Direct Remaining Useful Life Estimation Based on Support Vector Regression

TLDR

Prognostics and health management focus on estimating remaining useful life, yet traditional approaches rely on multi‑step processes involving health indicators, degradation states, and failure thresholds. This study develops a direct RUL estimation procedure that derives remaining useful life directly from sensor data, bypassing intermediate degradation state or failure threshold estimation. The method employs support vector regression to model a direct relationship between sensor readings and RUL, incorporates offline wrapper variable selection, and is evaluated on the Turbofan dataset. Variable selection improves prediction accuracy and reduces computational time, and experimental results demonstrate that the method performs competitively with existing RUL estimation approaches.

Abstract

Prognostics is a major activity in the field of prognostics and health management. It aims at increasing the reliability and safety of systems while reducing the maintenance cost by providing an estimate of the current health status and remaining useful life (RUL). Classical RUL estimation techniques are usually composed of different steps: estimations of a health indicator, degradation states, a failure threshold, and finally the RUL. In this work, a procedure that is able to estimate the RUL of equipment directly from sensor values without the need for estimating degradation states or a failure threshold is developed. A direct relation between sensor values or health indicators is modeled using a support vector regression. Using this procedure, the RUL can be estimated at any time instant of the degradation process. In addition, an offline wrapper variable selection is applied before training the prediction model. This step has a positive impact on the accuracy of the prediction while reducing the computational time compared to existing indirect RUL prediction methods. To assess the performance of the proposed approach, the Turbofan dataset, widely considered in the literature, is used. Experimental results show that the performance of the proposed method is competitive with other existing approaches.