基于时频空间的非模型组合导航滤波方法

Non-model Combined Navigation Filtering Method Based on Time-frequency Space

针对传统的组合导航方法存在建立模型困难和数据维度大等问题,提出了一种利用小波神经网络,直接对解算后的位置速度误差信息进行非线性预测的方法,该方法充分利用小波神经网络强大的时频分析与非线性预测能力,摆脱了数学模型的桎梏,避免模型建立中引入新的误差,并采用多个并行网络对数据进行降维处理,大大降低了计算量;以卡尔曼滤波为参照进行仿真实验,结果表明,该方法能够有效提高组合导航系统的精度与实时性,为组合导航滤波提供一种新的可行路径。

Aiming at the problems of traditional model navigation method,such as difficulty in establishing model and large data dimension,a method of nonlinear prediction based on wavelet neural network and directly solving the position and velocity error information after solving is proposed.The shackles prevent new errors from being introduced in the model establishment,and use multiple parallel networks to reduce the dimensionality of the data,greatly reducing the amount of calculation.The Kalman filter is used as a reference for simulation experiments.The results show that the proposed method can effectively improve the accuracy and real-time performance of the integrated navigation system,and provides a new feasible path for combined navigation filtering.