Direct Data-Driven Tuning of Look-Up Tables for Feedback Control Systems

In industry, a feedback controller with look-up table (LUT) is often used for nonlinear systems. Although this structure easy to understand, tuning the LUT parameters time-consuming due huge number of parameters. This paper presents direct data-driven design method gain-scheduled directly tune from single-experiment data without system model. Specifically, conventional virtual reference (VRFT), which method, extended and L2 norm adjacent added VRFT cost function avoid overlearning. The optimized are analytically obtained by generalized ridge regression. A simulation demonstrates that proposed can obtain knowledge controlled object’s characteristics.