Naslov
Practical verification of DGA automatic diagnosis for power transformers with new VEV method for second level of diagnosis resolution

Autori
Banović, Mladen ; Sanchez, Jean ; Belmiloud, Mohamed

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 2010 International Conference on Condition Monitoring and Diagnosis / - Tokyo : CMD 2010, 2010, 938-941

ISBN
978-4-88686-070-5

Skup
International Conference on Condition Monitoring and Diagnosis 2010

Mjesto i datum
Tokyo, Japan, 06.09.2010. - 11.09.2010

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
transformer; oil; dissolved gas analysis; interpretation; artificial intelligence; VEV inference method

Sažetak
Power transformers are key components of transmission and distribution system. Hence, knowing their health is very important for safe and reliable operation of power system. Many diagnostic techniques are used for assessment of transformer state. One of them is a dissolved gas analysis (DGA), which comprises measurement of concentrations of gases dissolved in transformer oil and interpretation of these concentrations, i.e. assessment of the condition, or health. Focus of this paper is on interpretation of DGA results. New method, based on artificial intelligence techniques, is developed. It is trained, tested and verified on real cases of transformer faults, and very good results are obtained. Method and verification results are described here.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika

POVEZANOST RADA