Abstract: The PID controller has been widely used in various industrial processes. However, for real practical control plants, their mechanisms, structures and operation conditions are different, and conventional tuning methods cannot always work in a desirable state. In order to improve the robustness and the stability of the control systems, advanced PID control algorithms have been attracted much attention. A prediction based adaptive control algorithm is proposed for CARIMA models, where the PID parameters can be tuned adaptively according to the parameters of the control plant. The key is minimizing a performance index which considers the quadratic predicted output, over the set point, as well as the control efforts, over a time horizon. For the online identification step, the recursive extended least squares estimation technique is implemented. The adaptability and the robustness of the proposed algorithm are validated by simulation results.

Key words: PID controller, CARIMA models, prediction, on-line identification, adaptability