Intelligent decision support technologies for design and manufacturing
For many of today`s complex manufacturing processes, there exists a solid body of knowledge that enables direct simulations of such processes yielding predictions about the final product and process characteristics using finite element or finite difference methods. However, the computational complexities of these simulations are such that they do not lend themselves easily to routine and timely use in optimization and control of manufacturing processes. More recently, neural network-based decision support technologies have been developed which hold the promise of bringing the body of analytical and simulation knowledge closer to the design and optimization processes in manufacturing industries. The paper discusses the application of a holistic approach wherein existing finite element, neural-network, and optical metrology methods are combined to develop a real time tool for optimization and control of the sheet metal stamping process. Significant issues in the development of such a tool and results from its application to a deformation process are discussed.
- Research Organization:
- Oak Ridge National Lab., Metals and Ceramics Div., TN (United States)
- Sponsoring Organization:
- USDOE Office of Energy Research, Washington, DC (United States)
- DOE Contract Number:
- AC05-96OR22464
- OSTI ID:
- 634141
- Report Number(s):
- CONF-970767-2; ON: DE97008553; BR: KC0201050; TRN: AHC2DT01%%152
- Resource Relation:
- Conference: Australia-Pacific forum on intelligent processing and manufacturing of materials, Sydney (Australia), 14-16 Jul 1997; Other Information: PBD: Jun 1997
- Country of Publication:
- United States
- Language:
- English
Similar Records
Embedded NERVE system for intelligent manufacturing of multifunctional composites for vehicles (Final Report)
Roll-to-Roll Advanced Materials Manufacturing DOE Laboratory Collaboration (FY2020 Final Report)