Aviation Surveillance Information Fusion Based on Multi Neural Network
Zhanchun Gao, Meng Zhiyuan · 2020
This paper introduces an aviation surveillance information fusion method based on multi neural networks. With the rapid growth of the number of civil and military aircraft, the air traffic is more and more busy. In order to ensure the flight safety of the aircraft, the application of the aviation surveillance information processing system is indispensable. The aviation surveillance information fusion technology in the system is the key to obtain the accurate information of the flight target position. As the traditional method of aviation surveillance information fusion method, the Kalman filter has the characteristics that it does not need to retain the past measurement data, but only needs to be recursive according to the state equation. But the Kalman filter has the problem of high requirements for model error and calculation accuracy, and it requires a large number of professionals to conduct time-consuming parameter adjustment, which consumes a lot of human and material resources. Thus, it is necessary to find an efficient and accurate information fusion method of aviation surveillance. The multi neural network proposed in this paper can overcome the above shortcomings of the Kalman filter. Furthermore, the multi neural network can achieve better than single neural network, which can predict the position of the aircraft more accurately.