Theory for Optimal Test Plans for the Random Fatigue-Limit Model
Author: Pascual F.G.1
Source: Technometrics, Volume 45, Number 2, 1 May 2003 , pp. 130-141(12)
Publisher: American Statistical Association
- Free Content
- New Content
- Subscribed Content
- Free Trial Content
Abstract:
This article presents methodology for planning life tests based on the random fatigue-limit model (RFLM). The RFLM describes the relationship between fatigue life and the applied load in the presence of fatigue limits. A standardization of the RFLM is presented, and corresponding expressions for the elements of the Fisher information matrix are given. Different test plan criteria that express various objectives that the practitioner may have in conducting experiments under the RFLM are discussed. These criteria include estimation of life quantiles, estimation of stress/strain levels that yield a specific life quantile, estimation of fatigue-limit quantiles, and D and Ds optimality. Equivalence theorems used to verify optimality of test plans are also presented. The methods are sufficiently general so they can be applied to criteria based on any function of the model parameters. They are demonstrated using a nickel-base superalloy experiment.Keywords: D OPTIMALITY; EQUIVALENCE THEOREM; FATIGUE TESTING; FISHER INFORMATION; MATRIX; HIGH-CYCLE FATIGUE; MINIMUM ASYMPTOTIC VARIANCE; RIGHT CENSORING
Document Type: Research article
DOI: 10.1198/004017003188618760
Affiliations: 1: Department of Mathematics and Department of Statistics Washington State University Pullman, WA
- Free Content
- New Content
- Subscribed Content
- Free Trial Content
Click here for Page Help