Improved wavelet neural network based on change rate to predict satellite clock bias

Abstract

To develop a high-accuracy method for predicting SCB based on the analysis of the shortcomings of the wavelet neural network (WNN) model, an improved WNN model to predict SCB is proposed herein. The activation function of the WNN is constructed by combining the advantages of Shannon and Gauss ‘window’ functions to improve the WNN. Finally, the improved WNN model is used to predict SCB. The results show that the proposed model has the highest prediction accuracy, stability, and robustness. Moreover, it effectively predicts long-time SCB data. Therefore, the proposed model can predict SCB with high accuracy.

Keywords:

• Satellite clock bias (SCB)
• Wavelet neural network
• Change rate
• Prediction

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by National Natural Science Foundation of China: [grant number 41574010], [grant number 41904039], and [grant number 41604013].

Notes on contributors

Xu Wang

Xu Wang is a lecturer at Liaoning Vocational College of Ecological Engineering. He received his BS in Civil Engineering from the University of Science and Technology Liaoning in 2007, and he received his MS degrees in Surveying and Mapping Engineering from Liaoning Technical University in 2011. He is now studying for his doctorate degree at the Zhengzhou Institute of Surveying and Mapping (GNSS). His research activities include survey data processing, satellite clock models, and their applications in the Global Navigation Satellite System. He is the author of more than ten journal papers.

Hongzhou Chai

Hongzhou Chai has been a professor since 2008 and a PhD supervisor since 2011 at Information Engineering University, where he received his doctorate in 2006. His research interests include surveying data processing and GNSS positioning and navigation.

Chang Wang

Chang Wang is a lecturer at the University of Science and Technology Liaoning. He received his BS and MS degrees in Surveying and Mapping Engineering from Liaoning Technical University in 2007 and 2010, respectively; he is now studying for a doctorate degree in Zhengzhou Institute of Surveying and Mapping. His current research interest is remote sensing image processing.

Guorui Xiao

Guorui Xiao is currently a PhD candidate at Geodetic Institute, Karlsruhe Institute of Technology (KIT). He received his BSc degree from the School of Geodesy and Geomatics in Wuhan University in 2011. His current research focuses on multi-frequency and multi-constellation GNSS precise positioning and applications.

Yang Chong

Yang Chong is a PhD student at Information Engineering University, where he focuses on Geodesy and Measurement Engineering; his main research interest is geomagnetic assisted navigation.

Xiaoguo Guan

Xiaoguo Guan is a PhD student at Information Engineering University, where he focuses on Geodesy and Measurement Engineering; his main research interest is GNSS (including the BeiDou Navigation Satellite System) precision positioning data processing.