SUMMARY OF THE RECENT DEVELOPED TECHNIQUES FOR MACHINE HEALTH PROGNOSTICS

*Achmad Widodo  -  Department of Mechanical Engineering, Diponegoro University, Indonesia
Wahyu Caesarendra  -  Department of Mechanical Engineering, Diponegoro University, Indonesia
Published: 1 Jan 2014.
Open Access
Citation Format:
Article Info
Section: Articles research
Language: EN
Statistics: 377 502
Abstract
This paper reviews relatively new developed techniques for machine health prognostics system. The prognostics assessment of machines is an important consideration for determining the remaining useful life (RUL) of machine components and prediction of future state of machines. The developed system has employed several approaches of machine health prognostics strategy such as data-driven, physical-based, and probability-based methods. The method of solution implemented artificial intelligence techniques including support vector machine (SVM), relevance vector machine (RVM), Dempster-Shafer theory, decision tree, particle filter, and autoregressive moving average/ generalized autoregressive conditional heteroscedasticity (ARMA/GARCH). Case studies of machine health prognostics are also presented to show the plausibility of the developed systems. Finally, this paper summarizes the research finding and directions of machine health prognostics system.
Keywords: artificial intelligence, machine prognostics, remaining useful life

Article Metrics: