Next Generation Relay Autotuners – Analysis and Implementation

In order to produce models for automatic controller tuning, this paper proposes a method that combines a short experiment with a novel scheme for approximating processes using low-order time-delayed models. The method produces models aimed to tune PI and PID controllers, but they could also be used for other model-dependent controllers like MPC. The proposed method has been evaluated in simulations on benchmark processes. It has also been implemented in an industrial controller and tested experimentally on a water-tank process. It is shown that our method is successful in estimating models for a variety of processes such as lag-dominated, delay-dominated, balanced, and integrating processes. We also demonstrate that the experiment time is both shorter and more predictable than currently used autotuners.