同济大学桥梁系桥梁健康监测与振动控制研究室成立于2001年，也是土木工程防灾国家重点实验室的一部分。研究室自成立以来，先后承担了国家自然科学基金，教育部、科技部、交通部、上海市科委、江苏省交通厅以及河北省交通厅等国家级、部省级重大或重点科研课题研究，为解决桥梁工程中的关键技术难题提供了基础理论、方法和技术。

桥梁健康监测与振动控制研究室主页：https://shmc.tongji.edu.cn/4f/de/c2302a282590/page.htm

1.     国家自然科学基金青年项目，基于层次贝叶斯理论和人工智能的桥梁结构混合数字孪生方法（编号52208199），2023.1 - 2025.12，主持

2.     上海市海外高层次人才项目，2022.3 – 2024.12，主持

3.     上海勘测设计研究院有限公司上海海上风能资源开发利用工程技术研究中心开放课题，海上风电结构健康监测及实时状态评估技术（编号FNZX2023KP01），2025.4 - 2028.3，主持

4.     国家自然科学基金面上项目，基于混合监测的桥梁数字化建模（编号52378187），2024.1 - 2027.12，参与

5.     国家自然科学基金面上项目，基于多源残错数据的桥梁网级评估方法（编号52278313），2023.1 - 2026.12，参与

6.     National Offshore Wind Research & Development Consortium, Physics Based Digital Twins for Optimal Asset Management (154719), 2021.1 - 2022.12, 80万美元, 参与

7.     National Science Foundation (NSF), An Adaptive System Identification Approach Using Mobile Sensors (1903972), 2019.6 - 2022.5, 52万美元, 参与

8.     Bureau of Safety and Environmental Enforcement (BSEE), The Block Island Structural Monitoring Joint Project (140E0119C0003), 2020.5 - 2021.12, 60万美元, 参与

9.     United States Geological Survey (USGS), A Hierarchical Bayes Inversion Approach for Site Characterization Using Surface Wave Measurements (G18AP00034), 2018.6 - 2020.5, 8万美元, 参与

10. National Science Foundation (NSF), CAREER: Probabilistic Nonlinear Structural Identification for Health Monitoring of Civil Structures (1254338), 2013.6 - 2019.5, 40万美元, 参与

1.    国家自然科学基金青年项目，基于层次贝叶斯理论和人工智能的桥梁结构混合数字孪生方法（编号52208199），2023.1 - 2025.12，主持

2.    上海市海外高层次人才项目，2022.3 – 2024.12，主持

3.     上海勘测设计研究院有限公司上海海上风能资源开发利用工程技术研究中心开放课题，海上风电结构健康监测及实时状态评估技术（编号FNZX2023KP01），2025.4 - 2028.3，主持

4.    国家自然科学基金面上项目，基于混合监测的桥梁数字化建模（编号52378187），2024.1 - 2027.12，参与

5.    国家自然科学基金面上项目，基于多源残错数据的桥梁网级评估方法（编号52278313），2023.1 - 2026.12，参与

6.    National Offshore Wind Research& Development Consortium, Physics Based Digital Twins for Optimal AssetManagement (154719), 2021.1 - 2022.12, 80万美元, 参与

7.    National Science Foundation (NSF),An Adaptive System Identification Approach Using Mobile Sensors (1903972), 2019.6- 2022.5, 52万美元, 参与

8.    Bureau of Safety andEnvironmental Enforcement (BSEE), The Block Island Structural Monitoring JointProject (140E0119C0003), 2020.5 - 2021.12, 60万美元, 参与

9.    United States Geological Survey(USGS), A Hierarchical Bayes Inversion Approach for Site Characterization UsingSurface Wave Measurements (G18AP00034), 2018.6 - 2020.5, 8万美元, 参与

10. National Science Foundation (NSF), CAREER: Probabilistic NonlinearStructural Identification for Health Monitoring of Civil Structures (1254338), 2013.6- 2019.5, 40万美元, 参与

1.    孙利民, 王艺晴, 宋明明*, 夏烨. 基于循环神经网络辅助卡尔曼滤波法的动力响应重构方法. Journal of Southeast University/Dongnan Daxue Xuebao. 2025 Nov1;55(6).

2.    罗岚炘，宋明明，钟华强，何天涛，孙利民*. 考虑运营荷载的大跨径拱桥层次贝叶斯模型修正方法. 振动与冲击.2025; 44(1).

3.    Wang T*, Zhang S, Song M,Sun L*. Dictionary Learning-Based Data Pruning for System Identification.Applied Sciences. 2025 Aug 26;15(17):9368.

4.    Liu J, Li Y*, Sun L, Luo L, SongM. Physics-encoded interpretable self-supervised learning for structuraldamage identification. Engineering Structures. 2025 Nov 15;343:121045.

5.    Luo L, Sun L, Song M,Liu J, Li Y*, Xia Y*. Joint load-parameter-response identification using aphysics-encoded neural network. Mechanical Systems and Signal Processing. 2025May 1;230:112597.

6.    Komarizadehasl S, Shen Z, Xia Y*,Song M, Turmo J. An innovative drive-through approach for structuraltesting and experimental insights from two cable stayed bridges. Developmentsin the Built Environment. 2025 Apr 1;22:100653.

7.    Qu G, Song M*, Xia Y,Sun L. Bridge Girder‐End Displacement Reconstruction Using a Novel Hybrid AttentionMechanism Leveraging Multisource Information. Structural Control and HealthMonitoring. 2025;2025(1):8249455.

8.    Luo W, Gong F, Song M,Xia Y*. A structural 3D displacement measurement method using monocular camerabased on multiple feature points tracking. Measurement. 2024 Dec9:116406.

9.    Qu G, Song M*, Sun L.Bridge deformation quantiles prediction with MVO-CNN-BiLSTM based on mixedattention mechanism and periodic multi-source information fusion. Journal ofCivil Structural Health Monitoring. 2024 Dec 9:1-22.

10. Song M, Moaveni B*, Hines E.Hierarchical Bayesian quantification of aerodynamic effects on an offshore windturbine under varying environmental and operational conditions. MechanicalSystems and Signal Processing. 2025 Feb 1;224:112174.

11. Valikhani M, Nabiyan M, Song M, Jahangiri V, Ebrahimian H*, MoaveniB. Bayesian finite element model inversion of offshore wind turbine structuresfor joint parameter-load estimation. Ocean Engineering. 2024 Dec1;313:119458.

12. Wang Y, Song M*, Wang A, Sun L. Structural Dynamic ResponseReconstruction Based on Recurrent Neural Network–Aided Kalman Filter. StructuralControl and Health Monitoring. 2024;2024(1):7481513.

13. Qu G, Song M*, Xin G, Shang Z, Sun L. Time-convolutionalnetwork with joint time-frequency domain loss based on arithmetic optimizationalgorithm for dynamic response reconstruction. Engineering Structures.2024 Dec 15;321:119001.

14. Qu G, Song M*, Sun L. Bayesian dynamic noise model for onlinebridge deflection prediction considering stochastic modeling error. Journalof Civil Structural Health Monitoring. 2024 Aug 18:1-8.

15. Qu G, Song M*, Sun L. Real-Time Bridge Deflection PredictionBased on a Novel Bayesian Dynamic Difference Model and Nonstationary Data. Journalof Bridge Engineering. 2024 Sep 1;29(9):04024064.

16. Luo L, Song M*, Li Y, Sun L*. A hierarchical Bayesian modelupdating method for bridge structures by fusing multi-source information. StructuralHealth Monitoring. 2024 Jun 13:14759217241253361.

17. Teymouri D, Sedehi O, Song M, Moaveni B, Papadimitriou C,Katafygiotis LS*. Hierarchical Bayesian finite element model updating: Optimalweighting of modal residuals with application to FINO3 offshore platform. MechanicalSystems and Signal Processing. 2024 Apr 1;211:111150.

18. Luo L, Song M*, Zhong H, He T, Sun L*. Hierarchical Bayesianmodel updating of a long-span arch bridge considering temperature and trafficloads. Mechanical Systems and Signal Processing. 2024 Mar 15;210:111152.

19. Song M, Mehr NP, Moaveni B*, Hines E,Ebrahimian H, Bajric A. One year monitoring of an offshore wind turbine:Variability of modal parameters to ambient and operational conditions. EngineeringStructures. 2023 Dec 15;297:117022.

20. Partovi-Mehr N, Branlard E, Song M, Moaveni B*, Hines EM,Robertson A. Sensitivity Analysis of Modal Parameters of a Jacket Offshore WindTurbine to Operational Conditions. Journal of Marine Science and Engineering.2023 Jul 30;11(8):1524.

21. Song M, Moaveni B*, Ebrahimian H, HinesE, Bajric A. Joint parameter-input estimation for digital twinning of the BlockIsland wind turbine using output-only measurements. Mechanical Systems andSignal Processing. 2023 Sep 1;198:110425.

22. Hines EM*, Baxter CD, Ciochetto D, Song M, Sparrevik P,Meland HJ, Strout JM, Bradshaw A, Hu SL, Basurto JR, Moaveni B. Structuralinstrumentation and monitoring of the Block Island Offshore Wind Farm. RenewableEnergy. 2023 Jan 1;202:1032-45.

23. Song M, Christensen S, Moaveni B*, Brandt A, Hines E. Jointparameter-input estimation for virtual sensing on an offshore platform usingoutput-only measurements. MechanicalSystems and Signal Processing. 2022 May 1;170:108814.

24. Mehrjoo A, Song M,Moaveni B*, Papadimitriou C, Hines E. Optimal sensor placement for parameterestimation and virtual sensing of strains on an offshore wind turbineconsidering sensor installation cost. MechanicalSystems and Signal Processing. 2022 Apr 15;169:108787.

25. Song M, Renson L*, Moaveni B, Kerschen G. Bayesian Model Updating andClass Selection of a Wing-Engine Structure with Nonlinear Connections usingNonlinear Normal Modes. Mechanical Systemsand Signal Processing. 2022 Feb 15;165:108337.

26. Zhang Y, Lian J, Zhang G, Liu Y, Song M*, Li S. Groundvibration characteristics induced by flood discharge of a high dam: Anexperimental investigation. Journal of Renewable and Sustainable Energy.2021 Jan 4;13(1):014502.

27. Liu P*, Huang S, Song M,Yang W. Bayesian Model Updating of a Twin-Tower Masonry Structure throughSubset Simulation Optimization Using Ambient Vibration Data. Journal ofCivil Structural Health Monitoring. 2020 Oct 23:1-20.

28. Song M, Behmanesh I, Moaveni B*,Papadimitriou C. Accounting for Modeling Errors and Inherent StructuralVariability through a Hierarchical Bayesian Model Updating Approach: AnOverview. Sensors. 2020 Jan;20(14):3874.

29. Song M, Astroza R, Ebrahimian H, MoaveniB*, Papadimitriou C. Adaptive Kalman filters for nonlinear finite element modelupdating. Mechanical Systems and Signal Processing. 2020 Sep1;143:106837.

30. Yousefianmoghadam S, Song M,Mohammadi M, Packard B, Stavridis A*, Moaveni B, Wood RL, Packard B. Nonlineardynamic tests of a reinforced concrete frame building at different damagelevels. Earthquake Engineering & Structural Dynamics. 2020 May 11.

31. Song M, Behmanesh I, Moaveni B*, Papadimitriou C. Modeling errorEstimation and response prediction of a 10-Story building model through ahierarchical Bayesian model updating framework. Frontiers in Built Environment. 2019;5:7.

32. Song M, Moaveni B*, Papadimitriou C, Stavridis A. Accounting for amplitudeof excitation in model updating through a hierarchical Bayesian approach:Application to a two-story reinforced concrete building. Mechanical Systems and Signal Processing. 2019 May 15;123:68-83.

33.Song M,Renson L, Noël JP, Moaveni B*, Kerschen G. Bayesianmodel updating of nonlinear systems using nonlinear normal modes. StructuralControl and Health Monitoring. 2018 Dec;25(12):e2258.

34. Song M, Yousefianmoghadam S, Mohammadi ME, Moaveni B*, Stavridis A, WoodRL. An application of finite element model updating for damage assessment of atwo-story reinforced concrete building and comparison with lidar. Structural Health Monitoring. 2018Sep;17(5):1129-50.

围绕结构健康监测与智能运维，重点开展数字孪生、贝叶斯推理与人工智能融合研究，面向桥梁与海上风电等重大基础设施，探索数据驱动与物理机理深度融合的新一代工程分析范式。

主要研究方向包括：

• 结构健康监测（SHM）
• 数字孪生（Digital Twin）
• 深度学习与科学计算融合（AI for Engineering）
• 无人机与计算机视觉智能巡检
• 贝叶斯推理与不确定性量化 
• 
  

1.    数字孪生与智能结构感知（Digital Twin and Intelligent Structural Sensing）

面向桥梁与风力发电机等复杂工程结构，本研究致力于构建融合物理机理模型与多源监测数据的高可信数字孪生系统，突破传统纯数值模拟或单一数据驱动方法的局限，形成“物理模型—数据驱动—不确定性量化”深度融合的新范式。依托结构健康监测系统与多源感知数据，开展结构状态感知与异常识别、复杂环境与运行工况下的运营模态智能识别、基于贝叶斯推理的结构参数识别与模型修正，以及稀疏观测条件下的全域响应重构与预测和未知荷载（如风、车辆与地震）的实时反演与解耦识别。在此基础上，构建具备实时感知、状态诊断、性能预测与决策支持能力的一体化数字孪生系统，实现面向工程实际的“可解释、可更新、可预测”的智能运维，为重大基础设施的安全评估与长期性能管理提供理论与技术支撑。

2.    无人机智能巡检与数字化感知（UAV-enabled Intelligent Inspection and Digital Sensing）

面向桥梁、建筑与风力发电机等大型基础设施，本研究基于无人机平台，融合可见光、红外与LiDAR等多源感知数据，构建集巡检、建模、识别与评估于一体的智能巡检体系。围绕复杂环境下的自主巡检需求，开展无人机路径规划与任务优化、基于深度学习的结构病害自动识别，以及倾斜摄影与多源数据融合的高精度三维重建，实现病害在三维空间中的精细化表达与定量评估。在此基础上，进一步探索与BIM/BrIM模型的深度融合，通过建立几何与语义映射关系，实现病害信息的构件级定位与全生命周期数据管理，支撑结构运维决策与检测报告的自动化生成。同时，结合计算机视觉与视频测量技术，从无人机视频中提取结构振动响应信息，突破传统接触式传感器的布设限制，推动“巡检—监测”一体化与监测系统轻量化发展。最终目标是构建具备自主巡检、多源感知、智能分析与决策支持能力的无人机智能巡检综合平台，服务于基础设施的高效、安全与智能运维。

3.    物理–数据融合智能推理（Physics–Data Hybrid Intelligent Inference）

面向桥梁与风力发电机等复杂工程结构在数字孪生与智能运维中的核心需求（如全域响应预测、未知荷载反演与损伤识别），本研究致力于构建物理机理与数据驱动深度融合的新一代智能推理方法。针对传统纯物理模型难以刻画复杂环境与模型误差、纯数据驱动方法在工程场景中泛化能力与可解释性不足的问题，探索融合有限元模型、微分方程与状态空间模型等物理先验，与多源监测数据和深度学习方法协同的统一建模框架，实现对结构状态与外部作用的高精度感知与推断。该方向强调在数据稀疏、环境复杂及模型不完备条件下，提升模型的鲁棒性、泛化能力与工程适用性，为无人机巡检与结构健康监测提供可靠的信息支撑，并为数字孪生系统中的状态更新、性能预测与运维决策提供关键方法基础。通过打通“感知—建模—预测—决策”的技术链条，推动基础设施智能运维由经验驱动向数据与机理融合驱动的范式转变。

相关网址：

土木工程学院教师主页：

https://faculty-civileng.tongji.edu.cn/songmingming/zh_CN/index.htm

桥梁系教师主页：https://bridge.tongji.edu.cn/45/53/c14930a279891/page.htm

ResearchGate: https://www.researchgate.net/profile/Mingming-Song-2

Google Scholar: https://scholar.google.com/citations?user=p_ryhTMAAAAJ&hl=en