A new GPC-based PID controller using memory-based identification

In this paper, a system identification scheme is proposed based on a memory-based modeling (MBM) method. According to the MBM method, some local models are automatically generated based on input/output data pairs of the controlled object stored in the data-base. Therefore, even if the system includes nonlinearities, the parameter estimation can work well. Furthermore, a PID parameters tuning method is discussed based on the relationship between the generalized predictive control (GPC) and the PID control. Then, the estimates given by the proposed identification scheme are utilized for the GPC-based PID controller.