一种基于近端策略优化的假目标欺骗干扰抑制方法
By using a near-end policy optimization approach and employing reinforcement learning algorithms and shearing functions, the optimal anti-jamming strategy for the radar is generated, solving the problem of radar detection performance degradation and achieving efficient suppression of false target deception interference while maintaining detection performance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-05
- Publication Date
- 2026-07-17
AI Technical Summary
When faced with deceptive interference from false targets, the radar's detection performance decreases due to the increase in the number of orthogonal waveforms, and traditional methods struggle to reduce the number of orthogonal waveforms while maintaining anti-jamming capabilities.
A near-end policy optimization approach is adopted, which uses reinforcement learning algorithm to construct a reward model for radar anti-jamming effect and number of transmitted waveform types. The training process is stabilized by combining a shearing function, and the optimal policy is generated by the PPO algorithm to select the transmitted waveform.
This approach achieves the goal of maintaining good radar detection performance while suppressing deceptive interference from false targets, and effectively reduces the number of orthogonal waveforms, thereby improving the radar's anti-jamming capability.
Smart Images
Figure CN118859130B_ABST