Fast self-learning improved adrc control method for nonlinear systems

Abstract

The invention discloses a fast self-learning improved ADRC control method for a nonlinear system, which includes the following steps: Step 1: Create an ADRC: the ADRC includes a tracking differentiator (TD), an expanded state Four parts of observer (ESO), nonlinear error feedback (NLSEF) and disturbance compensation; step 11) establish tracking differentiator (TD) control model; step 12) establish extended state observer (ESO) control model; step 13) establish Nonlinear error feedback (NLSEF) control model; Step 14) Establish a disturbance compensation control model; Step 2: Create a self-learning active disturbance rejection controller (SADRC): apply the self-learning method to the nonlinear error feedback (NLSEF) control model , establish a self-learning nonlinear ADRC control system model; Step 3: Create a fast self-learning ADRC (FSADRC): use the method of adding momentum to design an adaptive mechanism for learning rate, and establish a dynamic adaptive Fast self-learning model with learning rate.

Description

technical field [0001] The invention relates to a control method of a nonlinear system, in particular to a fast self-learning improved ADRC control method of the nonlinear system. Background technique [0002] The uniformity of the thickness of the biaxially stretched film is one of the important criteria for its quality. If the uniformity is not good, there will be a relative deviation in a certain position of the film. If this deviation position remains unchanged, after thousands of layers of winding, the film will have bad defects such as grooves, hoops or ribs, and cause permanent deformation. This makes the measurement and control of film thickness very important, because it directly affects the mechanical properties and performance quality of film products. In the production of biaxially stretched film, there are many factors that affect the thickness of the film, such as raw material quality, extrusion pressure, die temperature, stretching speed, etc. Changes in one ...

AI Technical Summary

Problems solved by technology

The RBF neural network algorithm can be used to control the film thickness, but the control effect is not good for large time delay systems

In short, there are still aspects to be optimized for the biaxially stretched film thickness control system

Images