A BDS/LTE-R Enhanced Data Fusion Positioning Algorithm Based on Deep Learning

Miao Luo; Jianwu Dang; Zhanjun Hao; Zhenhai Zhang

doi:10.6180/jase.202208_25(4).0002

A BDS/LTE-R Enhanced Data Fusion Positioning Algorithm Based on Deep Learning

Miao Luo This email address is being protected from spambots. You need JavaScript enabled to view it.^1,2, Jianwu Dang¹, Zhanjun Hao^3,4, and Zhenhai Zhang¹

¹College of Automatic & Electrical Engineering, Lanzhou Jiaotong University Lanzhou China
²College of Railway Technology, Lanzhou Jiaotong University Lanzhou China
³College of Computer Science and Engineering, Northwest Normal University Lanzhou China
⁴Gansu Province Internet of Things Engineering Research Center, Northwest Normal University, Lanzhou China

Received: July 11, 2021
Accepted: September 2, 2021
Publication Date: October 27, 2021

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202208_25(4).0002

ABSTRACT

Integrated positioning methods in the high-velocity train control system require auxiliary equipment leading to more construction and maintenance costs. This paper proposes a BDS/LTE-R (Beidou Navigation Satellite System/Long Term Evolution-Railway) integrated positioning system based on deep learning and establishes a 7L-CNNSeven-layer convolutional neural network) enhanced model of BDS/LTE-R data fusion positioning. Firstly, the positioning principles of the BDS and LTE-R system are analyzed to construct a data space secondorder autocorrelation matrix of the results from each single positioning system, which serves as the input of the 7L-CNN model. The positioning data are output after the depth feature extraction and feature fusion. In a test based on field data, the 7L-CNN model obtains fusion results with the second-order autocorrelation matrix of positioning data space as the input. Compared with the results obtained from the earlyfusion algorithm and CNN (convolutional neural network) fusion positioning model with the input of the original positioning data, the 7L-CNN enhanced algorithm can bring better convergence accuracy for both solving velocity and positioning results according to the velocity and position errors in the east and north directions. When a satellite is out of the lock, the 7L-CNN algorithm also has a good correction effect on the single LTE-R positioning, which can meet the requirements for high-precision and continuous real-time positioning of a train.

Keywords: traffic information engineering and control; Integrated train positioning; deep learning; enhanced data fusion positioning; positioning accuracy

REFERENCES

[1] G. S. Mi, M. Luo, and Y. X. Niu, (2015) “Application of CPSO-BP neural network algorithm to city tram positioning" Tiedao Xuebao/Journal of the China Railway Society 37(6): 67–72. DOI: 10.3969/j.issn.1001-8360.2015.06.010.
[2] C. Gu, S. Wang, and S. Shen, (2020) “Theoretical research on combined speed measurement and positioning of maglev train based on GNSS and INS" Journal of Railway Science and Engineering 17(11): 2756–2766. DOI: 10.19713.
[3] G. Chen, H. Liu, Z. Wei, and L. Zhang, (2020) “Research on RTK-GPS/INS-based Train Combination Positioning Method" Tiedao Xuebao/Journal of the China Railway Society 42(10): 67–75. DOI: 10.3969/j.issn.1001-8360.2020.10.010.
[4] S.-g. Wei, C. Xie, and W. Jiang, (2020) “Optimization Method for Integrated Train Positioning Accuracy Based on IMU Calibration Compensation" Tiedao Xuebao/Journal of the China Railway Society 42(2): 57–64. DOI: 10.3969/j.issn.100-8360.2020.02.008.
[5] C. D. Zhang, Z. Wang, and S. Jin, (2021) “Highprecision Positioning Method Based on SINS/RFID of Trains in Tunnel" Journal of Beijing University of Aeronautics and Astronautics:
[6] C. Liu, S. Cheng, and K. Li, (2020) “Position and Speed Measuring Method of Maglev Train Based on Federal Kalman Filter and Information Fusion" Journal of Physics: Conference Series 1621(1): 012067. DOI: 10.1088/1742-6596/1621/1/012067.
[7] D. Li, X. Jia, and J. Zhao, (2020) “A Novel Hybrid Fusion Algorithm for Low-Cost GPS/INS Integrated Navigation System during GPS Outages" IEEE Access 8: 53984–53996. DOI: 10.1109/ACCESS.2020.2981015.
[8] C. R. Li, J. L. Xie, W. Hu, and L. X. Du, (2015) “Researchon train positioning method based on LTE-R" Tiedao Xuebao/Journal of the China Railway Society 37(7): 15–19. DOI: 10.3969/j.issn.1001-8361.2015.07.003.
[9] M. Luo. “Research on train fingerprint positioning based on LTE-R signal strength”. In: IOP Conference Series: Materials Science and Engineering, Hangzhou, China, 892. 1. 2020, 1–8. DOI: 10.1088/1757- 899X/892/1/012044.
[10] R. Adanur, Y. Yesilyurt, C. Sisman, S. Sagir, and I. Kaya. “Deep Learning for Audio Signal Source Positioning Using Microphone Array”. In: Proceedings - 2019 7th International Conference on Digital Information Processing and Communications, ICDIPC 2019, Avrasya University, Trabzon, Turkey, 2019, 18–22. DOI: 10.1109/ICDIPC.2019.8723738.
[11] H. Niu, Z. Gong, E. Ozanich, P. Gerstoft, H. Wang, and Z. Li, (2019) “Deep-learning source localization using multi-frequency magnitude-only data" The Journal of the Acoustical Society of America 146(1): 211–222.
[12] Y. Wang and K. C. Ho, (2018) “Unified Near-Field and Far-Field Localization for AOA and Hybrid AOA-TDOA Positionings" IEEE Transactions on Wireless Communications 17(2): 1242–1254. DOI: 10.1109/TWC. 2017.2777457.
[13] J. Yin, Q.Wan, S. Yang, and K. C. Ho, (2016) “A simple and accurate TDOA-AOA localization method using two stations" IEEE Signal Processing Letters 23(1): 144–148. DOI: 10.1109/LSP.2015.2505138.
[14] T. Gustafsson and C. S. Mac Innés, (2000) “A class of subspace tracking algorithms based on approximation of the noise-subspace" IEEE Transactions on Signal Processing 48(11): 3231–3235. DOI: 10.1109/78.875479.
[15] Z. Sun, L. Xue, Y. Xu, and Z. Wang, (2012) “Overview of deep learning" Application Research of Computers 29(8): 2806–2810.
[16] S.W. Zhang, X. Zhou, and B. Li, (2021) “Holographic Information Extraction Method of Part Machining Features Based on Image Deep Learning" China Mechanical Engineering: Online First.
[17] J. M. Cheng. “Research and Simulation of Satellite Positioning Error Compensation Technology Based on Convolution Neural Network". (phdthesis). Beijing University of Posts and Telecommunications, 2018.