A computational system for process design of injection moulding: Combining a blackboard-based expert system and a case-based reasoning approach
UNSPECIFIED. (1998) A computational system for process design of injection moulding: Combining a blackboard-based expert system and a case-based reasoning approach. INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 14 (5). pp. 350-357. ISSN 0268-3768Full text not available from this repository.
Process design of injection moulding involves the selection of the injection moulding machine, mould design, production scheduling, cost estimation, and determination of injection moulding parameters. An expert system approach has been rued to derive the process solution for injection moulding over the past few years. However, this approach is found to be incapable of determining the injection moulding parameters owing to the fragile nature of the knowledge for setting the moulding parameters. In addition, the existing expert systems for process design lack proper architecture for organising heterogeneous knowledge sources. In this paper, the organising of a blackboard-based expert system and a case-based reasoning approach is introduced to eliminate the deficiency of the existing expert-system approach to process design, from which a computational system for the process design of injection moulding, named CSPD, has been developed; CSPD first derives the process solution including the selection of the injection moulding machine and the mould base, tooling cost, processing cost estimation, and production scheduling based on the blackboard-based expert-system approach. It is their followed by the determination of the injection moulding parameters based on the case-based reasoning approach and the previously derived partial solution.
|Item Type:||Journal Article|
|Subjects:||T Technology > TL Motor vehicles. Aeronautics. Astronautics
T Technology > TS Manufactures
|Journal or Publication Title:||INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY|
|Publisher:||SPRINGER-VERLAG LONDON LTD|
|Number of Pages:||8|
|Page Range:||pp. 350-357|
Actions (login required)