Radar track prediction method based on BP neural network

• Main Authors: Li Song, Wang Shengli, Xie Dingbao
• Format: Article
• Language: English
• Published: Wiley 2019-09-01
• Series: The Journal of Engineering
• Subjects: neural nets; backpropagation; radar tracking; target tracking; radar track prediction method; bp neural network; complex electromagnetic environment; backpropagation neural network; track prediction experiment; radar target tracking; track prediction accuracy; manoeuvring target track uncertainty
• Online Access: https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0655

Taking into account the complex electromagnetic environment in which the radar target is located, it is difficult for the traditional track prediction method to adapt for the high complexity, randomness, and uncertainty of the manoeuvring target track. This study proposes a radar track prediction method based on backpropagation (BP) neural network. According to the historical track of the radar target, this method uses BP neural network to model its movement law and obtain the target's predicted track. Finally, the track prediction experiment was conducted with measured data and compared with the Kalman filter track. The results show that the proposed method has higher track prediction accuracy and can be used for radar track prediction.