Search for Author, Title, Keyword
RESEARCH PAPER
Comparative Analysis of Stochastic and Uncertain Process Degradation Modeling Based on RQRL
,
 
,
 
 
 
More details
Hide details
1
Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, China
 
2
University of Chinese Academy of Sciences, Chinese Academy of Sciences, China
 
 
Submission date: 2023-11-23
 
 
Final revision date: 2024-01-18
 
 
Acceptance date: 2024-04-05
 
 
Online publication date: 2024-04-14
 
 
Publication date: 2024-04-14
 
 
Corresponding author
TianJi Zou   

Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, China
 
 
Eksploatacja i Niezawodność – Maintenance and Reliability 2024;26(3):186823
 
HIGHLIGHTS
  • Small sample sizes cause epistemic uncertainties in reliability estimation.
  • Uncertainty theory was utilized to address epistemic uncertainties.
  • The Wiener and Liu process degradation models were proposed.
  • Sensitivities of degradation models for various sample sizes and measurement times were analyzed based on RQRL.
  • Results showed using uncertain process degradation model improved stability of reliability estimation under small-sample conditions.
KEYWORDS
TOPICS
ABSTRACT
Small sample sizes cause epistemic uncertainties in reliability estimation and even result in potential risks in maintenance strategies. To explore the difference between stochastic- and uncertain-process-based degradation modeling in reliability estimation for small samples, this study proposes a comparative analysis methodology based on the range of quantile reliable lifetime (RQRL). First, considering both unit-to-unit variability and epistemic uncertainty, we proposed the Wiener and Liu process degradation models. Second, based on the RQRL, a comparative analysis method of different degradation models for reliability estimation under various sample sizes and measurement times was proposed. Third, based on a case study, the sensitivities of the Wiener and Liu process degradation models for various sample sizes and measurement times were compared and analyzed based on the RQRL. The results demonstrated that using the uncertain process degradation model improved the uniformity and stability of reliability estimation under small-sample conditions.
ACKNOWLEDGEMENTS
This study was supported by the National Natural Science Foundation of China under Grant No. 61703391.
eISSN:2956-3860
ISSN:1507-2711
Journals System - logo
Scroll to top