Bayesian assurance tests for degradation data. (5th October 2017)

• Record Type: Journal Article
• Authors: Weaver, B.P.; Hamada, M.S.; Wilson, A.G.; Bakerman, J.E.
• Is Part Of: Quality and reliability engineering international. Volume 33:Number 8(2017:Dec.)
• Page Start: 2699
• Page End: 2709
• Publication Date: 2017-10-05
• Subjects: Bayesian inference -- consumer's and producer's risks -- Markov chain Monte Carlo -- Monte Carlo integration -- reliability; Reliability (Engineering) -- Periodicals; Quality control -- Periodicals; High technology -- Periodicals; 620.00452
• DOI: 10.1002/qre.2228
• Languages: English
• ISSNs: 0748-8017

Abstract

Abstract: Assurance test plans are chosen to manage consumer's and producer's risks. We develop methods for planning Bayesian assurance tests for degradation data, ie, on the basis of the degradation data collected in the test, a decision is made whether to accept or reject a product. Bayesian assurance tests incorporate prior knowledge in the planning stage and use this information to evaluate posterior consumer's and producer's risks. We consider prior knowledge that takes the form of related degradation data. Assurance test plans are then found that meet the specified requirements for consumer's and producer's risks. We illustrate the planning of such assurance tests with an example involving printhead migration data. We also investigate the impact of measurement error on these assurance test plans.