MODEL BASED REAL TIME CONTROLLER PERFORMANCE ASSESSMENT FOR NONLINEAR SYSTEMS

The aim of this paper is to present a novel methodology for the performance assessment of proportional-integral-derivative (PID) controllers operating in the presence of process nonlinearities. The principle objective is to assess the quality of controller performance in real time when subjected to setpoint changes. Using prescribed operating regions, optimal PID controller settings are synthesized off-line by numerical optimisation from a trained artificial neural network (ANN) of the process. To demonstrate the effectiveness of the proposed controller benchmarking scheme, the procedure is applied to a simulation example, plus a real process control loop operating in a full scale pH neutralization pilot plant. Results obtained from the experiments indicate that the method is suitable for servo tracking in nonlinear control loops such as those found in the pulp and paper, and water purification industries.