scholarly journals Bayesian assessment of the variability of reliability measures

2006 ◽  
Vol 26 (1) ◽  
pp. 109-127 ◽  
Author(s):  
Enrique López Droguett ◽  
Frank J. Groen ◽  
Ali Mosleh
Keyword(s):  
Failure Rate ◽  
Failure Probability ◽  
Bayesian Updating ◽  
Estimation Procedure ◽  
Population Variability ◽  
Probability Assessment ◽  
Time Data ◽  
Reliability Measures ◽  
Variability Analysis ◽  
Variability Model

Population variability analysis, also known as the first stage in two-stage Bayesian updating, is an estimation procedure for the assessment of the variability of reliability measures among a group of sub-populations of similar systems. The estimated variability distributions are used as prior distributions in system-specific Bayesian updates. In this paper we present a Bayesian approach for population variability analysis involving the use of non-conjugate variability models that works over a continuous, rather than the discretized, variability model parameter space. The cases to be discussed are the ones typically encountered by the reliability practitioner: run-time data for failure rate assessment, demand-based data for failure probability assessment, and expert-based evidence for failure rate and failure probability analysis. We outline the estimation procedure itself as well as its link with conventional Bayesian updating procedures, describe the results generated by the procedures and their behavior under various data conditions, and provide numerical examples.

Failure Probability Assessment of Piping Systems Affected by SCC and Pipe Wall Thinning for LBB Analysis

2011 ◽  
Author(s):  
Hiromasa Chitose ◽  
Hideo Machida ◽  
Itaru Saito
Keyword(s):  
Failure Probability ◽  
Nuclear Power ◽  
Power Plants ◽  
Pipe Wall ◽  
Probability Assessment ◽  
Wall Thinning ◽  
Piping Systems ◽  
Leak Before Break ◽  
Thinning Rate ◽  
Service Inspection

This paper provides failure probability assessment results for piping systems affected by stress corrosion cracking (SCC) and pipe wall thinning in nuclear power plants. On the basis of the results, considerations for applying the leak-before-break (LBB) concept in actual plants are presented. The failure probability for SCC satisfies the target failure probability even if conservative conditions are assumed. Moreover, for pipe wall thinning analysis, pre-service inspection is important for satisfying the target failure probability because the initial wall thickness affects the accuracy of the wall thinning rate. The pipe wall thinning analysis revealed that the failure probability is higher than the target probability if the bending stress in the pipe is large.

Travel Time Reliability Measures Accommodating Scheduling Preferences of Travelers

2019 ◽  
Vol 2673 (4) ◽  
pp. 708-721 ◽  
Author(s):  
Mojtaba Rajabi-Bahaabadi ◽  
Afshin Shariat-Mohaymany ◽  
Shu Yang
Keyword(s):  
Travel Time ◽  
Time Distribution ◽  
Travel Time Reliability ◽  
Time Data ◽  
Reliability Measures ◽  
Time Performance ◽  
Early Arrival ◽  
Travel Time Distribution ◽  
Travel Time Data ◽  
Schedule Adherence

Existing travel time reliability measures fail to accommodate scheduling preferences of travelers and cannot distinguish between the variability associated with early and late arrivals. This study introduces two new travel time reliability measures based on concepts from behavioral economics. The first proposed measure is an indicator of the width of travel time distribution. It considers scheduling preferences of travelers and can distinguish between early arrival and late arrival. The second measure determines the skewness of travel time distribution. To estimate the proposed measures, travel time is modeled by mixture models and closed-form expressions are derived for the expected values of early and late arrivals. In addition, real travel time data from a freeway segment is used to compare the proposed measures with the existing travel time reliability measures. The results suggest that, although there exist significant correlations between travel time reliability measures, travelers’ preferences have considerable effects on the travel time reliability as perceived by them. Furthermore, four measures are developed based on the notions of early and late arrivals to assess the on-time performance (schedule adherence) of transit vehicles at stop level. The results of this study show that the four measures can serve as complementary to the existing on-time performance indices.

Estimation of expected number of accidents and workforce unavailability through Bayesian population variability analysis and Markov-based model

2016 ◽  
Vol 150 ◽  
pp. 136-146 ◽  
Author(s):  
Márcio das Chagas Moura ◽  
Rafael Valença Azevedo ◽  
Enrique López Droguett ◽  
Leandro Rego Chaves ◽  
Isis Didier Lins ◽  
...  
Keyword(s):  
Population Variability ◽  
Expected Number ◽  
Variability Analysis

Reliability Assessment of Software System Using IFS and OWA-Tree Analysis

2020 ◽  
Vol 27 (05) ◽  
pp. 2040013
Author(s):  
Abhishek Tandon ◽  
Neha ◽  
Anu G. Aggarwal ◽  
Ajay Jaiswal
Keyword(s):  
Failure Rate ◽  
Failure Probability ◽  
Intuitionistic Fuzzy Set ◽  
Reliability Assessment ◽  
Weighted Averaging ◽  
Software System ◽  
Tree Analysis ◽  
Software Product ◽  
To Come ◽  
Theory Failure

To address the software design and development, reliability assessment is considered as crucial and most important task. Several studies have been directed towards reliability assessment approaches for obtaining highly reliable software product. In conventional reliability theory, failure probability of any component is assumed as an exact value but in actuality it’s not possible to get failure probability precisely. In this study, we have proposed an approach to assess the reliability of a software system with vague failure rate of the components as the given information might be incomplete or uncertain. It is a bottom–top methodology which includes the combination of intuitionistic fuzzy set (IFS) theory and ordered weighted averaging (OWA) tree analysis. Using IFS, we are able to come over the vagueness in the failure rate data and by using OWA-tree, we incorporate the subjectivity in the opinion of software developers with respect to selection of module. Further, for the illustration of the proposed approach one numerical example has been discussed and software reliability is assessed based upon different orness level.

Sign in / Sign up

Export Citation Format

Share Document