Predictive control method and device of piezoelectric ceramic actuator on basis of neural network

Abstract

The invention discloses a predictive control method and device of a piezoelectric ceramic actuator on the basis of the neural network. The predictive control method includes modeling the piezoelectric ceramic actuator by the multilayer neural network to obtain a neural network model of the piezoelectric ceramic actuator; adopting the neural network model to obtain a synchronous linearized model in each sampling period; adopting the synchronous linearized model to obtain a predictive controller and optimizing the predictive controller; controlling displacement of the piezoelectric ceramic actuator on the basis of the synchronous linearized model and the corresponding predictive controller. On the basis of relevant content of the self-adaption control theory, displacement of the piezoelectric ceramic actuator is controlled in real time by means of a plurality of linear approximate models and the predictive controller on the basis of the neural network, the inherent problem of delay of the piezoelectric ceramic actuator is overcome, and displacement of the piezoelectric ceramic actuator is tracked and controlled in real time.

Description

technical field [0001] The invention relates to the fields of high-precision servo technology, nano-positioning technology, motion control technology and the like, in particular to a synchronous linearization model predictive control method of a piezoelectric ceramic actuator. Background technique [0002] The modern manufacturing industry is developing in the direction of increasing technological content and improving processing and manufacturing precision. Among them, the accuracy and precision of manufacturing are the primary demands for saving manufacturing costs and improving production efficiency. Nano-scale precise positioning technology, which is a key technology of precision machining and manufacturing, is one of the important technical means to realize the above demands. Piezoelectric ceramic actuator is one of the widely used components in precision machining and manufacturing, and has good precision positioning performance. [0003] However, the physical charac...

AI Technical Summary

Problems solved by technology

However, it is difficult to obtain a high-accuracy inverse model and the amount of calculation is large, which is not conducive to improving control accuracy and rapid application.

In addition, characteristics such as hysteresis are closely related to the frequency of the voltage signal acting on the piezoelectric ceramic actuator, and this property also has a certain impact on the inverse model modeling

Images