Tri-axial platform servo motor control method based on combination of BP neural network and active disturbance rejection controller

Abstract

The invention discloses a tri-axial platform servo motor control method based on the combination of a BP neural network and an active disturbance rejection controller. The tri-axial platform servo motor control method includes the following steps that 1, the kinetic equation of a tri-axial platform arbitrary-frame servo system containing a friction model is built; 2,according to the kinetic equation in the formula (I),the active disturbance rejection controller is designed; 3,a BP neural network parameter on-line setting module is designed and combined with the active disturbance rejection controller, and active disturbance rejection controller on-line parameter setting is achieved. By the adoption of the tri-axial platform servo motor control method based on the combination of the BP neural network and the active disturbance rejection controller, a flat top phenomenon and a dead zone phenomenon of a servo system can be basically eliminated, wherein the flat top phenomenon occurs during position signal tracking, and the dead zone phenomenon occurs during speed signal tracking; therefore, the position tracking precision and the speed tracking precision of the servo system can be improved.

Description

technical field [0001] The present invention relates to active disturbance rejection control in the field of nonlinear servo motor control, which is applied to a three-axis pan-tilt servo system with a friction model, and specifically relates to a three-axis pan-tilt servo based on a combination of BP neural network and an active disturbance rejection controller Motor control method. Background technique [0002] In recent years, with the rapid development of drone technology, consumer drones have been widely used in the field of low-altitude aerial photography. Due to the characteristics of small size and light weight, drones are easily affected by factors such as rotor rotation, motor vibration, attitude adjustment, and air flow during flight. It is difficult to directly install aerial cameras on drones to obtain high High-quality low-altitude aerial images, using a three-axis airborne stabilized gimbal can effectively reduce various interferences during the flight of the...

AI Technical Summary

Problems solved by technology

Research shows that the three parameters of ESO β 01 , β 02 , β 03 It has a great influence on the state estimation of the three-axis gimbal servo system with friction model, especially the accuracy of the total disturbance estimation has a great influence on the control performance, and the two parameters of NLSEF β 1 , β 2 Similar to k in PID control p 、k d , although the ADRC controller has many advantages over the classic PID control, there are many parameters in the ADRC, and the manual empirical method is usually used to adjust the parameters, and the parameter setting process is time-consuming and laborious

Images