Rule-based real-time control systems

Abstract

The premise that one can obtain more effective control systems with less engineering effort, less technical risk, and less cost via the use of artificial intelligence techniques is explored in this paper. In particular, we discuss, develop, and illustrate the use of a rule-based system for real-time control as a software environment that can be used for control system implementation, relieving the design engineer of much of the burden of taking a basic control algorithm and making it work in a real-world application. We show that the rule-based systems approach can be used to provide substantial support for the above task. A rule-based system provides the environment in which the designer can develop and test all of the required heuristic logic and control, using a programming language (production rules) that is ideally suited for the task. We develop the details of such an implementation methodology, and illustrate its application to failure detection and isolation.