Abstract
Switched reluctance generator (SRG) is becoming more and more attractive in wind energy applications mainly because of its high fault tolerant ability and high reliability. The position sensor is one of the vulnerable points of the SRG when exposed to harsh environments such as offshore where many wind turbines are operating. Fast and accurate rotor position estimation is essential to promote the sensorless control as well as sensor fault tolerant operation of the SRG, which may improve the reliability of the system. This paper presents a rotor position sensorless estimation scheme for Switched Reluctance Wind Generator (SRWG) based on Extreme Learning Machine (ELM) which could build a nonlinear mapping between flux linkage-current and rotor position. The learning data are derived from magnetization curves of the SRWG which are obtained from Finite Element Analysis (FEA) of an SRG with 8/6 stator and rotor poles . The effectiveness and accuracy of the proposed position estimation method are verified by simulation at various operating conditions.
Original language | English |
---|---|
Title of host publication | Proceedings of the International Conference on Wind energy Grid-Adaptive Technologies, WEGAT 2014 |
Number of pages | 9 |
Publisher | Chungbuk University, Korea |
Publication date | Oct 2014 |
Publication status | Published - Oct 2014 |
Event | International Conference on Wind energy Grid-Adaptive Technologies, WEGAT 2014 - Jeju, Korea, Republic of Duration: 20 Oct 2014 → 22 Oct 2014 |
Conference
Conference | International Conference on Wind energy Grid-Adaptive Technologies, WEGAT 2014 |
---|---|
Country/Territory | Korea, Republic of |
City | Jeju |
Period | 20/10/2014 → 22/10/2014 |
Keywords
- Extreme learning machine
- Finite element analysis
- Rotor position estimation
- Switched reluctance wind generator