选择语言
< 返回主菜单
weixintupian_20240110104455.jpg

孙利民

上海期智研究院PI(2020年7月-至今)
同济大学教授

个人简介

上海期智研究院PI,同济大学桥梁工程系教授,教育部长江学者特聘教授。

长期从事桥梁健康监测、振动控制及桥梁抗震等方向的教学和科研工作。在桥梁结构监测研究方向上,提出了桥梁网络监测与评估体系、以及混合监测、移动监测等新方法和理论,改善了传统监测系统测点信息不足和造价过高的技术瓶颈,推动了大数据方法在桥梁健康监测领域中的应用。在结构振动控制方向上,长期坚持拉索减振理论研究和装置研发,构建了超长斜拉索非线性阻尼器设计理论及阻尼装置性能评价方法。在大跨桥梁抗震方向上,开展了大跨深水基础索承重桥梁抗震设计理论及试验研究,提出了大跨深水基础索承重桥梁地震响应的系统分析方法并集成了计算软件平台,建立了主跨为1400 m斜拉桥的benchmark模型及全桥试验数据库,研究成果为重大桥梁工程抗震设计提供了技术手段。


个人荣誉

2020年获“中国公路学会科学技术一等奖”(强震区近断层、跨断层桥梁减灾关键技术及工程应用)

2019年获“上海市科学技术进步三等奖”(单边悬挂双桥面空间曲线悬索桥关键技术)

2013年获“广东省科学技术三等奖”(九江大桥船撞风险评估与防撞系统方案研究)

2013年获“日本土木工程学会国际活动协力奖”

2008年获“江苏省科技进步二等奖”(千米级斜拉桥超长斜拉索减振研究)

2007年获“上海市科学技术进步奖三等奖”(外海超长桥梁健康监测系统开发与应用)

2007年12月被授予新世纪百千万人才工程国家级人选

1997年获“日本大林组技术开发优秀奖”(混合滑模技工法技术研究(重水泥TLD开发部分)

1991年获“日本土木学会论文奖”(调谐液态阻尼器(TLD)的特性解明及模型建立)


研究方向

土木基础设施数字化建模:以数字化的方式建立土木工程物理实体的动态虚拟模型来刻画其在真实环境中的属性、行为和规则。为利用大数据、物联网、通信等信息技术来改造与提升传统土木工程技术提供数字底座。

基于AI技术的结构监测与状态评估:基于AI技术的监测数据驱动的环境作用与结构状态识别及诊断。研发结构健康监测系统软硬件集成平台。

结构智能防灾:下一代以人工智能为驱动的防灾减灾技术

亮点成果

成果6:桥梁网级智能评估技术

        孙利民团队提出了系统的桥梁网级评估理论、方法、技术,首先提出了一种自然退化的病害数据重构方法和基于自然语言处理技术的文本错误清洗方法,并基于检测报告中的病害数据提出两个基于病害严重程度的桥梁部件退化指标,随后集成病害指标、桥梁的基本结构信息和交通流数据建立路网桥梁多源信息数据库,最后基于自动机器学习建立并训练了了路网级的桥梁退化模型,实现对路网桥梁技术状况的准确预测。研究的主要创新点有:(1)目前在土木工程领域较少有人对桥梁非结构化文本数据进行研究,也罕见以桥梁检测报告为主体的数据清洗研究。本课题利用自然语言处理技术和深度学习等手段提取非结构化检测数据、定位并重构检测数据的残缺和错误数据,提高桥梁检测数据利用效率,为网级评估模型提供高质量的桥梁历史健康数据。(2)目前的桥梁评估模型都以评分和评级为量化手段,而评分、评级数据受检测人员主观影响大且不容易量化维修的影响。本课题基于桥梁定期检查得到的病害数据,提出两项衡量部件性能退化的技术状况指标,规避了技术状况评分受主观影响大的缺陷,同时实现对维修行为的量化。(3)目前对桥梁的评估和性能预测主要局限于单体桥梁级别,以区域桥梁为主体的桥梁退化模型也局限于神经网络,应用较少且需要大量参数调整。本课题基于自动机器学习框架将区域关键特征与结构状态进行关联,训练了两层的桥梁群退化模型,充分利用区域多源数据蕴含的桥梁退化信息,在较少的参数调整工作下,实现对区域全部桥梁(包含未有检测信息的桥梁)的状态评估与预测,并指导区域桥梁管养方案的制定。


2023孙利民成果照片5.jpg

图. 桥梁网级评估技术示意图


-------------------------------------------------------------------------------------------------------------------------------


成果5:基础设施性态智能预测

       在基础设施建设和正常运营阶段,对基础设施关键性态进行监测和预测并在严重变形时发出预警,防患于未然,是具有重要工程意义的工作。同济大学团队基于广州地铁在建项目大规模性态监测数据,建立了针对在建车站基坑及支护变形的智能预测框架及多通道多步预测模型。首先采用分步聚类方法,用层次聚类对监测物理量进行聚类,之后基于监测点空间分布特征和监测数据时间维度上的相似性,使用K-means对测点进行时空聚类。然后,建立基于经验模态分解(EMD)和长短期记忆神经网络(LSTM)的集成模型,并进一步构建基于分步聚类(Stepwise clustering)和Transformer的多通道多步预测模型,通过将数据重组成多维时间序列输入神经网络模型,得到多测点未来多步预测值。该方法有效挖掘监测数据特征,并且利用多测点信息进行联合预测,可实现多测点未来多步变形的准确预测。


2023孙利民成果照片6.jpg.png


       研究领域:基础设施智慧运维

       研究论文:Shan J, Zhang X, Liu Y, et al. Deformation prediction of large-scale civil structures using spatiotemporal clustering and empirical mode decomposition-based long short-term memory network[J]. Automation in Construction, 2024, 158: 105222.(土木IF最高)


-------------------------------------------------------------------------------------------------------------------------------


成果4:可迁移的大规模电子结构计算的机器学习加速方法

       密度泛函理论(DFT)是研究分子和材料电子结构的强大工具,它能够揭示许多物质性质的内在机制。然而,由于DFT在大型系统上计算时所需的高昂计算成本和运行时间,使得在此类系统中成功实施DFT计算仍然受到诸多限制。复旦大学的向红军团队提出了基于图神经网络实现的电子哈密顿矩阵的等变参数化方法,该方法可以实现从原子位置到电子哈密顿量的直接映射,从而绕过DFT方法中昂贵的自洽迭代过程。在碳同素异形体、硅同素异形体和SiO2异构体的哈密顿矩阵上分别进行训练后的HamGNN模型对训练集之外的同类结构预测的能带与DFT计算得到的能带高度一致。此外,训练之后的HamGNN模型还成功预测了含上千原子的大型硅位错超胞的缺陷能级和Moiré扭转双层MoS2的Dirac锥能带色散。电子结构这些实际测试证明该研究提出的机器学习模型对电子哈密顿量的预测具有很高的精度和可迁移性,可以替代DFT用于高效计算大型系统的电子结构。目前,HamGNN的代码已经开源到GitHub网站。



2023孙利民成果照片4.png.jpg


       

       研究领域:电子结构机器学习加速算法

       项目网站:https://github.com/QuantumLab-ZY/HamGNN 

       研究论文:Yang Zhong, Hongyu Yu, Mao Su, Xingao Gong and Hongjun Xiang. Transferable equivariant graph neural networks for the Hamiltonians of molecules and solids. npj Comput. Mater. 9, 182 (2023). 查看PDF


-------------------------------------------------------------------------------------------------------------------------------


成果3:基于多体矫正项的机器学习势函数新框架的开发

       近十年来迅速发展起来的高维机器学习势代表着复杂系统大规模原子模拟的巨大进步。然而高维机器学习势函数普遍具有长程相互作用和化学反应描述不准确的问题,其主要原因是以原子为中心的 机器学习模型结构判别能力差。项目提出了一种基于神经网络的低成本机器学习势函数结构,用于拟合全局势能面数据,即多体矫正机器学习神经网络势函数,它能在复杂势能面上提供更好的结构分辨能力,从而提高对能量和力的拟合精度。在多体矫正神经网络势函数中,计算总能量时明确包含了一组基于局部原子环境的多体能量项,而系统的总能量被写成原子能量和多体能量贡献之和。这些额外的多体能量项计算成本较低,而且重要的是,它们可以方便地获取复杂系统中的微妙能量项,如极短斥力、长程吸引力和敏感的角度依赖性共价相互作用。我们在 LASP 代码中实现了多体矫正机器学习神经网络势函数,并选取三元能量材料 LiCoOx、有缺陷的 TiO2 以及一系列有机反应作为代表性体系展示了新的势函数框架在不同场景中表现出的更高的计算精度。


2023孙利民成果照片3.png


      

       研究领域:机器学习神经网络势函数

       项目网站: http://www.lasphub.com/

       研究论文:Pei-Lin Kang, Zheng-Xin Yang, Cheng Shang and Zhi-Pan Liu, Global Neural Network Potential with Explicit Many-Body Functions for Improved Descriptions of Complex Potential Energy Surface, J. Chem. Theory Comput., 2023, 19, 7972-7981. 查看PDF


-------------------------------------------------------------------------------------------------------------------------------


成果2:重大结构混合监测、智能评估与工程应用

       结构监测是支撑在役建筑构件安全运维的重要技术手段,监测数据的扩充、分析和信息提取是提升该技术有效性之关键。孙利民团队以多座大跨度桥梁、城市桥梁群、以及典型超高超大建筑结构为对象,基于长期监测数据,结合数字化及人工智能手段,研发了异常数据清洗、残错数据修复、多源数据融合等技术手段,提升了监测数据质量,打破了多源数据间的壁垒;提出了将监测数据与有限元分析相结合的混合监测理论,丰富了数据种类,改善了数据完备性;建立了交通流、温度等运营环境荷载作用模型及不完备信息下结构响应求解方法并初步建立了用于在役桥梁运维养护的数字孪生模型。应用层面,提出了重大结构健康监测系统软硬件的集成开发模式,构建了超高超大建筑施工和运营全过程的健康监测一体化成套技术和设备系统,实现了超高超大建筑施工和运营全过程的传感器实时自动诊断、多源异构监测数据的同步采集、海量数据的动态存储与管理、结构性态的在线评估和预警等技术。

       团队成功主办了第三届国际健康监测智能方法竞赛(IC-SHM 2022),竞赛内容全部来自于研发团队的攻关算法,吸引了来自15个国家的四十余个顶级智能算法团队竞赛;研究成果在《Structural Control & Health Monitoring》等国际杂志发表多篇重要论文,项目数据作为理论应用于桥梁健康与安全状态评估,成果在宁波桥梁群、广州周大福金融中心、济南汉裕金谷大厦、G60科创云廊、上海天文馆等众多标志性项目中开展了示范应用。


2023孙利民成果照片1.png

图:混合监测理论与智能评估技术


2023孙利民成果照片2.jpg

图:重要区域与重点结构工程应用案例


-------------------------------------------------------------------------------------------------------------------------------


成果1:桥梁结构混合监测与数据孪生建模

       桥梁结构监测是支撑在疫桥梁安全运维的重要技术手段,监测数据的扩充、分析和信息提取是提升该技术有效性之关键。孙利民团队基于多座大跨度桥梁及城市桥梁群长期监测数据,结合数字化及人工智能手段,研发了异常数据清洗、残错数据修复、多源数据融合等技术手段,提升了监测数据质量,打破了多源数据间的壁垒;提出了将监测数据与有限元分析相结合的混合监测理论,丰富了数据种类,改善了数据完备性;建立了交通流、温度等运营环境荷载作用模型及不完备信息下结构响应求解方法并初步建立了用于在疫桥梁运维养护的数字孪生模型。研究成果在《Structural Control & Health Monitoring》等国际杂志发表多篇论文,并应用于桥梁健康与安全状态评估。


孙利民2022.jpg



招聘信息

论文发表

50. Di, FD (Di, Fangdian) ; Sun, LM (Sun, Limin) ; Chen, L (Chen, Lin) ; Zou, YQ (Zou, Yiqing) ; Qin, L (Qin, Lei)  ; Huang, ZQ (Huang, Zhiquan), Frequency and damping of hybrid cable networks with cross-ties and external dampers: Full-scale experiments, MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2023 查看PDF


49. Chen, L (Chen, Lin)  ; Liu, ZH (Liu, Zhanhang) ; Zou, YQ (Zou, Yiqing)  ; Wang, M (Wang, Meng); Nagarajaiah, S (Nagarajaiah, Satish)  ; Sun, FF (Sun, Feifei)  ; Sun, LM (Sun, Limin) , Practical negative stiffness device with viscoelastic damper in parallel or series configuration for cable damping improvement, Journal of Sound and Vibration, 2023 查看PDF


48. Chen, L (Chen, Lin) [1] ; Xia, Y (Xia, Ye) [1] ; Di, FD (Di, Fangdian) [5] ; Zhang, GQ (Zhang, Guoquan) [1] ; Li, XL (Li, Xiaolong) [3] ; He, TT (He, Tiantao) ; Sun, LM (Sun, Limin), Dynamic modeling and analysis of hanger cables with spacers and dampers for vibration mitigation, Structures, 2023 查看PDF


47. Gong, FZ (Gong, Fengzong); Lei, XM (Lei, Xiaoming) ; Xia, Y (Xia, Ye), Real-time damage identification of hinge joints in multi-girder bridges using recursive least squares solution of the characteristic equation, Engineering Structures, 2023 查看PDF


46. Lei, Xiaoming; Xia, Ye; Wang, Ao; Jian, Xudong; Zhong, Huaqiang; Sun, Limin, Mutual information based anomaly detection of monitoring data with attention mechanism and residual learning, Mechanical Systems and Signal Processing, 2023 查看PDF


45. Chen, L (Chen, Lin)  ; Qin, L (Qin, Lei) ; Di, FD (Di, Fangdian) ; Sun, LM (Sun, Limin); Zou, YQ (Zou, Yiqing)  ; Huang, ZQ (Huang, Zhiquan), Full-scale experimental study on dynamic behaviors of a three-cable network with a pretensioned cross-tie, Engineering Structures, 2023 查看PDF


44. Weng, JH (Weng, Jinghang) ; Chen, L (Chen, Lin); Sun, LM (Sun, Limin) ; Zou, YQ (Zou, Yiqing) ; Liu, ZH (Liu, Zhanhang)  ; Guo, H (Guo, Hui) , Fully automated and non-contact force identification of bridge cables using microwave remote sensing, Measurement, 2023 查看PDF


43. Liu Zhanghang, Chen Lin, Sun Limin, Zhao Lin, Cui Wei, Multimode damping optimization of a long-span suspension bridge with damped outriggers for suppressing vortex-induced vibrations, Engineering Structures, 2023 查看PDF


42. Jiazeng Shan, Changhao Zhuang, Cheng Ning Loong, Parametric identification of Timoshenko-beam model for shear-wall structures using monitoring data, Mechanical Systems and Signal Processing, 2023 查看PDF


41. Jiazeng Shan, Luji Wang, Cheng Ning Loong and Zijie Zhou, Rapid seismic performance evaluation of existing frame structures using equivalent SDOF modeling and prior dynamic testing, Journal of Civil Structural Health Monitoring, 2023 查看PDF


40. Jiangmeng Guo, Luji Wang, Jiazeng Shan, Data-driven modeling and prediction on hysteresis behavior of flexure RC columns using deep learning networks, The Structural Design of Tall and Special Buildings, 2023 查看PDF


39. Yang, Bin; Zhu, Haitao; Zhang, Qilin; Wüchner, Roland; Sun, Siyuan; Qiu, Jiahui, Identification of wind loads on a 600 m high skyscraper by Kalman filter, Journal of Building Engineering, 2023 查看PDF


38. Ning Hou, Limin Sun, Lin Chen, 《Modeling vehicle load for a long-span bridge based on weigh in motion data》, Journal of Measurement, 2021 查看PDF


37. Li, Yixian; Huang, Hongwei; Zhang, Wei; Sun, Limin, Structural full-field responses reconstruction by the SVD and pseudo-inverse operator-estimated force with two-degree multi-scale models, Engineering Structures, 2021 查看PDF


36. Xudong Jian, Huaqiang Zhong, Ye Xia, Limin Sun, Faulty data detection and classification for bridge structural health monitoring via statistical and deep-learning approach. , Structural Control & Health Monitoring, 2021 查看PDF


35. Ye Xia, Xiaoming Lei, Peng Wang, Limin Sun, Artificial Intelligence Based Structural Assessment for Regional Short- and Medium-Span Concrete Beam Bridges with Inspection Information, Remote Sensing, 2021 查看PDF


34. Hou, Ning; Sun, Limin; Chen, Lin, Modeling vehicle load for a long-span bridge based on weigh in motion data, Measurement, 2021 查看PDF


33. Ao Wang; Zongkai Zhang; Xiaoming Lei; Ye Xia; Limin Sun, All-weather thermal simulation methods for concrete maglev bridge based on structural and meteorological monitoring data, Sensors, 2021 查看PDF


32. Li, Yixian; Zhu, Ledong; Qian, Cheng; Jian, Xudong; Sun, Limin, The time-varying modal information of a cable-stayed bridge: Some consideration for SHM, Engineering Structures, 2021 查看PDF


31. Kai Cheng, Jiazeng Shan and Yuwen Liu, Feature-based image stitching for panorama construction and visual inspection of structures, Smart Structures and Systems, 2021 查看PDF


30. Jiaqiang Wang, Jin Zhao, Yuwen Liu, Jiazeng Shan, Vision-based displacement and joint rotation tracking of frame structure using feature mix with single consumer-grade camera, Structural Control and Health Monitoring, 2021 查看PDF


29. Yexiang Yan, Ye Xia, Jipeng Yang, Limin Sun, Optimal selection of scalar and vector-valued seismic intensity measures based on Gaussian Process Regression, Soil Dynamics and Earthquake Engineering, 2022 查看PDF


28. Ye Xia, Xiaoming Lei, Peng Wang, Limin Sun, A data-driven approach for regional bridge condition assessment using inspection reports,  Structural Control & Health Monitoring, 2022 查看PDF


27. 闫业祥; 孙利民, 基于高斯过程回归的桥梁多变量地震易损性分析, 振动与冲击, 2022 查看PDF


26. 孙利民; 狄方殿; 陈林; 邹易清, 考虑垂度影响的拉索-双粘滞阻尼器系统振动分析, 工程力学, 2022 查看PDF


25. Ni, Peng; Li, Yixian; Sun, Limin; Wang, Ao, Traffic-induced bridge displacement reconstruction using a physics-informed convolutional neural network, Computers and Structures, 2022 查看PDF


24. Di, Fangdian; Sun, Limin; Chen, Lin, Optimization of hybrid cable networks with dampers and cross-ties for vibration control via multi-objective genetic algorithm, Mechanical Systems and Signal Processing, 2022 查看PDF


23. Yang, Jipeng; Xia, Ye; Lei, Xiaoming; Sun, Limin, Hysteretic parameters identification of RC frame structure with Takeda model based on modified CKF method, Bulletin of Earthquake Engineering, 2022 查看PDF


22. Yan Yexiang; Huang Hongwei; Sun Limin, Multi-parameter seismic fragility and sensitivity analysis of long-span cable-stayed bridge based on multi-task lasso regression, Structures, 2022 查看PDF


21. Lei, Xiaoming; Xia, Ye; Deng, Lu; Sun, Limin, A deep reinforcement learning framework for life-cycle maintenance planning of regional deteriorating bridges using inspection data, Structural and Multidisciplinary Optimization, 2022 查看PDF


20. Yan, Yexiang; Huang, Hongwei; Sun, Limin, Multivariate structural seismic fragility analysis and comparative study based on moment estimation surrogate model and Gaussian copula function, Engineering Structures, 2022 查看PDF


19. Li, Yixian; Ni, Peng; Sun, Limin; Zhu, Wang, A convolutional neural network-based full-field response reconstruction framework with multitype inputs and outputs, Structural Control & Health Monitoring, 2022 查看PDF


18. Li, Yixian; Sun, Limin; Zhu, Wang; Zhang, Wei, A dynamic stiffness-based framework for harmonic input estimation and response reconstruction considering damage, Frontiers of Structural and Civil Engineering, 2022 查看PDF


17. Luo, Lanxin; Xia, Ye; Wang, Ao; Lei, Xiaoming; Jian, Xudong; Sun, Limin, Finite element model updating method for continuous girder bridges using monitoring responses and traffic videos, Structural Control & Health Monitoring, 2022 查看PDF


16. Lei, Xiaoming; Xia, Ye; Komarizadehasl, Seyedmilad; Sun, Limin, Condition level deteriorations modeling of RC beam bridges with U-Net convolutional neural networks, Structures, 2022 查看PDF


15. Lei, Xiaoming; Xia, Ye; Dong, You; Sun, Limin, Multi-level time-variant vulnerability assessment of deteriorating bridge networks with structural condition records, Engineering Structures, 2022 查看PDF


14. Jian, Xudong; Xia, Ye; Sun, Limin, Indirect identification of bridge frequencies using a four-wheel vehicle: Theory and three-dimensional simulation, Mechanical Systems and Signal Processing, 2022 查看PDF


13. Sun, Limin; Chen, Lin; Huang, Hongwei, Stay cable vibration mitigation: A review, Advances in Structural Engineering, 2022 查看PDF


12. Chen Lin; Liu Zhanhang; Nagarajaiah Satish; Sun Limin;, Vibration mitigation of long-span bridges with damped outriggers, Engineering Structures, 2022 查看PDF


11. Shang, Zhiqiang; Xia, Ye; Chen, Lin Z.; Sun, Limin, Damping ratio identification using attenuation responses extracted by time series semantic segmentation, Mechanical Systems and Signal Processing, 2022 查看PDF


10. Jian, Xudong; Xia, Ye; Sun, Shouwang; Sun, Limin, Integrating bridge influence surface and computer vision for bridge weigh-in-motion in complicated traffic scenarios, Structural Control & Health Monitoring, 2022 查看PDF


9. Jian, Xudong; Lai, Zhilu; Xia, Ye; Sun, Limin, A robust bridge weigh-in-motion algorithm based on regularized total least squares with axle constraints, Structural Control & Health Monitoring, 2022 查看PDF


8. Li, Yixian; Sun, Limin; Xia, Yong; Luo, Lanxin; Wang, Ao; Jian, Xudong, General Tikhonov regularization-based load estimation of bridges considering the computer vision-extracted prior information, Structural Control & Health Monitoring, 2022 查看PDF


7. Nan Gong, Peizhen Li, Jiazeng Shan, Aftershock performance evaluation of shear wall structures with replaceable coupling beam including low-cycle degradation, Structures, 2022 查看PDF


6. Jiazeng Shan, Zhi Jiang, Weichao Wu, Zhiguo Shi, Feasibility of using self-sensing component and response prediction model for rotation monitoring of shear wall structures, The Structural Design of Tall and Special Buildings, 2022 查看PDF


5. Zhiguo Shi, Cheng Ning Loong and Jiazeng Shan, Equivalent circuit model of eddy current damping regarding frequency-dependence with test validation, Advances in Structural Engineering, 2022 查看PDF


4. Jiazeng Shan, Yijie Gong, Jie Liu, Weixing Shi and Hanqing Zhang, Damage tracking and evaluation of RC columns with structural performances by using seismic monitoring data, Bulletin of Earthquake Engineering, 2022 查看PDF


3. Runze Yu, Peizhen Li, Jiazeng Shan, Hongtao Zhu, Structural state estimation of earthquake-damaged building structures by using UAV photogrammetry and point cloud segmentation, Measurement, 2022 查看PDF


2. Yang, Bin; Pan, Licheng; Zhu, Haitao; Sun, Siyuan; Zhang, Qilin, Spatiotemporal correlation analysis of the dynamic response of supertall buildings under ambient wind conditions, Structural Design of Tall and Special Buildings, 2022 查看PDF


1. 徐洪俊; 吴杰; 张锦东; 杨森; 张其林, 参数识别的改进Bayesian TDD-FFT方法及其应用, 建筑结构学报, 2022 查看PDF