A new universal multi-stress acceleration model and multi-parameter estimation method based on particle swarm optimization

Yao Liu, Yashun Wang, Zhengwei Fan, Xun Chen, Chunhua Zhang and Yuanyuan Tan

Journal of Risk and Reliability, 2020, vol. 234, issue 6, 764-778

Abstract: High reliability and long-lifetime products usually work in multi-stress environment such as temperature, humidity, electricity, and vibration. How to evaluate the reliability of the product under multi-stress condition is an urgent problem to ensure the safe and reliable operation of the product. Accelerated test provides an efficient and feasible way; however, the existing acceleration models have some shortcomings, such as less stress type, neglecting the stress coupling, and multi-parameter estimation difficulties. Therefore, in this article, first, a new universal multi-stress acceleration model is derived based on the classical Arrhenius model. Second, a multi-parameter estimation method for multi-stress model is proposed by combining particle swarm optimization and maximum likelihood estimation. Six simulation cases are used to verify the effectiveness of the proposed multi-parameter estimation method. The results of Case 1 to Case 3 show that the maximum mean square error of five parameters in the multi-stress model without considering stress coupling is 3.71%. The results of Case 4 to Case 6 show that the maximum mean square error of nine parameters in the multi-stress model considering stress coupling is 7.69%. Finally, an application example is performed to investigate the performance of the universal multi-stress acceleration model and multi-parameter estimation method.

Keywords: Multi-stress; accelerated model; multi-parameter estimation method; stress coupling; particle swarm optimization; maximum likelihood estimation (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
https://journals.sagepub.com/doi/10.1177/1748006X20918793 (text/html)

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:sae:risrel:v:234:y:2020:i:6:p:764-778

DOI: 10.1177/1748006X20918793

Access Statistics for this article

More articles in Journal of Risk and Reliability
Bibliographic data for series maintained by SAGE Publications ().