Run-to-run control methods based on the DHOBE algorithm

Many run-to-run (RtR) control methods have been developed in recent years. Two particular set-valued RtR control schemes based on the Dasgupta-Huang Optimal Bounded Ellipsoid (DHOBE) algorithm are introduced. Compared to other RtR control schemes, the methods in this paper only need to know the bound of the noises, and are easy to implement. The DHOBE algorithm, for each recursion, returns an outer bounding ellipsoid of the estimated parameters. If the center of the ellipsoid each time is taken as the model coefficients, the explicit model update is implemented which leads to a model-reference method. If we choose the worst-case point which maximizes the cost function in the set, then we can apply the set-valued worst case approach. These two methods were compared with two other main RtR control schemes: the Exponentially Weighted Moving Average (EWMA) method and the Optimizing Adaptive Quality Controller (OAQC) method. Simulation results showed the superior performance of the RtR controllers based on the DHOBE algorithm. Furthermore this paper showed that it is necessary to apply nonlinear models to compensate for severe nonlinear processes.