Method for constructing five-freedom bearingless asynchronous motor support vector machine inverse controller

Abstract

The invention discloses a method for constructing a five-freedom bearingless asynchronous motor support vector machine inverse controller. A support vector machine inverse with 7 input nodes and 7 output nodes is formed by using a support vector machine and 12 integrators, the support vector machine having 19 input nodes and 7 output nodes. The support vector machine inverse is disposed in front of a composite controlled object to form a pseudo-linear system. The pseudo-linear system is equivalent to five positional second-order integral pseudo-linear subsystems, a rotate speed first-order integral pseudo-linear subsystem, and a flux linkage first-order integral pseudo-linear subsystem. Corresponding controllers are respectively designed, and a linear closed loop controller is formed. A support vector machine inverse controller is formed by the linear closed loop controller, the support vector machine inverse, three Clark inverse transformation, three current-tracking inverters, and a linear power amplifier, thereby realizing non-linear dynamic decoupling control among suspension force, rotating speed, and flux linkage.

Description

technical field [0001] The invention relates to a construction method of an inverse controller of a five-degree-of-freedom bearingless asynchronous motor support vector machine, belonging to the technical field of electric drive control equipment. Bearingless asynchronous motors have broad application prospects in many high-speed and ultra-high-speed special electrical transmission fields such as centrifuges, sealed pumps, aerospace, CNC machine tools, flywheel energy storage, and life sciences. Background technique [0002] Utilizing the similarity between the magnetic bearing and the motor structure, the magnetic bearing suspension winding (coil) is embedded in the stator winding of the motor, so that the two magnetic fields can be integrated into one body, and the rotation and suspension of the motor rotor can be controlled independently at the same time. Bearingless motors are proposed based on this assumption. There are many types of bearingless motors, among which bear...

AI Technical Summary

Problems solved by technology

[0004] Based on the torque winding vector control method of bearingless asynchronous motor, the stable suspension control of bearingless asynchronous motor with five degrees of freedom can be realized, but this control is a kind of steady-state decoupling control, because the coupling effect between various variables of the system is ignored , unable to meet the high-speed and high-precision operation requirements of the five-degree-of-freedom bearingless asynchronous motor

Therefore, the inverse system method is used to dynamically decouple the five-degree-of-freedom bearingless asynchronous motor control system, but the realization of the dynamic decoupling must obtain the precise mathematical model of the controlled object

The five-degree-of-freedom bearingless asynchronous motor is a complex nonlinear system, and the parameters of the motor change significantly under various working conditions. In addition, there are magnetic circuit saturation, changes in the levitation force when the stator and rotor are eccentric, and load disturbances. The change of radial force when the upper rotor is eccentric, the existence of load disturbance and the influence of magnetic saturation make the inverse system method encounter bottlenecks in practical applications

Although the neural network inverse method solves the thorny problem that the inverse model is difficult to obtain in the inverse system method, due to the shortcomings of the neural network such as slow learning speed, long training time, local minimum problems, difficulty in extracting ideal samples, and difficult optimization of the network structure, The decoupling control effect of the inverse five-degree-of-freedom bearingless asynchronous motor based on the neural network is not ideal

Images