A qualitative reasoning approach for rule based controllers

This paper presents a qualitative reasoning approach for rule based controllers design. Through the proposed methodology the controllers are designed based on causal relationships between subsystems, and the control actions are inferred from samples of both controlled and noncontrolled variables. These causal relationships form a heuristic model of the system. Based on the heuristic model and the current state of the process, control actions can be inferred. Moreover, instead of continuous real-valued variables the process variable behaviour is represented through its qualitative values. In order to facilitate the relationships analysis among process variables a systematic methodology for description of system structures is proposed. These techniques have been successfully applied in simulation studies of a mixing process.