Decoupling control of AC active magnetic bearings based on DRFNN inverse

A dynamic decoupling control approach based on dynamic recurrent fuzzy neural network (DRFNN) inverse system theory is developed for the electric spindle system supported by 5-degree of freedom(DOF) AC active magnetic bearing (AMB), which is a multivariable, nonlinear, strong coupled system. The mathematical equations of radial and axial suspension forces are deduced. The analytical inverse system of the AMB is obtained by analyzing the reversibility of the mathematical model. The configuration of dynamic recurrent fuzzy neural network is introduced briefly. The dynamic recurrent fuzzy neural networks and integrators are used to construct fuzzy neural network inverse system. Then fuzzy neural network inverse system and original system are in series to constitute pseudo linear system, and linear system theory is applied to the pseudo linear system to synthesize and simulate. The simulation results show that this kind of control strategy can realize dynamic decoupling control among 5-degree of freedom of the system, and the whole control system has good dynamic and static performance.