Prognosis of degradation through a dynamic estimation of Remaining Useful Life

Abstract

All industrial systems and machines are subjected to degradation processes which can be related to the operating conditions. This degradation can cause unwanted stops at any time and major maintenance work sometimes. Prognostic activity is now recognized as a key feature in maintenance strategies, it gives operators a potent tool in decision making by quantifying how much time is left until functionality is lost. The reason is to plan the heavy interventions and to manage the stock of spare parts. In addition, it can be used to improve the characterization of the material proprieties that govern damage propagation for the structure being monitored. The tool for measuring the size of damage and health status in industry is the Remaining Useful Life (RUL), which can be estimated by using four main approaches, namely experience based, model-based, data-driven and hybrid approaches. A new method of prognosis is developed in this paper to improve the accuracy of the system state. This framework of forecasting integrates the model-based information and the hybrid approach, which employs the structured residuals in the first one and the Particle Filter in the second. The performance of the suggested fusion prognostic framework is employed to predict the RUL of battery pack in Hybrid Electric Vehicle (HEV).