A model adaptive predictive control method and system based on disturbance state compensation

By using a deep learning-based adaptive disturbance identifier and controller evaluation function, system disturbances are identified and compensated in real time. This solves the problem of poor control performance of traditional predictive control methods under complex disturbances, achieving high-precision and robust control performance, extending equipment life and reducing maintenance costs.

CN119356079BActive Publication Date: 2025-10-21CENT SOUTH UNIV
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411366785.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-29
Publication Date
2025-10-21
Estimated Expiration
2044-09-29

AI Technical Summary

Technical Problem

Traditional predictive control methods have difficulty in building accurate system models when faced with complex and variable disturbances, resulting in poor control effects and affecting system stability and control accuracy.

Method used

A deep learning-based adaptive disturbance identifier is used to identify and compensate for system disturbances in real time. By constructing an adaptive disturbance identifier model and a controller evaluation function, the optimal controller is automatically selected to achieve accurate disturbance compensation and correction of the prediction model.

Benefits of technology

It significantly improves the control accuracy and robustness of the system under varying disturbance environments, optimizes the control effect, extends the service life of the equipment, and reduces maintenance costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119356079B_ABST
    Figure CN119356079B_ABST
Patent Text Reader

Abstract

The application relates to the technical field of predictive control, and discloses a model adaptive predictive control method and system based on disturbance state compensation, which can identify and compensate system disturbances in real time by introducing an adaptive disturbance identifier based on deep learning, and significantly improves the control accuracy and robustness of the system when facing a variable disturbance environment; the application uses deep learning technology to construct a disturbance identifier, so that the disturbance identification process under data driving is more intelligent, subtle changes in the disturbance can be more accurately captured, and the accuracy of disturbance identification is improved; a performance evaluation mechanism is established, the optimal controller is automatically selected in the controller set, and the control optimization of the system under the disturbance is ensured; through accurate error evaluation, disturbance compensation and correction of the prediction model, the accuracy and effectiveness of the control signal are further ensured. These technologies and methods not only optimize the control effect, but also prolong the service life of the equipment and reduce the maintenance cost.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Wide-area power grid multi-disturbance accurate identification method and device based on big data analysis

    CN110414412A

  • Model predictive control parameter setting method based on multi-objective optimization algorithm

    CN115097727A

  • Power grid disturbance identification method and system based on improved FastICA

    CN115329820A