一种集成学习的高灵敏度动态GNSS欺骗检测方法
By integrating learning and indirect Kalman filtering techniques, multiple alternative deception detection indicators are constructed and the best indicator is dynamically selected, which solves the problems of noise interference and dynamic deception signal identification in existing technologies, and improves the security and detection accuracy of GNSS systems.
CN120507768BActive Publication Date: 2026-07-17NANKAI UNIV
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANKAI UNIV
- Filing Date
- 2025-03-25
- Publication Date
- 2026-07-17
Smart Images
Figure CN120507768B_ABST
Abstract
本发明涉及欺骗干扰检测技术领域，具体公开了一种集成学习的高灵敏度动态GNSS欺骗检测方法，包括：获取多相关器阵列的输出信号，计算得到同相信道多相关器SQM指标和正交信道多相关器SQM指标；采用间接卡尔曼滤波进行处理，得到平滑后的同相信道多相关器SQM指标和平滑后的正交信道多相关器SQM指标，以及稳态估计误差方差；构建备选欺骗检测指标；通过多个机器学习模型，选择备选欺骗检测指标中的一个作为欺骗检测指标；根据其与对应的阈值的比较结果，判定是否发生了欺骗攻击。本发明通过集成学习实现动态的检测指标选择，以应对不同欺骗攻击条件，能够显著提升对欺骗攻击的检测效能。
Need to check novelty before this filing date? Find Prior Art