IMPROVING ARTIFICIAL INTELLIGENCE–BASED METHODS FOR ENHANCING GNSS SIGNAL QUALITY
https://doi.org/10.53360/2788-7995-2026-3(23)-4
Abstract
In a Global Navigation Satellite System (GNSS) communication channel under weak-signal conditions, accurate tracking of the receiver carrier phase and frequency degrades sharply, reducing the stability and overall quality of the navigation solution. The purpose of this work is to improve weak GNSS signal quality, i.e., to increase the sensitivity of the carrier automatic control (tracking) system under low-quality signals and dynamic impacts and to reduce phase/frequency errors. The research object is the baseband I/Q signal at the output of the GNSS receiver correlator and the operation of the carrier tracking loop. The proposed method replaces conventional long coherent integration with block coherent integration (BCI). The total integration time T is preserved, the signal is divided into BBB short blocks, and a matrix Z[k] is formed from the block results Ib , Qb. This matrix preserves amplitude-phase variations and more accurately characterizes the effects of frequency mismatch and dynamics. Next, a neural-network discriminator (CNN+MLP) that processes Z[k] estimates the phase error; the error is then filtered by a PI-type loop filter and, in closed feedback, updates the parameters of the numerically controlled oscillator (NCO). The novelty of the approach lies in representing BCI information as a 2D matrix, replacing the classical phase-locked loop discriminator with a neural discriminator in a closed BCI-NPLL architecture, and providing a quantitative sensitivity justification via the CRLB-phase jitter relationship. Simulation results show that the proposed approach maintains tracking stability in the weaksignal region, the phase error is concentrated around zero, and the frequency estimation accuracy is high (RMSE≈0.084 Hz). Consequently, the method improves weak GNSS signal quality and increases receiver tracking robustness.
About the Authors
N. P. SaparhodzhaevKazakhstan
Nurbek Pazharbekovich Saparkhodzhayev – PhD, associate professor, Chairman of the management board-Rector
Rudny, Kostanay Region, 50 Let Oktyabrya Street, 38
A. Khabay
Kazakhstan
Anar Khabay – PhD, associate professor, Department of Electrical Engineering and Telecommunications of space technolog
050013, Republic of Kazakhstan, Almaty, Satpayev Street, 22
M. Zh. Igen
Kazakhstan
Magzhan Zhaksylykovich Igen – master's student, Department of Electrical Engineering and Telecommunications of space technology
050013, Republic of Kazakhstan, Almaty, Satpayev Street, 22
E. A. Tuleshov
Kazakhstan
Erkebulan Amandykovich Tuleshov – candidate of Technical Sciences, Associate Professor, Department of robotics and technical means of automation, Institute of automation and information technologies
050013, Republic of Kazakhstan, Almaty, Satpayev Street, 22
Republic of Kazakhstan, Almaty, Shevchenko Street, 28
Zh. N. Issabekov
Kazakhstan
Zhanibek Nazarbekovich Issabekov – PhD, Associate Professor, Department of robotics and technical means of automation, Institute of automation and information technologies
050013, Republic of Kazakhstan, Almaty, Satpayev Street, 22
References
1. Jing S. Weak and dynamic GNSS signal tracking strategies for flight missions in the space service volume / S. Jing et al // Sensors. – 2016. – Vol. 16, № 9. – Art. 1412. https://doi.org/10.3390/s16091412.
2. Scientific and methodological bases of GPS monitoring of intensive movements of the Earth’s crust in the earthquake-prone regions of Kazakhstan / Zh.Sh. Zhantayev et al // News of the National Academy of Sciences of the Republic of Kazakhstan. Series of Physics and Mathematics. – 2020. – Vol. 3, № 331. – P. 177-182. https://doi.org/10.32014/2020.2518-1726.51.
3. A two-stage Kalman filter-based carrier tracking loop for weak GNSS signals / Y. Cheng et al // Sensors. – 2019. – Vol. 19, № 6. – Art. 1369. https://doi.org/10.3390/s19061369.
4. Guo K. Effects of GNSS receiver tuning on the PLL tracking jitter estimation in the presence of ionospheric scintillation / K. Guo, M. Aquino, S. Vadakke Veettil // Space Weather. – 2020. – Vol. 18, № 7. – Article e2019SW002362. https://doi.org/10.1029/2019SW002362.
5. Examining the tolerance of GNSS receiver phase tracking loop under the effects of severe ionospheric scintillation conditions based on its bandwidth / I.P. Portella et al // Radio Science. – 2021. – Vol. 56, № 6. – P. 1-11. https://doi.org/10.1029/2020RS007160.
6. Bochkati M. Use of ultra-low-bandwidth tracking loops for improved GNSS receiver phase tracking under thermal stress / M. Bochkati, J. Dampf, T. Pany // NAVIGATION: Journal of the Institute of Navigation. – 2026. – Vol. 73. – Article navi.744. https://doi.org/10.33012/navi.744.
7. Evaluation of adaptive loop-bandwidth tracking techniques in GNSS receivers / I. Cortés et al // Sensors. – 2021. – Vol. 21, № 2. – Art. 502. https://doi.org/10.3390/s21020502.
8. A carrier estimation method based on MLE and KF for weak GNSS signals / H. Zhang et al // Sensors. – 2017. – Vol. 17, № 7. – Art. 1468. https://doi.org/10.3390/s17071468.
9. Stevanovic S. A GPS phase-locked loop performance metric based on the phase discriminator output / S. Stevanovic, B. Pervan // Sensors. – 2018. – Vol. 18, № 1. – Art. 296. https://doi.org/10.3390/s18010296.
10. O’Driscoll C. Choosing the coherent integration time for Kalman filter-based carrier-phase tracking of GNSS signals / C. O’Driscoll, M.G. Petovello, G. Lachapelle // GPS Solutions. – 2011. – Vol. 15. – P. 345-356. https://doi.org/10.1007/s10291-010-0194-4.
11. Improved GNSS vector tracking loop to enhance the navigation performance of USV / W. Liu et al // Ocean Engineering. – 2022. – Vol. 258. – Art. 111865. https://doi.org/10.1016/j.oceaneng.2022.111865.
12. Weak GPS signal tracking using block coherent integration based on NN discriminator / Z. Gong et al // Research Square. – 2025. – Preprint. https://doi.org/10.21203/rs.3.rs-6350123/v1.
13. Borio D. A non-coherent architecture for GNSS digital tracking loops / D. Borio, G. Lachapelle // Annals of Telecommunications. – 2009. – Vol. 64, № 9-10. – P. 601-614. https://doi.org/10.1007/s12243-009-0114-1.
14. Zhao W. Adaptive multiple-model Kalman filter for GNSS carrier phase and frequency estimation through wideband interference / W. Zhao, S. Khanafseh, B. Pervan // NAVIGATION: Journal of the Institute of Navigation. – 2024. – Vol. 71, № 2. – Article navi.646. https://doi.org/10.33012/navi.646.
15. Guillard A. Using convolutional neural networks to detect GNSS multipath / A. Guillard, P. Thevenon, C. Milner // Frontiers in Robotics and AI. – 2023. – Vol. 10. – Art. 1106439. – https://doi.org/10.3389/frobt.2023.1106439.
Review
For citations:
Saparhodzhaev N.P., Khabay A., Igen M.Zh., Tuleshov E.A., Issabekov Zh.N. IMPROVING ARTIFICIAL INTELLIGENCE–BASED METHODS FOR ENHANCING GNSS SIGNAL QUALITY. Bulletin of Shakarim University. Technical Sciences. 2026;(3(23)):31-42. (In Kazakh) https://doi.org/10.53360/2788-7995-2026-3(23)-4
JATS XML















