TY -的A2 Cervone安吉洛盟——刘,Di盟——夏,清远盟——江Changhui AU -王,Chaochen AU - Bo,媒体PY - 2020 DA - 2020/08/12 TI - LSTM-RNN-Assisted向量跟踪回路的信号中断连接SP - 2975489六世- 2020 AB -全球导航卫星系统(GNSS)一直是最受欢迎的工具提供定位、导航和定时(PNT)信息。已经开发了一些方法提高GNSS信号具有挑战性的环境中性能(城市峡谷,茂密的枝叶,信号阻塞,多路径,和none-line-of-sight信号)。矢量跟踪循环(VTL)被认为是最有前途的和潜在的在这些技术中,由于VTL意识到渠道之间的相互协助。然而,瞬时信号影响的跟踪通道堵塞部分VTL操作和导航解决方案的评估。此外,可用卫星使用不足将导致错误随时间发散的快速导航解决方案。短期或临时信号阻塞是常见的在城市地区。旨在提高VTL的性能在信号中断,本文深入学习方法用于协助VTL导航解决方案的评估;更具体地说,很长一段短期Memory-Recurrent神经网络(LSTM-RNN)是用来援助VTL导航滤波器(导航滤波器通常是一个卡尔曼滤波器)。LSTM-RNN获得性能优良的时间序列数据处理;因此,本文LSTM-RNN来预测导航滤波器创新序列值在信号中断,然后,预测创新的值是用来帮助导航滤波器估计导航解决方案。 The LSTM-RNN was well trained while the signal was normal, and the past innovative sequence was employed as the input of the LSTM-RNN. A simulation was designed and conducted based on an open-source Matlab GNSS software receiver; a dynamic trajectory with several temporary signal outages was designed for testing the proposed method. Compared with the conventional VTL, the LSTM-RNN-assisted VTL could keep the horizontal positioning errors within 50 meters during a signal outage. Also, conventional Support Vector Machine (SVM) and radial basis function neural network (RBF-NN) were compared with the LSTM-RNN method; LSTM-RNN-assisted VTL could maintain the positioning errors less than 20 meters during the outages, which demonstrated LSTM-RNN was superior to the SVM and RBF-NN in these applications. SN - 1687-5966 UR - https://doi.org/10.1155/2020/2975489 DO - 10.1155/2020/2975489 JF - International Journal of Aerospace Engineering PB - Hindawi KW - ER -