Sihem Aliouat
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sihem Aliouat has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Hocine Moulai
PhD in Electrical Engineering Institution Characterization and Diagnosis of Power Equipments Laboratory USTHB University Address Bab Ezzouar Algeria
2 shared publications Azzeddine Nacer
1 shared publication- Azzeddine Nacer
Faculty of Electrical Engineering, University of Science and Technology Houari Boumediene (USTHB), Algiers, Algeria
1 shared publication Kamel Boudjit
1 shared publication- M. Gueraichi
Faculty of Electrical Engineering, University of Science and Technology Houari Boumediene (USTHB), Algiers, Algeria
1 shared publication - Nabila Dhahbi-Megriche
National Institute of Applied Sciences and Technology, LR11ES25 MMA Lab University of Cartage Tunis, Tunisa
1 shared publication
Latest Publications
- 3 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dielectrics and Electrical Insulation
- Vol. 32 (5) , 2888-2895
Discriminative Analysis of HVDC Discharges Over Composite Insulators by Feature Selection Combined With SVM
HV insulation systems under AC or DC are subject to partial discharges (PD) phenomena which happen randomly and can lead to progressive damage of the dielectric material and/or the outage of the line in which they occur. In order to automate the predictive maintenance, these discharges must be monitored in real time to recognize their energetic nature: low-energy (LE) ones which extinguish by themselves, or contrarily high-energy (HE) ones which can lead to flashovers that imply line outage. One has then to focus on high-energy discharges since they constitute the major risk for the insulation systems and the network stability. For this aim, an experimental investigation was performed for HVDC voltages applied to composite insulators, from levels corresponding to low energy partial discharges to flashover occurrence. Thereby, low noise nanosecond scale measurements are taken simultaneously for voltages, currents and radiated magnetic fields by both types of discharge where a qualitative database was obtained. This paper presents the use of efficient and fast feature selection software that uses the Fisher score as evaluation criterion. The features are selected, and then classified from the most to the least discriminant. The number of the most successive discriminant features which correspond to the best high-energy discharges recognition ratio is then searched. The obtained results from the achieved algorithm, combined with SVM, allow an important reduction of feature number from 25000 to only 37, and an improvement of 4.9% of high-energy discharges recognition when compared to the results obtained before feature selection. The approach is suitable for real time diagnosis of insulator chains close to substations and power plants.
- 3 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dielectrics and Electrical Insulation
- Vol. 32 (5) , 2888-2895
Discriminative Analysis of HVDC Discharges Over Composite Insulators by Feature Selection Combined With SVM
HV insulation systems under AC or DC are subject to partial discharges (PD) phenomena which happen randomly and can lead to progressive damage of the dielectric material and/or the outage of the line in which they occur. In order to automate the predictive maintenance, these discharges must be monitored in real time to recognize their energetic nature: low-energy (LE) ones which extinguish by themselves, or contrarily high-energy (HE) ones which can lead to flashovers that imply line outage. One has then to focus on high-energy discharges since they constitute the major risk for the insulation systems and the network stability. For this aim, an experimental investigation was performed for HVDC voltages applied to composite insulators, from levels corresponding to low energy partial discharges to flashover occurrence. Thereby, low noise nanosecond scale measurements are taken simultaneously for voltages, currents and radiated magnetic fields by both types of discharge where a qualitative database was obtained. This paper presents the use of efficient and fast feature selection software that uses the Fisher score as evaluation criterion. The features are selected, and then classified from the most to the least discriminant. The number of the most successive discriminant features which correspond to the best high-energy discharges recognition ratio is then searched. The obtained results from the achieved algorithm, combined with SVM, allow an important reduction of feature number from 25000 to only 37, and an improvement of 4.9% of high-energy discharges recognition when compared to the results obtained before feature selection. The approach is suitable for real time diagnosis of insulator chains close to substations and power plants.
- 29 December 2024
- Published by Elsevier in Electric Power Systems Research
- Vol. 241
Behavior of composite insulators under HVDC stress, from creeping discharges until flashover
- 29 December 2024
- Published by Elsevier in Electric Power Systems Research
- Vol. 241
Behavior of composite insulators under HVDC stress, from creeping discharges until flashover