Self-sensing Modeling of Rotor Displacement for Six-pole Radial Hybrid Magnetic Bearing Using Improved Simplified Particle Swarm Optimization LS-SVM

In order to solve the problems of large volume, high cost and low reliability caused by eddy current sensors or Hall sensors in magnetic bearings, a self-sensing control method based on the improved simplified particle swarm optimization (SPSO) least square support vector machine (LS-SVM) prediction model was proposed for six-pole radial hybrid magnetic bearing (HMB). The structure and principle of the six-pole radial HMB were introduced, and the mathematical model of its radial suspension force was derived according to the equivalent magnetic circuit method. Based on the principle of the support vector machine, the nonlinear predictive model between the currents and the rotor displacements was established, and the performance parameters of LS-SVM were optimized by using the improved SPSO algorithm, which realized the rotor displacement self-sensing control. The self-sensing simulation model of the six-pole radial HMB system was constructed, and the floating simulation experiment was carried out, which shows the feasibility of the self-sensing method. © 2020 Chin. Soc. for Elec. Eng.