Abstract
This work studies the construction of state cognition and threat cognition models for a single time-sensitive target in an air combat scenario. It uses a bidirectional long short-term memory network model based on an attention mechanism for target state cognition and a subjective-objective weighted combination model for target threat cognition. In the experiment, the data of the simulated scenario was input, and the cognitive accuracy of the state cognition model could reach 80%. Then, the target state cognition results were input into the threat cognition model to participate in the threat cognition process. The cognition results output by the threat cognition model were consistent with the actual situation. Therefore, the target state and threat cognition model proposed in this paper has good performance and can provide support for subsequent combat decision-making and execution.