Cube Satellite Failure Detection and Recovery Using Optimized Support Vector Machine

Failure detection and recovery is one of the important operations of the health monitoring management system which plays a relevant role for keeping the reliability and availability of the failed sensor over an on-orbit system whole lifetime mission especially where the maintenance may be impossible. In this paper we have implemented Grey Wolf Optimization (GWO) for optimizing Support Vector Machines (SVM) in terms of recovering the detected failure of the failed sensor. The performance of the proposed model with GWO is compared against to four swarm algorithms; Ant Lion Optimizer (ALO), Dragonfly Algorithm (DA), Moth Flame Optimizer (MFO) and Whale Optimizer Algorithm (WOA), four different evaluation aspects are used in this comparison; failure recovering accuracy, stability, convergence and computational time. The experiment is implemented using cube satellite telemetry data, the experimental results demonstrate that the optimization of SVM using GWO (SVM-GWO) model can be regarded as a promising success for satellite failure detection and recovery.