Critics and advisors: Heuristic knowledge and manufacturability
In recent years, much of the progress in Computer-Aided Manufacturing has emphasized the use of simulation, finite-element analysis, and other science-based techniques to plan and evaluate manufacturing processes. These approaches are all based on the idea that we can build sufficiently faithful models of complex manufacturing processes such as machining, welding, and casting. Although there has been considerable progress in this area, it continues to suffer from difficulties: the first of these is that the kind of highly accurate models that this approach requires may take many person months to construct, and the second is the large amount of computing resources needed to run these simulations. Two design advisors, Near Net-Shape Advisor and Design for Machinability Advisor, are being developed to explore the role of heuristic, knowledge-based systems for manufacturing processes, both as an alternative to more analytical techniques, and also in support of these techniques. Currently the advisors are both in the prototype stage. All indications lead to the conclusion that the advisors will be successful and lay the groundwork for additional systems such as these in the future.
- Research Organization:
- Sandia National Labs., Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- AC04-94AL85000
- OSTI ID:
- 243463
- Report Number(s):
- SAND--96-1124C; CONF-9606211--1; ON: DE96010552
- Country of Publication:
- United States
- Language:
- English
Similar Records
Framework for the Evolution of Heuristics in Advanced Manufacturing
Intelligent Weld Manufacturing: Role of Integrated Computational Welding Engineering