Adaptive inverse controller construction method for bearingless permanent magnetic synchronous motor radial position nerve network

Abstract

The invention relates to an adaptive inverse controller construction method for a bearingless permanent magnetic synchronous motor radial position nerve network. The method comprises steps that: 1), a composite controlled object is constructed; 2), the nerve network is utilized to construct a horizontal displacement object model, a horizontal displacement inverse control model, a vertical displacement object model and a vertical displacement inverse control model of the composite controlled object; 3), the horizontal displacement inverse control model and the vertical displacement inverse control model are connected in series before the composite controlled object as two paths of feedforward controllers of the composite controlled object; 4), on-line adjustment on weight parameters of the horizontal displacement object model, the horizontal displacement inverse control model, the vertical displacement object model and the vertical displacement inverse control model is carried out in real time; and 5), a horizontal displacement nerve network adaptive inverse controller and a vertical displacement nerve network adaptive inverse controller are constructed and commonly form a nerve network adaptive inverse controller which controls the composite controlled object.

Description

technical field [0001] The invention relates to a construction method of a radial position neural network self-adaptive inverse controller of a bearingless permanent magnet synchronous motor, belonging to the technical field of special electric transmission / drive control. Background technique [0002] In recent years, with the rapid development of magnetic levitation technology, rare earth permanent magnet materials, control theory, and power electronics technology, bearingless permanent magnet synchronous motors and related technologies have been continuously developed and improved. Centrifuges, turbomolecular pumps, life sciences, flywheel energy storage and other fields have shown important scientific research and application value, especially the advantages of bearingless permanent magnet synchronous motors without lubrication and contact wear, making them suitable for vacuum technology, aseptic It has broad application prospects in special occasions such as workshops, p...

AI Technical Summary

Problems solved by technology

However, the key to implementing adaptive inverse control is to accurately obtain the mathematical model of the controlled object and its inverse model, and the radial position system of the bearingless permanent magnet synchronous motor is a complex system with multiple variables, nonlinearity, and strong coupling , it is difficult to obtain its precise mathematical model, not to mention the precise model of its inverse model, so the use of the adaptive inverse method is limited

Images