A practical global multi-stage method for fully automated closed-loop identification of industrial processes

A method for automated closed-loop identification is presented. The method is focused on practical deployment and has evolved based on academic developments, personal experience in industrial applications and feedback from seasoned practitioners who have a wealth of experience in implementing multivariable predictive control (MPC) and optimization projects. In essence, the basic idea here is that no single method will be adequate for the range of conditions encountered in the target industries. Hence this approach utilizes a family of prediction error model derived structures and consequently a family of model orders for each structure. These families are then searched for the most effective model for the given application. Key in this search is the definition of metrics not exclusively dependent on asymptotic theory. Extensive plant data are used to illustrate important features of the approach and overall performance.