A Two-Stage Layered Mixture Experiment Design for a Nuclear Waste Glass Application-Part 1
A layered experimental design involving mixture variables was generated to support developing property-composition models for high-level waste (HLW) glasses. The design was generated in two stages, each having unique characteristics. Each stage used a layered design having an outer layer, an inner layer, a center point, and some replicates. The layers were defined by single- and multi-variable constraints. The first stage involved 15 glass components treated as mixture variables. For each layer, vertices were generated and optimal design software was used to select alternative subsets of vertices and calculate design optimality measures. Two partial quadratic mixture models, containing 25 terms for the outer layer and 30 terms for the inner layer, were the basis for the optimal design calculations. Distributions of predicted glass property values were plotted and evaluated for the alternative subsets of vertices. Based on the optimality measures and the predicted property distributions, a ''best'' subset of vertices was selected for each layer to form a layered design for the first stage. The design for the second stage was selected to augment the first-stage design. The discussion of the second-stage design begins in this Part 1 and is continued in Part 2 (Cooley and Piepel, 2003b).
- Research Organization:
- Pacific Northwest National Lab., Richland, WA (US)
- Sponsoring Organization:
- US Department of Energy (US)
- DOE Contract Number:
- AC05-76RL01830
- OSTI ID:
- 15016574
- Report Number(s):
- PNWD-SA-6275; TRN: US0502593
- Resource Relation:
- Conference: 2003 ASA Proceedings. Papers presented at the Annual Meeting of the American Statistical Association. Joint Statistical Meetings, San Francisco, CA (US), 08/03/2003--08/07/2003; Other Information: PBD: 1 Dec 2003
- Country of Publication:
- United States
- Language:
- English
Similar Records
Construction of a 21-Component Layered Mixture Experiment Design Using a New Mixture Coordinate-Exchange Algorithm
Construction of a 21-Component Layered Mixture Experiment Design