Design of a Database-Driven Model Error Compensator

A model error compensator (MEC) was proposed as a method to improve the control loop performance by suppressing modeling errors. MEC suppresses modeling errors by providing feedback on the error between control output and model output. In MEC, the performance of the modeling error suppression is strongly affected by the structure of the compensator and the tuning of control gains. Model-based design methods based on robust control and parameter tuning methods based on data-driven approaches have been proposed as design methods for MEC. However, an appropriate compensator structure and parameters are required to suppress modeling errors effectively. This study proposes a design method for structure-free MEC to directly determine compensation inputs using a database-driven approach. Thanks to the proposed method, the optimal output from the compensator can be obtained using only data. This paper verifies the effectiveness through numerical examples and implementation to the hydraulic motor control system.