Bayesian classifier is the tool of increasing the efficiency of defects recognition in power transformers
https://doi.org/10.30724/1998-9903-2019-21-6-11-18
Abstract
The article considers the method of forming a statistical Bayesian classifier in relation to the problems of operational diagnostics and rapid evaluation of the technical condition of transformer equipment. It is proposed to use the classifier as a regular means to improve the reliability of defect recognition in power oil-filled transformers based on the analysis of dissolved gases in oil. A stochastic approach to the formation of the classifier in a conditions linearly realized dichotomy of technical status classes is developed. As a distinguishing feature, a nonlinear function of the primary parameters of state is used. This simultaneously achieves both a reduction in the dimension of the feature space and an improvement in the characteristics of the random distribution. The proposed approach allows to form a decisive rule that minimizes the total error of decision-making regardless of the impact on the object of random operational factors. The results of the study of stochastic properties of the distributions of the distinguishing feature for each of the selected classes of states are obtained. The algorithm to perform statistical calculations and procedures for recognizing the current state of the transformer using the generated decision rule is designed. The results of the study illustrate the possibility of practical application of the developed approach in the real exploitation of power transformers.
About the Authors
А. A. Yahya
Novosibirsk State Technical University
Russian Federation
Russian Federation
Ammar A. Yahya
Novosibirsk
V. M. Levin
Novosibirsk State Technical University
Russian Federation
Russian Federation
Vladimir M. Levin
Novosibirsk
References
1. Zheleznov FD, Akulov VA, Plotnikov YuI et al. Metody i sredstva povysheniya dostovernosti ul'trafioletovoi diagnostiki izolyatsii kontaktnoi seti. Available at: www.panatest.ru/static?al=ultrafioletovaja-diagnostika-izoljacii-contaktnoj-seti. Accessed to: 28 Aug 2019.
2. Chernopazov MS, Mironov IS, Postanogov SA, et al. Povyshenie dostovernosti otsenki izmeryaemykh parametrov tekhnicheskogo sostoyaniya. 2015;3:24-29.
3. Kuznetsova MI, Kitaev SV. Povyshenie dostovernosti diagnostirovaniya tekhnicheskogo sostoyaniya gazoturbinnykh ustanovok. Transport i khranenie nefteproduktov i uglevodorodnogo syr'ya. 2014;3:25-28.
4. Agarkov SA, Vlasov AB, Yudin YuI. Sistema teplovizionnoi diagnostiki elektro- i teploenergeticheskogo oborudovaniya na sudakh i ob"ektakh beregovoi infrastruktury . Vestnik Astrakhanskogo gosudarstvennogo tekhnicheskogo universiteta. Seriya: Morskaya tekhnika i tekhnologiya. 2016;3:66-74.
5. Birger IA. Tekhnicheskaya diagnostika. M.: Mashinostroenie, 1978. P. 240.
6. Catterson VM and Rudd, SE and McArthur, et al. On-line transformer condition monitoring through diagnostics and anomaly detection. In: IEEE International Conference on Intelligent Systems Application to Power Systems 2009 (ISAP 2009), 8-12 Nov 2009, Curitiba, Brazil.
7. Dončuk J, Mentlik V, Velek J. Condition assessment of power transformer using gas detection methods. Available at: http://pe.org.pl/articles/2013/1a/42.pdf. Accessed: 28 Aug 2019.
8. Mirowski P, LeCun Ya. Statistical Machine Learning and Dissolved Gas Analysis: A Review. IEEE Transactions on Power Delivery. 2012;27(4):1791-1799.
9. Wang L, Zhao X, Pei , et al. Transformer fault diagnosis using continuous sparse auto encoder Springer Plus (2016) 5: 448. Published online 2016. doi: 10.1186/s40064-016-2107-7.
10. Davidenko IV, Komarov VI. Primenenie metodov matematicheskoi statistiki dlya polucheniya kriteriev otsenki sostoyaniya silovykh transformatorov po rezul'tatam khromatograficheskogo analiza rastvorennykh v masle gazov. Elektrotekhnika, elektroenergetika, elektrotekhnicheskaya promyshlennost'. 2003;1:37-41.
11. Kovalenko DA, Zavidei VI, Pechenkin VI. Primenenie korrelyatsionnogo analiza pri aktivno-teplovoi diagnostike vnutrennego sostoyaniya silovykh transformatorov. V mire nauchnykh publikatsii. 2015; 2 (62): 449-464. doi: 10.12731/wsd-2015-2-26.
12. Zakharov AV. Korrelyatsionnye kharakteristiki diagnosticheskikh parametrov gazov, rastvorennykh v masle, pri normal'nom rezhime raboty transformatora . NRE. 2002;1:36-40.
13. Aivazyan SA, Bukhshtaber VM, Enyukov IS, et. al. Prikladnaya statistika. Klassifikatsiya i snizhenie razmernosti. Moskva: Finansy i statistika, 1989. P. 607 .
14. Levin VM, Yakh'ya AA. Adaptivnoe upravlenie tekhnicheskim sostoyaniem silovykh transformatorov. Novoe v rossiiskoi elektroenergetike. 2018;11:81-89.
15. Puza B. Bayesian methods for statistical analysis: Australian National University, VIEW. 2015; 677 p.
16. Yudin SV, Protas'ev VB, Podkopaev RYu, et. al. Metodika statisticheskogo priemochnogo kontrolya na osnove baiesovskogo podkhoda (gipergeometricheskoe raspredelenie). Sovremennye naukoemkie tekhnologii. 2018;10:161-165.
Review
For citations:
Yahya А.A., Levin V.M. Bayesian classifier is the tool of increasing the efficiency of defects recognition in power transformers. Power engineering: research, equipment, technology. 2019;21(6):11-18. (In Russ.) https://doi.org/10.30724/1998-9903-2019-21-6-11-18
Views:
438
Email this article 