Research on Abnormal Behavior Detection Technology of Launch Vehicle Controlled Network

Launch vehicle network as an extremely important national defense information system, is faced with the threat of information security because of the dynamic detection limitation of the traditional firewall, virus detection software and so on. In this paper, we choose evaluation index and establish the entropy weight combination model based on the exponentially weighted moving-average (EWMA) model and the echo state network (ESN) model, Finally, we select the actual traffic data of the network, verify the effectiveness of the sequential dynamic security detection model, and study the influence of different time window observation scale on anomaly detection.