DocumentCode :
1779016
Title :
Constructing Bayesian Network by Integrating FMEA with FTA
Author :
Dezhong Ma ; Zhen Zhou ; Yongqing Jiang ; Wenfei Ding
Author_Institution :
Coll. of Meas.-control Technol. & Commun. Eng., Harbin Univ. of Sci. & Technol., Harbin, China
fYear :
2014
fDate :
18-20 Sept. 2014
Firstpage :
696
Lastpage :
700
Abstract :
Bayesian Network has an advantage in dealing with uncertainty. But It is difficult to construct a scientific and rational Bayesian Network model in practice application. In order to solve this problem, a novel method for constructing Bayesian Network by integrating Failure Mode and Effect Analysis (FMEA) with Fault Tree Analysis (FTA) was proposed. Firstly, the structure matrix representations of FMEA, FTA and Bayesian Network were shown and a structure matrix integration algorithm was explained. Then, an approach for constructing Bayesian Network by obtaining information on node, structure and parameter from FMEA and FTA based on structure matrix was put forward. Finally, in order to verify the feasibility of the method, an illustrative example was given. This method can simplify the modeling process and improve the modeling efficiency for constructing Bayesian Network and promote the application of Bayesian Network in the system reliability and safety analysis.
Keywords :
belief networks; failure analysis; matrix algebra; reliability theory; FMEA; FTA; failure mode and effect analysis; fault tree analysis; rational Bayesian network model; safety analysis; structure matrix integration algorithm; structure matrix representations; system reliability; Analytical models; Bayes methods; Computer network reliability; Fault trees; Reliability; Safety; Uncertainty; Bayesian Network; Failure Mode and Effect Analysis (FMEA); Fault Tree Analysis (FTA); Reliability; Structure Matrix;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Instrumentation and Measurement, Computer, Communication and Control (IMCCC), 2014 Fourth International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4799-6574-8
Type :
conf
DOI :
10.1109/IMCCC.2014.148
Filename :
6995118
Link To Document :
بازگشت