GNSS信号丢失会导致GNSS/I NS组合导航系统定位失准甚至失效,而现有辅助模型仍存在不足。针对这一问题,本文提出了一种基于遗传算法(GA)优化E l man神经网络的车辆辅助组合导航算法。首先,使用小波阈值去噪算法降低惯导系统测量数据的噪...GNSS信号丢失会导致GNSS/I NS组合导航系统定位失准甚至失效,而现有辅助模型仍存在不足。针对这一问题,本文提出了一种基于遗传算法(GA)优化E l man神经网络的车辆辅助组合导航算法。首先,使用小波阈值去噪算法降低惯导系统测量数据的噪声,然后再使用GA优化E l man神经网络的权重和结构参数,以提高模型的预测精度和泛化能力。其次,构建基于GA-E l man神经网络的车辆辅助导航模型。该模型将系统分为两种模式,在GNSS信号正常时进入训练模式进行在线训练;当GNSS信号丢失后系统变为纯惯导模式,此时启用训练好的模型接收惯导系统的数据进行实时解算和预测。最后,跑车实验结果表明,与PSO-BPNN辅助模型和E l man辅助模型相比,本文所提出算法的定位精度得到有效提升。展开更多
Railway safety and efficiency increasingly rely on precise train positioning. The integration of the Global Navigation Satellite System (GNSS) into railway control systems aims to reduce dependence on track-side infra...Railway safety and efficiency increasingly rely on precise train positioning. The integration of the Global Navigation Satellite System (GNSS) into railway control systems aims to reduce dependence on track-side infrastructure. While GNSS has significantly improved train localization, challenges such as the susceptibility to jamming remain. To address this, this paper introduces an Inertial Navigation System (INS)-aided train positioning system based on deep integration, exploring its performance through semi-physical experiments and simulations. Experimental results demonstrate that the proposed solution is able to reduce the positioning error by 63.47%, and the velocity error by 58.47% under jamming conditions. The study highlights the potential of deep integration for improving the resilience of GNSS-based train control systems, especially in the face of Radio Frequency (RF) jamming threats.展开更多
文摘GNSS信号丢失会导致GNSS/I NS组合导航系统定位失准甚至失效,而现有辅助模型仍存在不足。针对这一问题,本文提出了一种基于遗传算法(GA)优化E l man神经网络的车辆辅助组合导航算法。首先,使用小波阈值去噪算法降低惯导系统测量数据的噪声,然后再使用GA优化E l man神经网络的权重和结构参数,以提高模型的预测精度和泛化能力。其次,构建基于GA-E l man神经网络的车辆辅助导航模型。该模型将系统分为两种模式,在GNSS信号正常时进入训练模式进行在线训练;当GNSS信号丢失后系统变为纯惯导模式,此时启用训练好的模型接收惯导系统的数据进行实时解算和预测。最后,跑车实验结果表明,与PSO-BPNN辅助模型和E l man辅助模型相比,本文所提出算法的定位精度得到有效提升。
基金supported by the Beijing Natural Science Foundation(4232031)the National Natural Science Foundation of China(T2222015,U2268206).
文摘Railway safety and efficiency increasingly rely on precise train positioning. The integration of the Global Navigation Satellite System (GNSS) into railway control systems aims to reduce dependence on track-side infrastructure. While GNSS has significantly improved train localization, challenges such as the susceptibility to jamming remain. To address this, this paper introduces an Inertial Navigation System (INS)-aided train positioning system based on deep integration, exploring its performance through semi-physical experiments and simulations. Experimental results demonstrate that the proposed solution is able to reduce the positioning error by 63.47%, and the velocity error by 58.47% under jamming conditions. The study highlights the potential of deep integration for improving the resilience of GNSS-based train control systems, especially in the face of Radio Frequency (RF) jamming threats.
