US 12,481,072 B2
Satellite multipath signal identification method based on temporality and spatial interaction
Kan Xie, Guangzhou (CN); Zhenni Li, Guangzhou (CN); Shengli Xie, Guangzhou (CN); Ci Chen, Guangzhou (CN); Victor Fedorovich Kuzin, Guangzhou (CN); Kungan Zeng, Guangzhou (CN); and Bo Li, Guangzhou (CN)
Assigned to Guangdong University of Technology, Guangzhou (CN)
Filed by GUANGDONG UNIVERSITY OF TECHNOLOGY, Guangzhou (CN)
Filed on Apr. 24, 2023, as Appl. No. 18/305,784.
Claims priority of application No. 202310005077.7 (CN), filed on Jan. 4, 2023.
Prior Publication US 2024/0219578 A1, Jul. 4, 2024
Int. Cl. G01S 19/22 (2010.01); G01S 19/37 (2010.01)
CPC G01S 19/22 (2013.01) [G01S 19/37 (2013.01)] 7 Claims
OG exemplary drawing
 
1. A satellite multipath signal identification method based on temporality and spatial interaction, comprising the following steps:
acquiring satellite data, and dividing the satellite data into a time series dataset and a multi-satellite input dataset;
building a multipath signal identification model, and inputting the time series dataset and the multi-satellite input dataset into the multipath signal identification model;
wherein, the multipath signal identification model comprises a long short-term memory (LSTM) network, a transformer block, and a fully connected network;
performing, by the LSTM network, feature extraction on the time series dataset to acquire a time series feature;
performing, by the transformer block, feature extraction on the multi-satellite input dataset to acquire an environmental characterization; and
fusing, by the fully connected network, the time series feature and the environmental characterization to acquire a multipath signal identification result;
wherein the performing, by the LSTM network, feature extraction on the time series dataset to acquire a time series feature specifically comprises:
inputting the time series dataset into the LSTM network;
removing, by a forget gate, invalid information at a historical time in the time series dataset to acquire a valid time series feature of a satellite;
updating, by an input gate, the valid time series feature of the satellite to acquire processed state information;
encoding, by an output gate, the processed state information to acquire a fixed time series; and
cyclically updating, according to a length of the time series, the time series to acquire the time series feature.