Material transfer device reinforcement learning control method based on state and disturbance estimation

Abstract

The invention discloses a material transfer device reinforcement learning control method based on state and disturbance estimation. The method comprises the steps that firstly, a control model of a material transfer device electro-hydraulic servo system is established; then, a novel nonlinear extended state observer is adopted to estimate the unknown state and equivalent disturbance of the hydraulic servo system, and the theoretical estimation error of the nonlinear extended state observer is zero; on the basis of the state and equivalent disturbance estimation, a sliding mode controller is designed to realize rapid and high-precision control of the hydraulic servo system; finally, a reinforcement learning method is adopted, online self-adaptive learning is conducted on sliding mode controller parameters through system self-adaptive learning, and the control performance of the hydraulic servo system is improved. According to the invention, other states and disturbance information can be obtained according to the position information of the hydraulic servo system; the sliding mode controller parameter self-tuning method can realize control of sliding mode controller parameter self-tuning through a reinforcement learning method, a large number of manual experiments for tuning are not needed, the workload is reduced and the control precision is improved.

Description

technical field [0001] The invention belongs to the field of fluid transmission and control, in particular to a material transfer device reinforcement learning control method based on state and disturbance estimation. Background technique [0002] The electro-hydraulic servo system has the characteristics of large output torque / force, high rigidity, high precision, and fast response, and is widely used in robotics, aerospace, defense industry, and large-scale construction machinery. In recent years, with the development of technology, the requirements for the hydraulic control system have become higher and higher. However, due to the strong nonlinearity and uncertainty of the hydraulic system, it is difficult to achieve high-performance control of the hydraulic system. At present, the hydraulic servo system still adopts the PID control strategy to a large extent. Not only is the PID parameter setting difficult, the ability to adapt to system parameter changes is weak, but al...

AI Technical Summary

Problems solved by technology

In recent years, with the development of technology, the requirements for hydraulic control systems have become higher and higher. However, due to the strong nonlinearity and uncertainty of the hydraulic system, it is difficult to achieve high-performance control of the hydraulic system.

At present, the hydraulic servo system still adopts the PID control strategy to a large extent. Not only is the PID parameter setting difficult, the ability to adapt to system parameter changes is weak, but also the control accuracy and response speed are difficult to meet the increasing control performance requirements. Design of control method for electro-hydraulic servo system with strong self-adaptation and self-learning ability

Images