Discharge Currents Discrimination Technique Based on Multi-Linear Regression Line and Arti cial Neural Networks for Power Transformers Diagnosis

F. Benyahia (1) , Azzeddine Nacer (1) , Hocine Moulai (1) , F. Aberkane (1) , Abderrahmane Beroual (2)

1 USTHB - Université des Sciences et de la Technologie Houari Boumediene = University of Sciences and Technology Houari Boumediene [Alger]
2 EE - Ampère, Département Energie Electrique

The proposed work will be consecrated to the study of positive pre-breakdown currents triggered in mineral transformer oil under 50 Hz alternating overvoltage. Since negative currents are recorded in low rates and for higher voltage levels than positive ones, only the latter will be prior taken into consideration. Both streamer propagation and arc discharge current types are identi ed and are used in the training process of an arti cial neural network and the multi-linear regression line of these currents in order to develop a complementary diagnosis tool that can serve as an on-line transformer protection. More successful results than those obtained by other developed techniques are expected.

Domaines: Energie électrique

F. Benyahia, Azzeddine Nacer, Hocine Moulai, F. Aberkane, Abderrahmane Beroual. Discharge Currents Discrimination Technique Based on Multi-Linear Regression Line and Arti cial Neural Networks for Power Transformers Diagnosis. Acta Physica Polonica A, 2013, 123 (2), pp.250-253. ⟨10.12693/APhysPolA.123.250⟩. ⟨hal-01074188⟩