DocumentCode :
2587703
Title :
Probabilistic models to assist maintenance of multiple instruments
Author :
Melendez, Joaquim ; Lopez, Beatriz ; Millán-Ruiz, David
Author_Institution :
Inst. d´´Inf. i Aplicacions, Univ. de Girona, Girona, Spain
fYear :
2009
fDate :
22-25 Sept. 2009
Firstpage :
1
Lastpage :
4
Abstract :
The paper discusses maintenance challenges of organisations with a huge number of devices and proposes the use of probabilistic models to assist monitoring and maintenance planning. The proposal assumes connectivity of instruments to report relevant features for monitoring. Also, the existence of enough historical registers with diagnosed breakdowns is required to make probabilistic models reliable and useful for predictive maintenance strategies based on them. Regular Markov models based on estimated failure and repair rates are proposed to calculate the availability of the instruments and Dynamic Bayesian Networks are proposed to model cause-effect relationships to trigger predictive maintenance services based on the influence between observed features and previously documented diagnostics.
Keywords :
Markov processes; belief networks; cause-effect analysis; maintenance engineering; probability; cause-effect relationship; dynamic Bayesian networks; failure estimation; maintenance planning; monitoring; multiple instruments maintenance; predictive maintenance services; probabilistic models; regular Markov model; repair rate; Bayesian methods; Chemical industry; Condition monitoring; Costs; Electric breakdown; Instruments; Job shop scheduling; Predictive maintenance; Predictive models; Preventive maintenance;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Emerging Technologies & Factory Automation, 2009. ETFA 2009. IEEE Conference on
Conference_Location :
Mallorca
ISSN :
1946-0759
Print_ISBN :
978-1-4244-2727-7
Electronic_ISBN :
1946-0759
Type :
conf
DOI :
10.1109/ETFA.2009.5347263
Filename :
5347263
Link To Document :
بازگشت