Open AccessReliability Analysis of Dependent Systems using Copula Bayesian Networks: A Case Study
Author(s) -
Xie Guo-Feng,
Liudong Xing,
Faisal Khan,
Lei He
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1043/3/032034
Subject(s) - copula (linguistics) , bayesian network , computer science , dependence analysis , bayesian probability , reliability engineering , reliability (semiconductor) , data mining , machine learning , econometrics , artificial intelligence , mathematics , engineering , power (physics) , physics , quantum mechanics , parallel computing
The Bayesian Network (BN) is a technique that utilizes updating, adapting and discrete-time-based analysis properties for system reliability analysis. Although the BN is a powerful technique, it still faces the challenge of modelling non-linear complex correlations of process components. This paper presents a Copula Bayesian Network (CBN) model to address challenge of modeling non-linear relationships. The superiority of the CBN model lies in integrating the advantage of Copula functions in modelling complex dependent structures with the cause-effect relationship reasoning of process variables using BN. Application of the CBN model is illustrated through a detailed reliability analysis of an example mud pump system. The results reveal the influence of different types of Copula functions and different parameters on the system reliability.