An Investigation of Switched Reluctance Rotor Position Estimation Using Neural Networks
Abstract
The Switched Reluctance Machine (SRM) has potential applications in the More-Electric Aircraft program. Such applications include fuel and oil pump, actuators, braking systems and integral starter/generators. However, one difficulty in the controller design still exists. Knowledge of the relative position of the rotor with the stator is required for timing of the excitation pulses. This position is conventionally measured by an encoder or resolver. However, for many applications of the SRM such a sensor will not operate in the harsh environment of the machine. Developing a means of estimating the rotor position without the need for a rotor-mounted position sensor is the aim of this research. Specifically, this paper investigates the possibility of using neural networks for rotor position estimation.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 1992
- Accession Number
- ADA252846
Entities
People
- Jenifer M. Shannon
Organizations
- Naval Air Warfare Center Aircraft Divison