Heterogeneous integration architecture for intelligent control systems

Abstract

Better automation is a key to the improvement of industrial competitiveness. However, in most industrial plants, full automation is not possible because intelligent decisions play an essential part in guaranteeing the success of the production process. The currently favoured solution is to rely on human controllers for intelligent input, although instances of installations with AI-based control do exist. Our belief is that process control problems require the cooperative application of more than one AI technique to be successful, and that the lack of a common framework to support AI-based process control designs has contributed to their relative lack of penetration in the industrial market-place. The HINT Project (ESPRIT E6447) has been created to address this perceived need. We are engaged in developing a conceptual framework, a software architecture, and a methodology which will together support the integration of different AI techniques to provide solutions to process control problems that require the kind of intelligent supervision that is currently carried out by human operatives.