A knowledge acquisition and processing strategy based on formal concept analysis

Abstract

A new method for knowledge acquisition and processing is developed by using the mathematical theory of formal concept analysis. First it is demonstrated how a decision table for a process control problem (distillation column) is obtained by a dialogue between the expert and the computer. Then the concept analysis approach is briefly outlined. This enables an optimization of conventional expert systems. However, more important for practical real time applications is the direct processing of the knowledge contained in a decision table by combining concept analysis with Shannon's entropy. Thus the resulting knowledge based system is optimal in an information theoretical view. It can be implemented in a procedural language and therefore simply be embedded into existing process control systems.