Maximal margin classifiers applied to DGA-based diagnosis of power transformers

• Autorzy: Szczepaniak P. , Kłosiński M.

Warianty tytułu

PL

Zastosowanie klasyfikatora do diagnozy gazów rozpuszczonych w oleju transformatora mocy

• Języki publikacji: EN

Abstrakty

EN

The paper addresses a modern approach to the problem of power transformer diagnosis. The method called support vector machines enables the creation of an expert system for oil transformer technical condition diagnosis. The system, which is based on real results of chromatography of gases dissolved in transformer oil (DGA), performs better than an internationally acknowledged standard – the IEC code.

PL

Przedstawiono nową metodę diagnostyki transformatora mocy bazująca na algorytmie “support vector machine”. W systemie bada się chromatograficznie gazy rozpuszczone w oleju transformatorowym.

Słowa kluczowe

EN

classification; power transformers; DGA; IEC; maximal margin classifiers; SVM

PL

SVM; transformator mocy; analiza oleju; klasyfikator

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2012
• Tom: R. 88, nr 2
• Strony: 100--104
• Opis fizyczny: Bibliogr. 16 poz., rys., tab.

Twórcy

autor

Szczepaniak P.

autor

Kłosiński M.

• Technical University of Łódź, Institute of Information Technology, ul. Wólczańska 215, 90-924 Łódź,

Bibliografia

• [1] IEC (1979): International Electrotechnical Commission, Interpretation of the Analysis of Gases in Transformers and other Oil-Filled Electrical Equipment in Service. Geneva, 1979.
• [2] B.E.Boser , I.M.Guyon, V.N.Vapnik (1992): A training algorithm for optimal margin classifier. In: D.Haussler (Ed.): 5th Annual ACM Workshop on COLT. Pittsburg, PA, ACM Press, 144-152.
• [3] V.N.Vapnik (1995): The Nature of Statistical Learning Theory. Springer-Verlag, Berlin, 1995.
• [4] V.N.Vapnik (1998): Statistical Learning Theory. Wiley, New York.
• [5] N.Cristianini (2001): ICML’01 Tutorial. http://www.kernelmachines. org .
• [6] N.Cristianini, J.Shawe-Taylor (2003): Support Vectors and Kernel Methods. In: M.Berthold, D.J.Hand (Eds.): Intelligent Data Analysis; An Introduction. Springer-Verlag, Berlin, Heidelberg.
• [7] P.-H.Chen, C.-J.Lin, B.Schölkopf (2001): A tutorial on _- Support Vector Machines. http://www.kernel-machines.org .
• [8] C.Cor tes , V.N.Vapnik (1995): Support Vector Networks. Machine Learning, 20, 273-297.
• [9] T.M.Cover (1965): Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition. IEEE Trans. on Electronic Computers, 14, 326- 334.
• [10] D.Decoste, B.Schölkopf (2002): Training Invariant Support Machines. Machine Learning, 46, 161-190.
• [11] V.Kecman (2001): Learning and Soft Computing. The MIT Press, Cambridge, Massachusetts.
• [12] B. Schölkopf, C.J.C.Burges, A.J.Smol a (Eds.): Advances in Kernel Methods: Support Vector Learning. The MIT Press, Cambridge, MA; 255-268.
• [13] Y.Lin, Y.Lee, G.Wahba (2002): Support vector machines for classification in nonstandard situations. Machine Learning, 46, nos.1-3; 191-202.
• [14] B. S chölkopf (1997): Support vector learning. R.Oldenbourg Verlag, München. Doktorarbeit, TU Berlin; http://www.kernelmachines. org
• [15] B.Schölkopf, A.Smola (2002): Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond. MIT Press, 2002.
• [16] M.Ulewicz (2003): Support Vector Machines with Distortions for Handwritten Digits Recognition. In: M.Kurzyński, E.Puchała, M.Woźniak (Eds.), KOSYR’2003 – Computer Recognition Systems, Wrocław, 109-114.