Automatic Detection of Galileo Satellite Oscillator Anomaly by Using a Machine Learning Algorithm

Kahn-Bao Wu, Yunxiang Liu and Y. Jade Morton

Abstract: This paper presents a radial basis function (RBF) support vector machine (SVM)-based machine learning (ML) algorithm to automatically detect Galileo satellite oscillator anomalies by using triple-frequency carrier phase measurements. The algorithm is capable of distinguishing Galileo satellite oscillator anomaly from ionospheric scintillation, receiver oscillator anomaly, and other phase disturbances. The results show that RBF SVM reaches a ????1 score of 94%. In addition, the trained ML model is used to automatically detect Galileo satellite oscillator anomalies on data collected from Greenland, South Korea, Alaska and Hawaii in 2018 to 2019. The preliminary detection results show that on average 0.6 oscillator anomaly events are detected per day.
Published in: Proceedings of the 34th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2021)
September 20 - 24, 2021
Union Station Hotel
St. Louis, Missouri
Pages: 2925 - 2939
Cite this article: Wu, Kahn-Bao, Liu, Yunxiang, Morton, Y. Jade, "Automatic Detection of Galileo Satellite Oscillator Anomaly by Using a Machine Learning Algorithm," Proceedings of the 34th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2021), St. Louis, Missouri, September 2021, pp. 2925-2939.
https://doi.org/10.33012/2021.17992
Full Paper: ION Members/Non-Members: 1 Download Credit
Sign In