Abstract
The ability to monitor and detect potential faults in smart grid system components is extremely valuable. In this paper, we demonstrate the use of machine learning techniques for condition monitoring in power transformers. Our objective is to classify the three different types of Partial Discharge (PD), the identify of which is highly correlated with insulation failure. Measurements from Acoustic Emission (AE) sensors are used as input data. Two broad machine learning based approaches are considered - the conventional method which uses a predefined feature set (Fourier based), and deep learning where features are learned automatically from the data. The performance of deep learning compares very favorably to the traditional approach, which includes ensemble learning and support vector machines, while eliminating the need for explicit feature extraction from the input AE signals. The results are particularly encouraging as manual feature extraction is a subjective process that may require significant redesign when confronted with new operating conditions and data types. In contrast, the ability to automatically learn feature sets from the raw input data (AE signals) promises better generalization with minimal human intervention.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Harbaji, M., El-Hag, A., Shaban, K.: Accurate partial discharge classification from acoustic emission signals. In: 2013 3rd International Conference on Electric Power and Energy Conversion Systems (EPECS), pp. 1–4. IEEE (2013)
Brown, M.H., Sedano, R.P.: Electricity transmission: a primer. Natl Conference of State (2004)
Kuo, C.C., Shieh, H.L.: Artificial classification system of aging period based on insulation status of transformers. In: 2009 International Conference on Machine Learning and Cybernetics, vol. 6, pp. 3310–3315. IEEE (2009)
Sikorski, W., Ziomek, W.: Detection, recognition and location of partial discharge sources using acoustic emission method. Acoustic Emission, pp. 49–74 (2012)
Woon, W.L., El-Hag, A., Harbaji, M.: Machine learning techniques for robust classification of partial discharges in oil-paper insulation systems. IET Sci. Measur. Technol. 10(3), 221–227 (2016)
Swedan, A., El-Hag, A., Assaleh, K.: Acoustic detection of partial discharge using signal processing and pattern recognition techniques. Insight-Non-Destr. Test. Cond. Monit. 54(12), 667–672 (2012)
Boczar, T., Borucki, S., Cichon, A., Zmarzly, D.: Application possibilities of artificial neural networks for recognizing partial discharges measured by the acoustic emission method. IEEE Trans. Dielectr. Electr. Insul. 16(1), 214–223 (2009)
Harbaji, M., Shaban, K., El-Hag, A.: Classification of common partial discharge types in oil-paper insulation system using acoustic signals. IEEE Trans. Dielectr. Electr. Insul. 22(3), 1674–1683 (2015)
Hand, D.J., Mannila, H., Smyth, P.: Principles of Data Mining. MIT press (2001)
Hastie, T., Tibshirani, R., Friedman, J., Hastie, T., Friedman, J., Tibshirani, R.: The Elements of Statistical Learning, vol. 2. Springer, New York (2009). https://doi.org/10.1007/978-0-387-84858-7
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Woon, W.L., Aung, Z., El-Hag, A. (2018). Intelligent Monitoring of Transformer Insulation Using Convolutional Neural Networks. In: Woon, W., Aung, Z., Catalina Feliú, A., Madnick, S. (eds) Data Analytics for Renewable Energy Integration. Technologies, Systems and Society. DARE 2018. Lecture Notes in Computer Science(), vol 11325. Springer, Cham. https://doi.org/10.1007/978-3-030-04303-2_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-04303-2_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04302-5
Online ISBN: 978-3-030-04303-2
eBook Packages: Computer ScienceComputer Science (R0)