TY - GEN
T1 - Comprehensive evaluation and detection of partial discharge in WBG motor drive using DBSCAN based feature extraction
AU - Choksi, Kushan
AU - Mirza, Abdul Basit
AU - Salehi Vala, Sama
AU - Luo, Fang
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The emergence of Wide Band Gap (WBG) technology has significantly enhanced the efficiency and power density of motor drives. As a result, WBG motor drives have widely been adopted in aircraft and transportation applications, particularly in More Electric Aircraft (MEA) systems. However, the reliability of the WBG high-power drive system is still a major concern. The reliability of medium and high-voltage motor drives sees an increased insulation degradation due to a more intense partial discharge (PD) exposure. Hence, PD condition monitoring, detection, and analysis are valuable for reliable operation and timely maintenance. This paper deals with PD detection at various voltage levels, dV/dt, and waveform shapes. This paper provides robust detection and analysis of PD events deriving the key relationship between PD probability and factors impacting PD events. This paper provides novel PD detection based on pattern recognition which is adaptable to varying voltage and frequency of supply. This algorithm can help the computation of charge per PD event as well as PD probability.
AB - The emergence of Wide Band Gap (WBG) technology has significantly enhanced the efficiency and power density of motor drives. As a result, WBG motor drives have widely been adopted in aircraft and transportation applications, particularly in More Electric Aircraft (MEA) systems. However, the reliability of the WBG high-power drive system is still a major concern. The reliability of medium and high-voltage motor drives sees an increased insulation degradation due to a more intense partial discharge (PD) exposure. Hence, PD condition monitoring, detection, and analysis are valuable for reliable operation and timely maintenance. This paper deals with PD detection at various voltage levels, dV/dt, and waveform shapes. This paper provides robust detection and analysis of PD events deriving the key relationship between PD probability and factors impacting PD events. This paper provides novel PD detection based on pattern recognition which is adaptable to varying voltage and frequency of supply. This algorithm can help the computation of charge per PD event as well as PD probability.
KW - DBSCAN feature extraction
KW - detection algorithm
KW - Partial discharge
KW - PD detection setup
UR - https://www.scopus.com/pages/publications/85182930032
U2 - 10.1109/ECCE53617.2023.10362669
DO - 10.1109/ECCE53617.2023.10362669
M3 - Conference contribution
AN - SCOPUS:85182930032
T3 - 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023
SP - 3503
EP - 3509
BT - 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023
Y2 - 29 October 2023 through 2 November 2023
ER -