Case-Based Expert Controller for Combustion Control of Blast Furnace Stoves

Usually said expert controller takes RBR (rule-based reasoning) as its reasoning methodology. For the last few years, AI offers with cased-based reasoning (CBR) a powerful methodology, which has already proved its potentials in different industrial applications. However the related applications up to now are mainly focused on non real-time targets. In our work, CBR methodology is introduced into real-time expert controller as its reasoning methodology, thus expanding expert controller family to form a novel category, which can be called case-based expert controller (CBEC) to distinguish from the traditional Rule-Based one. The main advantage of CBEC is that it can overcome the obstacle or bottle neck for getting knowledge while building the knowledge base of a rule-based expert controller. CBEC has been put into operation for combustion control of blast furnace stoves in some in-situ applications. It is shown with the applications that CBEC may be an effective tool for dealing with the control problems of complicated industrial processes.