Gongliu Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Gongliu Yang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Haozhou Mo
Zhejiang University
2 shared publications Daqing Pan
College of Control Science and Engineering, Zhejiang University, Hangzhou, China
1 shared publication- Dongsheng Xu
School of Automation, Beijing Institute of Technology, Beijing, China
1 shared publication - Hongze Yang
School of Physics and Information Engineering, Fuzhou University, Fuzhou, China
1 shared publication Runzhuo Xu
Zhejiang University
1 shared publicationWenqiang Li
College of Optical Science and Engineering, Zhejiang University, Hangzhou, China
1 shared publication
Latest Publications
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (17) , 25762-25774
An Improved Dual-Attention Transformer–LSTM for Small-Sample Prediction of Modal Frequency in Micro Hemispherical Resonator
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (17) , 25762-25774
An Improved Dual-Attention Transformer–LSTM for Small-Sample Prediction of Modal Frequency in Micro Hemispherical Resonator
- 23 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. PP (1530437X) , 1
A Hybrid Physics–Data-Driven Navigation Method for AUVs Fusing Hydrographic Information with INS/DVL Integration
In GNSS-denied underwater environments, the navigation accuracy of Inertial Navigation Systems (INS) aided by Doppler Velocity Logs (DVL) is often severely degraded by complex hydrographic conditions. To address this, this paper proposes a hybrid physics and data driven integrated navigation method that fuses real-time hydrographic information to enhance performance. The approach establishes a layered error-suppression framework. At the physical layer, Conductivity-Temperature-Depth (CTD) sensors are used to construct real-time sound speed profiles, applying Snell’s law-based ray tracing to correct DVL sound-speed scale factors and refraction-induced geometry errors. At the data-driven layer, a hybrid CNN-MLP network intelligently estimates and compensates for residual ocean-current velocity disturbances remaining after physical corrections. Sea trial results validate the complementary contributions of the hybrid architecture: the physical layer effectively corrects acoustic geometric errors (reducing velocity RMSE by ∼35%), while the data-driven layer compensates for dynamic environmental residuals, ultimately reducing velocity RMSE by approximately 60% and suppressing position error by around 80%. This study validates that combining physics-based models with learning-based corrections effectively overcomes drift caused by DVL bottom-lock loss and time-varying currents, enabling high-accuracy, long-endurance AUV operations.
- 23 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. PP (1530437X) , 1
A Hybrid Physics–Data-Driven Navigation Method for AUVs Fusing Hydrographic Information with INS/DVL Integration
In GNSS-denied underwater environments, the navigation accuracy of Inertial Navigation Systems (INS) aided by Doppler Velocity Logs (DVL) is often severely degraded by complex hydrographic conditions. To address this, this paper proposes a hybrid physics and data driven integrated navigation method that fuses real-time hydrographic information to enhance performance. The approach establishes a layered error-suppression framework. At the physical layer, Conductivity-Temperature-Depth (CTD) sensors are used to construct real-time sound speed profiles, applying Snell’s law-based ray tracing to correct DVL sound-speed scale factors and refraction-induced geometry errors. At the data-driven layer, a hybrid CNN-MLP network intelligently estimates and compensates for residual ocean-current velocity disturbances remaining after physical corrections. Sea trial results validate the complementary contributions of the hybrid architecture: the physical layer effectively corrects acoustic geometric errors (reducing velocity RMSE by ∼35%), while the data-driven layer compensates for dynamic environmental residuals, ultimately reducing velocity RMSE by approximately 60% and suppressing position error by around 80%. This study validates that combining physics-based models with learning-based corrections effectively overcomes drift caused by DVL bottom-lock loss and time-varying currents, enabling high-accuracy, long-endurance AUV operations.
- 27 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-13
Image-Free Optical Assistance Method for Impact Vibration Localization in Inertial-Based Hull Deformation Measurement
Large naval vessels are not strictly rigid bodies. Inertial matching measurements are often used to continuously measure hull deformation, thereby achieving a unified spatial reference for the entire ship to ensure the combat effectiveness of onboard weapons. However, during combat, the inertial measurement unit (IMU) is highly sensitive to impact vibration. This sensitivity induces attenuated interference signals, leading to significant steady-state errors or even divergence in inertial-based hull deformation measurements. Therefore, it is necessary to localize the position of the impact vibration, allowing for timely error correction in the inertial-based hull deformation measurement system. To address the challenge of impact vibration localization, this paper proposes a method for locating hull deformation impact vibration using inertial measurement information in conjunction with optical assistance on ships equipped with advanced optical sighting systems. Furthermore, to ensure rapid and precise localization of the impact vibration localization in wartime, the method combines inertial information with single-pixel imaging (SPI), utilizing high-speed light field modulation to achieve image-free and high-speed optical sighting point coordinate acquisition in the Fourier domain under ultra-low sampling rate conditions. By eliminating the need to reconstruct redundant information from complete images, this image-free optical assistance method effectively localizes inertial-based hull deformation impact vibration through the integration of inertial information. Experimental results demonstrate that the proposed method, with a sampling rate as low as 0.02 % of whole image-based methods within the response time of 600 ms, can effectively perform rapid impact vibration localization in inertial-based hull deformation measurements without requiring full images. Additionally, the method exhibits strong noise resistance and good applicability, offering new insights for the combined optical and inertial hull deformation measurement on large naval vessels.
- 27 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-13
Image-Free Optical Assistance Method for Impact Vibration Localization in Inertial-Based Hull Deformation Measurement
Large naval vessels are not strictly rigid bodies. Inertial matching measurements are often used to continuously measure hull deformation, thereby achieving a unified spatial reference for the entire ship to ensure the combat effectiveness of onboard weapons. However, during combat, the inertial measurement unit (IMU) is highly sensitive to impact vibration. This sensitivity induces attenuated interference signals, leading to significant steady-state errors or even divergence in inertial-based hull deformation measurements. Therefore, it is necessary to localize the position of the impact vibration, allowing for timely error correction in the inertial-based hull deformation measurement system. To address the challenge of impact vibration localization, this paper proposes a method for locating hull deformation impact vibration using inertial measurement information in conjunction with optical assistance on ships equipped with advanced optical sighting systems. Furthermore, to ensure rapid and precise localization of the impact vibration localization in wartime, the method combines inertial information with single-pixel imaging (SPI), utilizing high-speed light field modulation to achieve image-free and high-speed optical sighting point coordinate acquisition in the Fourier domain under ultra-low sampling rate conditions. By eliminating the need to reconstruct redundant information from complete images, this image-free optical assistance method effectively localizes inertial-based hull deformation impact vibration through the integration of inertial information. Experimental results demonstrate that the proposed method, with a sampling rate as low as 0.02 % of whole image-based methods within the response time of 600 ms, can effectively perform rapid impact vibration localization in inertial-based hull deformation measurements without requiring full images. Additionally, the method exhibits strong noise resistance and good applicability, offering new insights for the combined optical and inertial hull deformation measurement on large naval vessels.