Machine learning based iterative learning control for non‐repetitive time‐varying systems

The repetitive tracking task for time-varying systems (TVSs) with non-repetitive parameters at each trial, which is also called TVSs, realized in this article using iterative learning control (ILC). A machine (ML) based nominal model update mechanism, utilizes the linear regression technique to ILC trial only current information, proposed TVSs order enhance performance. Given that ML mechanism forces uncertainties remain within robust tolerance, an law deal TVSs. How tune inside and algorithms achieve desired aggregate performance provided. robustness reliability of method are verified by real experiments. Real data comparison state-of-the-art methods demonstrates its superior terms controlling precision. This broadens applications from time-invariant adopts estimate between two trials proposes a detailed parameter tuning performance, main contributions.