Decoupling Control of Permanent Magnet-Assisted Bearingless Synchronous Reluctance Motor Based on Fuzzy Neural Network Inverse System Optimized by Improved Differential Evolution Algorithm

Abstract

In order to realize the high performance control of the permanent magnet-assisted bearingless synchronous reluctance motor (PMa-BSynRM), a decoupling control method combining fuzzy neural network (FNN) inverse system (IS) and improved differential evolution (IDE) optimization algorithm is proposed. First, the working principle of the PMa-BSynRM is introduced, and the mathematical models of suspension forces and torque are derived and the reversibility of the PMa-BSynRM is analyzed. Second, the IDE algorithm is used to optimize the premise and the result parameters of the FNN to solve the problem that it is difficult to determine the training parameters of the FNN. Third, the FNN is used to fit the IS model of the PMa-BSynRM, the IS model is connected in series with the original system to form a pseudo-linear system, and a linear closed-loop controller is designed for the control. Finally, the simulations and experiments studies are carried out for the designed control system, and the results show that the proposed control method realizes the decoupling between the electromagnetic torque and the suspension forces, and the robustness and dynamic performance of the system are improved.