基于PNN的北斗转发式欺骗干扰信号检测方法

BDS against repeater deception jamming detection algorithm based on PNN

针对载波相位差分检测技术中存在的模糊度解算复杂和虚警率高的问题,提出基于概率神经网络(PNN)的北斗转发式欺骗信号检测方法。在推导不同条件下载波相位双差检测方法的基础上,采取故障诊断的思想,通过构建PNN模型,利用真实信号双差观测值随时间变化的一致性特点,实现对欺骗信号的分类检测;然后根据不同星间差分组合的检测结果,进一步确认受欺骗干扰的卫星信号。实测数据结果表明,所提方法的检测正确率在样本历元数为100时,能够达到98.51%,检测耗时不超过0.1 s,不仅满足对转发式欺骗干扰实时检测的要求,还可对不同类型组合的欺骗信号进行有效识别。

Aiming at the problems of complex ambiguity resolution and high false alarm rate in carrier phase differential detection technology,a BDS forwarding spoofing signal detection method based on probabilistic neural network(PNN)is proposed.On the basis of deriving download wave phase double-difference detection methods under different conditions,the idea of fault diagnosis is adopted.By constructing a PNN model,the consistent characteristics of real signal double-difference observations over time is utilized to achieve the classification and detection of spoofed signals.Then according to the detection results of different inter-satellite difference combinations,the deception interfering satellite signals are further confirmed.The measured data results show that when the number of samples is 100,the detection accuracy of the proposed method can reach 98.51%,and the detection time is less than 0.1 s,which not only meets the requirements for real-time detection of forwarding spoofing interference,but also effectively recognizes different types of combinations of spoofing signals.