Threat Estimation of Aerial Target Based on Extreme Learning Machine

A new threat estimation method based on the extreme learning machine (ELM) neural network is proposed against the shortcomings of the existing methods that are difficult to satisfy both accuracy and real-time performance. The air combat data is selected from the air combat maneuvering instrument (ACMI), and the threat estimation sample data is established based on the threat index method. The threat estimation model based on the ELM neural network is constructed, and the accuracy and computational complexity of the algorithm are analyzed by simulation. The results show that the method not only has high accuracy, but also has good efficiency, and can accurately and quickly perform target threat estimation in air combat.