Abstract
A number of industrial diagnostic systems have achieved an expert system status in that they have achieved expert-level performance. Indications are increasingly positive that these methods will scale up for large expert systems for large industrial plants A variety of general tools for building expert systems are now available, but only a few of them provide all the facilities needed for efficient development of diagnostic systems for large industrial plants. Our tool, called BEST (Blackboard-based Expert System Toolkit), aims to provide all the necessary infrastructure for diagnostic system development, including hybrid knowledge representation language to describe both structural properties (causal relations, inheritance and abstraction hierarchies) and behavioral characteristic (i.e. functionality), compilation techniques to support rapid inference, a wide array of inference control and search strategies, hypothetical and explanatory reasoning, etc. To prove BEST'S suitability for the diagnostic task, we will use a real world application in the aluminum industry. We will also show in this article how a structural model and compiled heuristic knowledge can be combined in a diagnostic task.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: WIT Transactions on Information and Communication Technologies
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.