Experiment design for the economic performance evaluation of industrial controllers

Experimental design techniques are routinely used in the social and biological sinces to determine the relative performance of different strategies or factors. However, these techniques are largely unknown to the process control community. The aim of this paper is to give a brief summary of standard experiment design concepts, and to illustrate their use on a flotation level control problem. Common incorrect experiments are demonstrated and it is shown how grossly incorrect conclusions can be drawn from such experiments. Our contention is that greater use of these tools by the process control community would significantly enhance the validity of comparative trials.