Design method of linear active disturbance rejection controller based on neural network prediction

Abstract

The invention discloses a method for designing a linear active disturbance rejection controller based on neural network prediction, which comprises the following steps of: 1, acquiring and preprocessing sample data, and constructing a sample training set and a sample test set; 2, constructing an ELMAN neural network prediction model by using the sample training set, and verifying the ELMAN neural network prediction model by using the sample test set; and 3, inputting the working condition data to the ELMAN neural network prediction model to obtain an output value to transform the extended state observer. Through the design of the linear active disturbance rejection controller, the control effect of the controlled object under various interferences is improved.

Description

technical field [0001] The invention belongs to the field of automatic control, and in particular relates to a design method of a linear active disturbance rejection controller based on neural network prediction. Background technique [0002] Active disturbance rejection control (ADRC) regards the unmodeled dynamics and unknown disturbances of the system as total disturbances, which are estimated by the extended state observer and eliminated in the feedback control. ADRC does not depend on the system model, has strong robustness, is suitable for complex on-site control environments, and can be relatively easily built in the configuration, and has been widely used in industries. In complex industrial environments, there are generally large inertia and large delay control objects, and it is difficult for the classic ADRR technology to deal with the large delay directly. Therefore, the application of the classic ADRR technology in the large delay system faces the situation that...

AI Technical Summary

Problems solved by technology

[0005] Both of the above two controllers use part of the information of the controlled object, which can improve the control effect of the large-delay object to a certain extent. The time-delay system often reflects the phenomenon of time-varying, and the delay characteristics are prone to fluctuations and changes. The existing controlled objects are affected by external disturbances, which leads to the change of the adjustment effect of the existing improved ADRC controller in actual engineering. Poor or even unstable situation, ADRC is difficult to achieve satisfactory control effect

Images