Abstract
Many manufacturing processes have, by nature, multiple-input and multiple-output (MIMO) variables. However, despite of the frequently encountered applications MIMO process feedback control has not been fully investigated in literature.Under a linear MIMO model, this paper proposed a multivariate exponentially-weighted moving-average (MEWMA) controller.The stability condition of this controller and the feasible region of its associated discount matrix is derived. To implement this run-to-run (RTR) feedback control scheme, a discount factor that minimizes the total mean square error (TMSE) of the process output is obtained under the assumption that the process disturbance is a white noise series, or IMA(1,1) series. An example is given to demonstrate the proposed method. Some concluding remarks are also made.