Knowledge and Control for a Mechanical Design Expert System
Computer - Special issue on expert systems in engineering
PRIDE: An Expert System for the Design of Paper Handling Systems
Computer - Special issue on expert systems in engineering
Intelligent computer-aided engineering
AI Magazine
Geometric reasoning
Knowledge Engineering in Computer-Aided Design: Proceedings of the IFIP WG 5.2 Working Conference on Knowledge Engineering in Computer-Aided Degin, Budapest, Hungary, 17-19 September, 1984
Automated design and sketching of mechanisms based on specified design requirements by employing expert system methodologies
| Hi-index | 0.00 |
Knowledge-based systems have traditionally been implemented in vertical application areas, which are characterized by a deep knowledge in a narrow domain. We developed and fielded a successful knowledge-based tool that is characterized by shallow knowledge of a wide range of cost-estimation problems. Our system is used to estimate piece-part manufacturing costs and has broad knowledge of many commodities and their corresponding manufacturing processes. We believe our design, manufacturability, and cost model (DMCM) system is also unique for the following reasons: First, the system has enabled business process changes, such as allowing cost estimation to be done at an earlier state of the design process. Second, the cost estimate is now continually refined. The cost estimate is updated as newer and better data become available. This process is repeated at all stages of the design. Third, a high level of integration is achieved with existing design information stores, such as a commercial computer-aided design (CAD) system and existing corporate databases. Fourth, a conventional, commercial database is used to provide flexible data storage and a repository for persistent objects. Fifth, accelerated implementation allowed the application to be fielded into an integrated business process. Sixth, simultaneous implementation of multiple cost models maximizes payback in a competitive situation. This chapter describes our experiences in developing DMCM, including the technology used to reason in the design domain, a detailed description of the application, business process results, and long-term plans.