ASSESSMENT OF THE ELECTRICAL EQUIPMENT INSULATION STATE USING THE GRADIENT BOOSTING ALGORITHM

Yaroslav V. Mironenko, Alexey D. Kurzanov

DOI: 10.47026/1810-1909-2021-3-94-102

Key words

diagnostics of high-voltage equipment, partial discharges, machine learning, gradient boosting, CatBoost.

Abstract

The creation of analytical software products aimed at assessing the electrical equipment state has become a priority in the development of diagnostics in the power industry. The artificial intelligence methods are useful for this problem-solving. In the article, we propose a method for analyzing the monitoring data of partial discharges in the insulation of electrical equipment using machine-learning technologies. An analytical assessment of the partial discharges characteristics allows us to conclude on the insulation state of the object. It is proposed to use integrated diagnostic parameters, such as partial discharges intensity – the maximum measured value of the apparent charge of a single, repetitive and regular partial discharges. The total sample is characterized by an imbalance, which is typical for technical diagnostics in general. Among machine learning algorithms, bagging and boosting have proven to be the most effective. The mathematical apparatus of gradient boosting is considered in the example of the most common algorithms GBM (Gradient Boosting Machine) and CatBoost. The model was created in the Python programming language. The model created on the basis of the CatBoost algorithm was used for assessing the condition of the oil insulation of power transformers. The model’s accuracy of 68.85% was achieved after optimizing the parameters of the CatBoost algorithm. The article concluded that it is necessary to increase the training sample size and improve its balance. It is inadvisable to interpret the predicted data in the field of diagnostics parameters at the available accuracy of the model’s wok.

References

1. Ansamblevye metody: begging, busting i steking [Ensemble methods: bagging, boosting and stacking]. Available at: https://neurohive.io/ru/osnovy-data-science/ansamblevye-metody-begging-busting-i-steking/ (Access Date 2021, Aug. 13).
2. Vdoviko V.P. Chastichnye razryady v diagnostirovanii vysokovol’tnogo oborudovaniya [Partial discharges in diagnostics of high-voltage equipment]. Novosibirsk: Nauka, 2007, 155 p.
3. Klyachkin V.N., Kuvaiskova Yu.E., Zhukov D.A. Vybor metoda binarnoi klassifikatsii pri tekhnicheskoi diagnostike s primeneniem mashinnogo obucheniya [The choice of a binary classification method in technical diagnostics using machine learning]. Izvestiya Samarskogo nauchnogo tsentra Rossiiskoi akademii nauk, 2018, vol. 20, no. 4(3), pp. 494–497.
4. Malafeev S.I. Nadezhnost’ elektrosnabzheniya [Power supply reliability]. Petersburg: Lan Publ., 2017, 368 p.
5. Mironenko Ya.V. Perspektiva razvitiya tekhnologii diagnostiki vysokovol’tnogo elektroenergeticheskogo oborudovaniya [A Prospect for the development of diagnostic technologies for high-voltage electric power equipment]. In: Sovremennaya tekhnika i tekhnologii: problemy, sostoyanie i perspektivy: sb. dokl. X Vseros. nauchn. konf. [Proc. of 10^th Sci. Conf. «Modern equipment and technologies: problems, state and prospects»]. Rubtsovsk, 2020, pp. 130–136.
6. Opisanie vedomstvennogo proekta Ministerstva energetiki Rossiiskoi Federatsii «Tsifrovaya energetika» [Description of the departmental project of the Ministry of Energy of the Russian Federation “Digital Energy”]. Available at: https://digital.gov.ru/uploaded/files/vedomstvennyij-proekt-tsifrovaya-energetika.pdf (Access Date 2021, Aug. 13).
7. Rusov V.A. Diagnosticheskii monitoring vysokovol’tnykh silovykh transformatorov [Diagnostic monitoring of high voltage power transformers]. Perm, DIMRUS Publ., 2013, 159 p.
8. Esteva A., Kuprel B., Novoa R.A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature, 2017, no. 542, pp. 115–118.
9. Fenton W., McGinnity T., Maguire L. Fault diagnosis of electronic systems using intelligent techniques: a review. IEEE Transactions on Systems, Man, and Cybernetics, Part C, 2001, vol. 31, no. 3, pp. 269–281.
10. Gertler J., Costin M., Fang X., Kowalczuk Z. et al. Model based diagnosis for automotive engines-algorithm development and testing on a production vehicle. IEEE Transactions on Control Systems Technology, 1995, vol. 3, no. 1, pp. 61–69.
11. Gulshan V., Peng L., Coram M., Stumpe M.C. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 2016, no. 316(22), pp. 2402–2410.
12. Hosny A., Parmar C., Quackenbush J., Schwartz L.H., Aerts H.J. W.L. Artificial intelligence in radiology. Nat Rev Cancer, 2018, no. 18(8), pp. 500–510.
13. How Do You Know You Have Enough Training Data? Available at: https://towardsdatascience.com/how-do-you-know-you-have-enough-training-data-ad9b1fd679ee (Access Date 2021, Aug. 21).
14. Malafeev A., Laptev D., Bauer S., Omlin X. et al. Automatic Human Sleep Stage Scoring Using Deep Neural Networks. Front Neurosci, 2018, vol. 12, art. 781, pp. 1–15.
15. Masrur M.A., Chen Z., Zhang B., Jia H., Murphey Y. Model-Based Fault Diagnosis in Electric Drives Using Artificial Neural Networks. IEEE Transactions On Mechatronics, 2005, no. 11(3), pp. 290–303.
16. Mastering The New Generation of Gradient Boosting. Available at: https://towardsdatascience.com/https-medium-com-talperetz24-mastering-the-new-generation-of-gradient-boosting-db04062a7ea2 (Access Date 2021, Aug. 21).
17. Singhal Y., Jain A., Batra Sh., Varshney Y., Rathi M. Review of Bagging and Boosting Classification Performance on Unbalanced Binary Classification. IEEE 8^th International Advance Computing Conference (IACC), 2018.
18. Murphey Y. L., Masrur M. A., Chen Z. Fault Diagnostics in Electric Drives Using Machine Learning. IEEE International Conference: Electric Machines & Drives Conference (IEMDC), 2013.

Information about the authors

Yaroslav V. Mironenko – Deputy General Director, Company “RES Group”, Russia, Vladimir (yaroslav.mironenko@inbox.ru; ORCID: https://orcid.org/0000-0001-9836-7676).

Alexey D. Kurzanov – Leading Engineer, Company “RES Group”, Russia, Vladimir (rezer33@yandex.ru; ORCID: https://orcid.org/0000-0002-6910-7426).

For citations

Mironenko Ya.V., Kurzanov A.D. ASSESSMENT OF THE ELECTRICAL EQUIPMENT INSULATION STATE USING THE GRADIENT BOOSTING ALGORITHM. Vestnik Chuvashskogo universiteta, 2021, no. 3, pp. 94–102. DOI: 10.47026/1810-1909-2021-3-94-102 (in Russian).

Download the full article