Title :
Diagnostic Bayesian Networks auto-construction and diagnostic strategy design based on multi-signal model
Author :
Zhang Shigang ; Hu Zheng
Author_Institution :
Sch. of Mechatron. Eng. & Autom., Nat. Univ. of Defense Technol., Changsha, China
Abstract :
Based on multi-signal model, a novel diagnostic Bayesian networks auto-construction method is proposed in this paper. Combined with information entropy theory, a diagnostic strategy with the ability of sequential fault diagnosis, multi-fault diagnosis and coupling faults diagnosis is designed. In order to deal with uncertain problems and increase diagnostic accuracy, the self adjustment method of diagnostic Bayesian networks (DBN) is also discussed. The effectiveness of the proposed method is verified by the application on a diesel engine test and diagnosis process.
Keywords :
belief networks; condition monitoring; diesel engines; entropy; fault diagnosis; mechanical engineering computing; mechanical testing; autoconstruction; coupling faults diagnosis; diagnostic Bayesian network; diagnostic strategy design; diesel engine test; information entropy theory; multifault diagnosis; multisignal model; self adjustment method; sequential fault diagnosis; Bayesian methods; Condition monitoring; Design automation; Design engineering; Diesel engines; Fault diagnosis; Information entropy; Joining processes; Mechatronics; System testing;
Conference_Titel :
Prognostics and Health Management Conference, 2010. PHM '10.
Conference_Location :
Macao
Print_ISBN :
978-1-4244-4756-5
Electronic_ISBN :
978-1-4244-4758-9
DOI :
10.1109/PHM.2010.5413507
