Knowledge-Based Approach to Reconfigurable Control Systems

Abstract

Unstable, dynamically changing environments represent a major challenge for the design of adaptive control systems. Significant changes in the process model, various hardware failures may require the modification of the basic control law in order to maintain the control of the plant. To support the design and implementation of structurally adaptive systems, we have developed a new architecture and programming tools. The architecture enables on-line and automatic reconfiguration of the control structure. The most important features of our approach are: (1) knowledge-based techniques are used to represent the model of the process and the possible control schemes including alternatives and selection rules, (2) a graph-oriented computational model has been defined which allows the efficient implementation of reconfigurable signal processing systems and (3) a special interpretation technique has been developed which can build and dynamically change the signal-flow of signal processing and control systems. The operation of the system can be conceptualized in the following way. The actual state of the process is continuously monitored. If a significant change is detected, the process model will be updated which will start a reasoning process on the effects of the change. The result may be a partial or full reconfiguration of the cotroller without interrupting the system operation. The method has been implemented and tested in different applications. The paper will present the structure of a fault tolerant controller built for the control of a chemical process with unreliable sensors.