Abstract
This research intends to augment the validity of simulation models in the most economic way via incorporating dynamic data into the executing model, which then steers the measurement process for selective data update. To this end, we developed four algorithms that are embedded into the simulations, including 1) data filtering algorithm utilizing control charts, 2) preliminary fidelity selection algorithm using the Bayesian belief network, 3) fidelity assignment algorithm considering the currently available computational resources and integer programming, and 4) real-time scheduling algorithm using multi-linear regression. A prototype system was successfully developed for preventive maintenance scheduling for a semiconductor supply chain.
| Original language | English (US) |
|---|---|
| Pages | 110-115 |
| Number of pages | 6 |
| State | Published - 2007 |
| Event | IIE Annual Conference and Expo 2007 - Industrial Engineering's Critical Role in a Flat World - Nashville, TN, United States Duration: May 19 2007 → May 23 2007 |
Other
| Other | IIE Annual Conference and Expo 2007 - Industrial Engineering's Critical Role in a Flat World |
|---|---|
| Country/Territory | United States |
| City | Nashville, TN |
| Period | 5/19/07 → 5/23/07 |
Keywords
- Grid computing
- Maintenance scheduling
- Multi-fidelity simulation
- Supply chain
- Web services
ASJC Scopus subject areas
- Industrial and Manufacturing Engineering