Suspension Control for Bearingless Doubly Salient Electromagnetic Motor Considering Magnetic Saturation Based on Back Propagation Neural Network

The saturation state of the bearingless doubly salient electromagnetic motor (BDSEM) changes the gain relationship between current and suspension forces, which makes the suspension control system of the BDSEM unstable. In this paper, a suspension control method for the BDSEM based on the back propagation (BP) neural network is proposed. Firstly, the influence of magnetic saturation on the suspension control system and its mechanism are analyzed. Secondly, suspension forces characteristics are analyzed based on the finite element simulation under saturation conditions, and the data set is provided for the suspension forces modeling. Thirdly, the suspension control method based on neural network is introduced to control the nonlinear suspension forces with different field current. Finally, the simulation verification confirms the feasibility of the proposed control method under the BDSEM saturation conditions.