Neural-Network-Based Rotor Position Estimation for Switched Reluctance Motor in Full Range of Speed

摘要

This paper proposes a novel online neural network of Switched Reluctance Motor (SRM) in order to estimate rotor position. Online learning algorithms and training steps are also discussed and analyzed. At zero and low speeds, a voltage pulse injection method is used to estimate the initial rotor position. Neural network online training algorithm on 15kW three-phase 12/8 SRM is implemented by TMS320F2812 DSP. Experimental results demonstrate the proposed method has a good estimation performance with a maximal error lower than 1%.