ISHM-based intelligent fusion prognostics for space avionics

The remaining useful life (RUL) of a system is defined as the length of time from when an anomaly or failure symptom occurs to the time when the component or module cannot be used. Prognostics plays a crucial role in integrated system health management (ISHM) for space avionics. In this paper, a new RUL definition is given, and RUL prognostics based on ISHM for space avionics, a complex electronics system composed of many components and modules, is focused on. An intelligent fusion prognostics approach is proposed, the GASVM, which is based on support vector machine theory and the genetic algorithm. The fusion prognostics approach incorporates the advantages of these two methods. Finally, a numerical example is given to show the efficiency of the proposed method. Compared to standard Support Vector Machines (SVM) and Artificial Neural Networks (ANN), the proposed approach has a better predictive performance.