In predicting the reliability and failure of components, classical methods are often used by determining the distribution between failure times. Sometimes, the determination of this distribution does not always match the data pattern that is owned because of the limited data records and the many types of distribution that must be chosen. In addition, how much influence the time series has on components cannot be clearly analyzed. Therefore, in this study a prediction will be carried out by combining classical methods with machine learning, namely Support Vector Regression (SVR) and Least Square Support Vector Regression (LSSVR). Both methods are considered capable of improving the prediction accuracy of a series of data. The results showed that the classical combined method with LSSVR had better accuracy than SVR.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.