Multi-objective Bayesian Optimal Design for Accelerated Degradation Testing

Xiao-Yang Li ()
Additional contact information
Xiao-Yang Li: Beihang University

A chapter in Multicriteria and Optimization Models for Risk, Reliability, and Maintenance Decision Analysis, 2022, pp 321-344 from Springer

Abstract: Abstract Accelerated degradation testing (ADT) can be regarded as a scientific experimental method, which aims to recognize a performance degradation law under the influence of uncertainties by using an experimental way. How to control the uncertainties embedded in an ADT to better recognize a degradation law is one of the core tasks of an ADT. Actually, there are two kinds of uncertainties in an ADT: (i) the inherent uncertainties, which come from the unit-to-unit variation and the errors of measurement instruments and testing equipment, and (ii) the model selection uncertainties, which are due to the accelerated degradation model assumptions and the testing objective selections. In this chapter, the methodology of multi-objective Bayesian optimal design for ADT is proposed to handle these uncertainties. The objectives of the proposed optimization model consist of maximizing the KL divergence, minimizing the quadratic loss function of the q-quantile lifetime at usage condition and minimizing the test cost. Moreover, the data envelopment analysis (DEA) is further used to prune the Pareto solutions so as to find out the plan with the highest relative efficiency. Therefore, the inherent uncertainties and the model selection uncertainties can be well controlled.

Keywords: Accelerated degradation testing; Multi-objective Bayesian optimal design; Data envelopment analysis (DEA); Control of uncertainty; Inverse Gaussian process (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:isochp:978-3-030-89647-8_15

Ordering information: This item can be ordered from
http://www.springer.com/9783030896478

DOI: 10.1007/978-3-030-89647-8_15

Access Statistics for this chapter

More chapters in International Series in Operations Research & Management Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().