Intelligent Control of Hydraulic Excavators Based on Data-Driven GPC and High-Order Fully Actuated Systems

This paper proposes an intelligent control approach based on data-driven generalized predictive control (DD-GPC), which is based on a high-order fully actuated (HOFA) system model and aims to solve the difficult problems of parameter uncertainties, strong nonlinearities, and significant time delays in the hydraulic excavator system. First, a generalized predictive controller is designed to compensate for the time delay of the system. Then, the GPC controller parameters are computed online using data-driven control theory within the framework of a HOFA system model to improve controller performance without the need for a comprehensive global mathematical model. Finally, an error feedback mechanism is introduced into the future reference value to improve the responsiveness of the system. The simulation results of the hydraulic excavator grading operation proved the superiority and effectiveness of the proposed method.