Xun Su
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xun Su has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Jianxiao Mao
Key Laboratory of C&PC Structures of the Ministry of Education, Southeast University, Nanjing 211189, P. R. China
2 shared publications - Gui Gui
Key Laboratory of Concrete and Prestressed, Concrete Structures of Ministry of Education, Southeast University, Nanjing 211189, P. R. China
1 shared publication - Hai Zong1 shared publication
- Hao Wang
Key Laboratory of C&PC Structures of Ministry of Education, Southeast University, Nanjing, China
1 shared publication - Hao Wang1 shared publication
- Hui Gao
International Joint Research Lab for Eco-building Materials and Engineering of Henan Province, North China University of Water Resources and Electric Power, Zhengzhou 450045, China
1 shared publication
Latest Publications
- 21 April 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Structural Stability and Dynamics
- Vol. 26 (24)
Reconstruction of Missing Vibration Data for Long-Span Bridges by Fusing Multiple-Frequency Information Utilizing LSTM with Bayesian Optimization
Effective monitoring of bridge structural health relies heavily on continuous and accurate data acquisition. However, sensor failures, communication disruptions, and environmental factors often lead to missing data, challenging the reliability of monitoring systems. Given the intricate features and nonlinear characteristics of vibration data, traditional full-band reconstruction methods based on machine learning may encounter difficulties in feature selection and extraction and are notably sensitive to data quality, especially when data loss occurs in parts of a single measurement. To address this challenge, this paper proposes an LSTM-based reconstruction method for missing vibration data by splitting band to fuse multi-frequency information. Bayesian optimization complements LSTM to improve the accuracy and robustness of reconstruction by systematically optimizing network hyperparameters. The reconstructed effectiveness is verified using acceleration data from both a numerical-simulated three-span continuous beam bridge and a full-scale long-span suspension bridge. The results provide a thorough comparison between the performance and advantages of full-band reconstruction and the proposed split-band reconstruction approaches. Through comparative analyses, the efficacy and practicality of the split-band reconstruction approach based on LSTM with Bayesian optimization is underscored. This research aims to provide a theoretical basis for improving the resilience and service life of civil infrastructure by improving the reconstruction of missing data from vibration signals.
- 21 April 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Structural Stability and Dynamics
- Vol. 26 (24)
Reconstruction of Missing Vibration Data for Long-Span Bridges by Fusing Multiple-Frequency Information Utilizing LSTM with Bayesian Optimization
Effective monitoring of bridge structural health relies heavily on continuous and accurate data acquisition. However, sensor failures, communication disruptions, and environmental factors often lead to missing data, challenging the reliability of monitoring systems. Given the intricate features and nonlinear characteristics of vibration data, traditional full-band reconstruction methods based on machine learning may encounter difficulties in feature selection and extraction and are notably sensitive to data quality, especially when data loss occurs in parts of a single measurement. To address this challenge, this paper proposes an LSTM-based reconstruction method for missing vibration data by splitting band to fuse multi-frequency information. Bayesian optimization complements LSTM to improve the accuracy and robustness of reconstruction by systematically optimizing network hyperparameters. The reconstructed effectiveness is verified using acceleration data from both a numerical-simulated three-span continuous beam bridge and a full-scale long-span suspension bridge. The results provide a thorough comparison between the performance and advantages of full-band reconstruction and the proposed split-band reconstruction approaches. Through comparative analyses, the efficacy and practicality of the split-band reconstruction approach based on LSTM with Bayesian optimization is underscored. This research aims to provide a theoretical basis for improving the resilience and service life of civil infrastructure by improving the reconstruction of missing data from vibration signals.
- Open Access
- 1 January 2024
- Published by Wiley in Structural Control and Health Monitoring
- Vol. 2024 (1)
Vortex‐Induced Vibration of Long Suspenders of a Long‐Span Suspension Bridge and Its Effect on Local Deck Acceleration Based on Field Monitoring
As the main structural component, the possibility of wind‐induced vibration, especially vortex‐induced vibrations (VIVs), is greatly increased due to the shape and structural characteristics of the long suspenders. To investigate the full‐scale wind‐induced vibration of the long suspenders of a long‐span suspension bridge with a main span of 1418 m, the long‐term vibration‐based monitoring system was established. Based on the recorded structural health monitoring (SHM) data, the corresponding wind conditions and the vibration characteristics of long suspenders with different diameters and tensions are investigated. Furthermore, modal parameters including frequencies and damping ratios of long suspenders are identified and tracked during the VIV period. The relationship between the shedding frequency of long suspenders and the corresponding wind speed is studied. Results show that the VIVs with frequencies ranging from 8 Hz to 20 Hz were observed continuously across a wide range of wind speeds in both sets of long suspenders. Due to the relatively low modal damping, significant vortex characteristics and lock‐in phenomena can be expected on the long suspenders. A new frequency‐adjustable Stockbridge damper is employed to suppress multimodal VIVs in the long suspenders. The effectiveness of Stockbridge damper is verified through field application and comparative analysis. Finally, the effect of long suspender VIVs on local deck vibration is discussed, and it is clarified that the bridge deck vibration is mainly caused by multimodal VIVs of the long suspenders, rather than by external loads such as vehicles and wind. The study endeavors to provide a case to progress the identification, assessment, and control of long suspender VIVs in similar long‐span bridges.
- 1 January 2024
- Published by Wiley in Structural Control and Health Monitoring
- Vol. 2024 (1)
Open AccessVortex‐Induced Vibration of Long Suspenders of a Long‐Span Suspension Bridge and Its Effect on Local Deck Acceleration Based on Field Monitoring
As the main structural component, the possibility of wind‐induced vibration, especially vortex‐induced vibrations (VIVs), is greatly increased due to the shape and structural characteristics of the long suspenders. To investigate the full‐scale wind‐induced vibration of the long suspenders of a long‐span suspension bridge with a main span of 1418 m, the long‐term vibration‐based monitoring system was established. Based on the recorded structural health monitoring (SHM) data, the corresponding wind conditions and the vibration characteristics of long suspenders with different diameters and tensions are investigated. Furthermore, modal parameters including frequencies and damping ratios of long suspenders are identified and tracked during the VIV period. The relationship between the shedding frequency of long suspenders and the corresponding wind speed is studied. Results show that the VIVs with frequencies ranging from 8 Hz to 20 Hz were observed continuously across a wide range of wind speeds in both sets of long suspenders. Due to the relatively low modal damping, significant vortex characteristics and lock‐in phenomena can be expected on the long suspenders. A new frequency‐adjustable Stockbridge damper is employed to suppress multimodal VIVs in the long suspenders. The effectiveness of Stockbridge damper is verified through field application and comparative analysis. Finally, the effect of long suspender VIVs on local deck vibration is discussed, and it is clarified that the bridge deck vibration is mainly caused by multimodal VIVs of the long suspenders, rather than by external loads such as vehicles and wind. The study endeavors to provide a case to progress the identification, assessment, and control of long suspender VIVs in similar long‐span bridges.