The Survival Analysis for a Predictive Maintenance in Manufacturing.

The Predictive Maintenance (PdM) as a tool for detection future failures in manufacturing has recognized as innovative and effective method. Different approaches for PdM have been developed in order to compromise availability of data and demanding needs for predictions. In this paper the Survival Analysis (SA) method was used for the probability estimation for the machine failure. The paper presents the use of the two most popular SA models Kaplan-Meier non-parametric and Cox proportional hazard models. The first model was used to estimate the probability of machine to survive certain amount of cycles time. The Cox proportional model was used to find out the most significant covariates in the observed data set. The analysis shown that use of SA in the PdM is a challenging task and can be used as additional tool for failure analysis. However, due to its foundation there are several limitations in the application of SA which in most cases are the availability of the right information in the data set.identified