Statistical Analysis of Current-based Features for Dip Voltage Fault Detection and Isolation

Amel Adouni , Dhia Chariag (1, 2) , Claude Delpha (3) , Demba Diallo (4) , Lassaad Sbita (2)

1 Université de Gabès
2 ENIG - Ecole Nationale d'Ingénieurs de Gabès
3 L2S - Laboratoire des signaux et systèmes
4 GeePs - Laboratoire Génie électrique et électronique de Paris

The high penetration of Wind Turbine (WT) in the grid is a promising solution to increase the electricity production with renewable energies. In this work, we propose a data-driven methodology for dip voltage fault detection and diagnosis. From experimental measurements the current vector trajectory deformation in the (αβ) reference frame is derived and a statistical-based analysis (first four statistical moments) of two relevant features are extracted (the ratio between the two axis and the rotation angle) is conducted. Thanks to this ratio, the method is robust to load variations. The fault isolation is done accurately with the analysis of the shift angle. The fault detection performances are evaluated with the ROC curves that reveal a probability of detection equal to 1 and a null probability of false alarm.

Keywords: ROC curves; current-based features; dip voltage fault detection; Wind Turbine; electricity production; renewable energies; fault isolation; current vector trajectory deformation; Current vector; Fault Detection and Identification; Statistical moments; Dip voltage fault

Domains: Engineering Sciences [physics]; Signal and Image processing

Amel Adouni, Dhia Chariag, Claude Delpha, Demba Diallo, Lassaad Sbita. Statistical Analysis of Current-based Features for Dip Voltage Fault Detection and Isolation. 43rd Annual Conference of the IEEE Industrial Electronics Society (IECON 2017), Oct 2017, Beijing, China. ⟨10.1109/iecon.2017.8216748⟩. ⟨hal-01578478⟩