. 2023. Evaluating sampling techniques for healthcare insurance fraud detection in imbalanced dataset. JITEKI, 9(2), 223–238.

  22. Martinez-Gil, J., Buchgeher, G., Gabauer, D., Freudenthaler, B., Filipiak, D., Fensel, A. 2022. Root cause analysis in the industrial domain using knowledge graphs: A Case study on power transformers. Procedia Computer Science, 200, 944–953.

  23. Muntasir Nishat, M., Faisal, F., Jahan Ratul, I., Al-Monsur, A., Ar-Rafi, A.M., Nasrullah, S.M., Reza, M.T., Khan, M. R.H. 2022. A Comprehensive Investigation of the Performances of Different Machine Learning Classifiers with SMOTE-ENN Oversampling Technique and Hyperparameter Optimization for Imbalanced Heart Failure Dataset. Scientific Programming, 2022 (Cvd).

  24. Nanfak, A., Eke, S., Kom, C.H., Mouangue, R., Fofana, I. 2021. Interpreting dissolved gases in transformer oil: A new method based on the analysis of labelled fault data. IET Generation, Transmission and Distribution, 15(21), 3032–3047.

  25. Pribadi, M.R., Purnomo, H.D., Hendry, Hartomo, K. D., Sembiring, I., Iriani, A. 2022. Improving the accuracy of text classification using the over sampling technique in the case of Sinovac Vaccine. 2022 9th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI).

  26. Saeed, U., Kumar, K., Khuhro, M.A., Laghari, A.A., Shaikh, A.A., and Rai, A. 2024. DeepLeukNet—A CNN based microscopy adaptation model for acute lymphoblastic leukemia classification. Multimedia Tools and Applications, 83, 21019–21043.

  27. Sasada, T., Liu, Z., Baba, T., Hatano, K., Kimura, Y. 2020. A resampling method for imbalanced datasets considering noise and overlap. Procedia Computer Science, 176, 420–429.

  28. Schober, P., Schwarte, L.A. 2018. Correlation coefficients: appropriate use and interpretation. Anesthesia and Analgesia, 126(5), 1763–1768.

  29. Sharma, S., Sharma, S., Athaiya, A. 2020. Activation Functions in Neural Networks. International Journal of Engineering Applied Sciences and Technology, 4(12), 310–316.

  30. Stangierski, J., Weiss, D., Kaczmarek, A. 2019. Multiple regression models and Artificial Neural Network (ANN) as prediction tools of changes in overall quality during the storage of spreadable processed gouda cheese. European Food Research and Technology, 245, 2539–2547.

  31. Syahfitra, F.D., Syahputra, R., Putra, K.T. 2017. Implementation of backpropagation Artificial Neural Network as a forecasting system of power transformer peak load at bumiayu substation. Journal of Electrical Technology, 1(3), 118–125.

  32. Velásquez, R.M.A., Lara, J.V.M. 2020. Data for: root cause analysis improved with machine learning for failure analysis in power transformers. Engineering Failure Analysis, 115, 104684.

  33. Wang, C.I., Joanito, I., Lan, C.F., Hsu, C.P. 2020. Artificial neural networks for predicting charge transfer coupling. Journal of Chemical Physics, 153(21), 1–15.

  34. Wang, J., Fan, Y., Li, H., Yin, S. 2023. WeChat mini program for wheat diseases recognition based on VGG-16 convolutional neural network. International Journal of Applied Science and Engineering, 20(3), 1–9.

  35. Yin, S., Li, H., Laghari, A. A., Gadekallu, T. R., Sampedro, G. A., Almadhor, A. 2024. An anomaly detection model based on deep auto-encoder and capsule graph convolution via Sparrow Search Algorithm in 6G internet-of-everything. IEEE Internet of Things Journal, Early Access.

  36. Zhengwei, G., Xinju, G., Xiangli, L., Min, T., Dong, L. 2018. Study on Decomposition gas explosion of transformer oil under Arc. 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2), 1–5.


ARTICLE INFORMATION


Received: 2024-04-06
Revised: 2024-05-14
Accepted: 2024-06-14
Available Online: 2024-11-21


Cite this article:

Hartomo, K.D., Nataliani, Y., Indrajaya, D., Abdul Wahab, N.H., Rahardja, U., Dewi, C. 2024. Improving the accuracy of an ANN model for transformer condition assessment using the SMOTE-R2E method. International Journal of Applied Science and Engineering, 21, 2024117. https://doi.org/10.6703/IJASE.202412_21(5).003

  Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.