Health management based on fusion prognostics for avionics systems

Abstract

Health management permits the reliability of a system and plays a increasingly important role for achieving efficient system-level maintenance. It has been used for remaining useful life (RUL) prognostics of electronics-rich system including avionics. Prognostics and health management (PHM) have become highly desirable to provide avionics with system level health management. This paper presents a health management and fusion prognostic model for avionics system, combining three baseline prognostic approaches that are model-based, data-driven and knowledge-based approaches, and integrates merits as well as eliminates some limitations of each single approach to achieve fusion prognostics and improved prognostic performance of RUL estimation. A fusion model built upon an optimal linear combination forecast model is then utilized to fuse single prognostic algorithm representing the three baseline approaches correspondingly, and the presented case study shows that the fusion prognostics can provide RUL estimation more accurate and more robust than either algorithm alone.

PHM-Oriented Integrated Fusion Prognostics for Aircraft Engines Based on Sensor Data

“…Moreover, both the experiencebased and data-driven approaches while having some strengths also have some limitations, so neither of these two is able to solve all PHM-oriented aircraft engine prognostics problems. To obtain more accurate and reasonable results, fusion prognostics has been introduced in recent research [11], [12], [19]. Most of this research involves a fusion of the model-based and data-driven prognostics approaches.…”

“…Therefore, it is not surprising that finding solutions to aircraft engine prognostics problems is a very active research area. In general, research in this field can be classified into three major categories; modelbased prognostics approaches, experience-based prognostics approaches and data-driven prognostics approaches [11], [12]. Usually the model-based approach makes use of mathematical models for the monitored system, but is difficult to model for a complex system (e.g.…”

A review on prognostics and health monitoring of proton exchange membrane fuel cell

“…Therefore, the accuracy of the fusion approach should be higher than both model and data driven approaches when used individually [26], although for a real-time analysis it may not be suitable due to 215 the significant computational resources required. The fusion approach has been reported to be used in many applications before [26,64,65,66,67,68,69].…”

Entropy-based sensor selection for condition monitoring and prognostics of aircraft engine

“…In general, PHM methods can be classified into three major categories: model-based method, experience-based method, and data-driven method [7]. The model-based method is applicable for the system which can be represented by exact model.…”