Pregled bibliografske jedinice broj: 440651
The Failure Rate Modeling using Neural Network
The Failure Rate Modeling using Neural Network // Annals of DAAAM for 2009 & Proceedings of the 20th International DAAAM Symposium / Katalinić Branko (ur.).
Beč: DAAAM International Vienna, 2009. str. 1455-1457 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 440651 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
The Failure Rate Modeling using Neural Network
Autori
Lisjak, Dragutin ; Čala, Ivo ; Štefanić, Nedeljko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Annals of DAAAM for 2009 & Proceedings of the 20th International DAAAM Symposium
/ Katalinić Branko - Beč : DAAAM International Vienna, 2009, 1455-1457
ISBN
978-3-901509-70-4
Skup
DAAAM International Symposium (20 ; 2009)
Mjesto i datum
Beč, Austrija, 25.11.2009. - 28.11.2009
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
failure rate; reliability; modelling; maintenance
Sažetak
The failure rate is one of the most important features in the theory of reliability, defined as the probability of failure in unit time of a device that is still working. This paper presents the possibility of the failure rate modeling using neural networks and comparison with classical models, i.e. modeling functions such as Exponential, Normal or Weibull. The paper is based on real examples shown statistical selection of optimal failure rate function and was proposal model and structure of neural networks as an improvement over the classical models.
Izvorni jezik
Engleski
Znanstvena područja
Strojarstvo
POVEZANOST RADA
Projekti:
120-1201780-1779 - Modeliranje svojstava materijala i parametara procesa (Filetin, Tomislav, MZOS ) ( CroRIS)
Ustanove:
Fakultet strojarstva i brodogradnje, Zagreb
