VARIABLE-STRUCTURE MODELS IN-PROCESS OBSERVATION AND CONTROL

A method is proposed for the modeling, observation, and control of pro cesses characterized by sequential transformation steps. Using the met hod, such processes are described by a battery of alternative submodel s, each of which qualitatively represents one of the process steps. Th e submodels cannot themselves track transitions from step to step. Thi s is handled by switching to an alternative submodel with a significan tly better predictive performance than that presently in use. The main advantage of the proposed approach is that each submodel is significa ntly simpler than the full model of the system. Example applications d emonstrate that these submodels, when combined with the switching stra tegy, are also convenient for parameter estimation, state observation, and regulatory control.