A Data-Driven method for estimation Remaining Useful Life (RUL) of turbofan based on multi-sensor information integrations

Abstract

Determination of degradation status and estimating remaining useful life are two main activities in prognostics and health management. These two main activities can be perceived as the problem of multi-sensor data fusion. These sensors contain information including speed, pressure, and temperature. In terms of evidence theory, the information obtained from each of these sensors can be regarded as a part of the evidence and determination of degradation status and estimating remaining useful life based upon this information can be considered as the problem of multi-sensor data fusion. In this article, the Dempster-Shafer theory has been employed as a tool for modeling and multi-sensor data fusion as an indicator of the health status of the turbofan. In this regard, initially, the theory of evidence has been reviewed and then how to model the remaining useful life estimation problem by multi-sensor data fusion within the framework of the concepts of this theory including mass function, focal elements and rules of evidence composition is explained. This paper has introduced a new approach for combining the results of different estimates of remaining useful life through determining the weighs. Furthermore, it has offered two different scenarios to specify the similarity between the system under study and the available evidence. Finally, to appraise the proposed method, the turbofan engines data set (C-MAPSS) has been used as it has been extensively addressed in literature by researchers. According to the results, the proposed method revealed better score and performance compared with other available methods in the literature.