Gaussian mixture model for automated tracking of modal parameters of long-span bridge

다국어 초록 (Multilingual Abstract)

Determination of the most meaningful structural modes and gaining insight into how these modes evolve are important issues for long-term structural health monitoring of the long-span bridges. To address this issue, modal parameters identified throughout the life of the bridge need to be compared and linked with each other, which is the process of mode tracking. The modal frequencies for a long-span bridge are typically closely-spaced, sensitive to the environment (e.g., temperature, wind, traffic, etc.), which makes the automated tracking of modal parameters a difficult process, often requiring human intervention. Machine learning methods are well-suited for uncovering complex underlying relationships between processes and thus have the potential to realize accurate and automated modal tracking. In this study, Gaussian mixture model (GMM), a popular unsupervised machine learning method, is employed to automatically determine and update baseline modal properties from the identified unlabeled modal parameters. On this foundation, a new mode tracking method is proposed for automated mode tracking for long-span bridges. Firstly, a numerical example for a three-degree-of-freedom system is employed to validate the feasibility of using GMM to automatically determine the baseline modal properties. Subsequently, the field monitoring data of a long-span bridge are utilized to illustrate the practical usage of GMM for automated determination of the baseline list. Finally, the continuously monitoring bridge acceleration data during strong typhoon events are employed to validate the reliability of proposed method in tracking the changing modal parameters. Results show that the proposed method can automatically track the modal parameters in disastrous scenarios and provide valuable references for condition assessment of the bridge structure.

참고문헌 (Reference)

1 Zhou, G. D., "Wireless sensor placement for structural monitoring using informationfusing firefly algorithm" 26 (26): 2017

2 Jeffreys, H., "The theory of probability" Oxford University Press 1998

3 T.K. Moon, "The expectation-maximization algorithm" Institute of Electrical and Electronics Engineers (IEEE) 13 (13): 47-60, 1996

4 J.M. Ko, "Technology developments in structural health monitoring of large-scale bridges" Elsevier BV 27 (27): 1715-1725, 2005

5 Hao Wang, "Structural health monitoring system for Sutong Cable-stayed Bridge" 국제구조공학회 18 (18): 317-334, 2016

6 Jinping Ou, "Structural Health Monitoring in mainland China: Review and Future Trends" SAGE Publications 9 (9): 219-231, 2010

7 Bart Peeters, "Stochastic System Identification for Operational Modal Analysis: A Review" ASME International 123 (123): 659-667, 2001

8 Parisa Asadollahi, "Statistical Analysis of Modal Properties of a Cable-Stayed Bridge through Long-Term Wireless Structural Health Monitoring" American Society of Civil Engineers (ASCE) 22 (22): 2017

9 B. F. Spencer, "State of the Art of Structural Control" American Society of Civil Engineers (ASCE) 129 (129): 845-856, 2003

10 Douglas A. Reynolds, "Speaker Verification Using Adapted Gaussian Mixture Models" Elsevier BV 10 (10): 19-41, 2000

11 Svante Wold, "Principal component analysis" Elsevier BV 2 (2): 37-52, 1987

12 Bishop, C. M., "Pattern recognition and machine learning" Springer Science 2006

13 Edwin Reynders, "Output-only structural health monitoring in changing environmental conditions by means of nonlinear system identification" SAGE Publications 13 (13): 82-93, 2014

14 Hu, W. H., "Operational modal analysis and continuous dynamic monitoring of footbridges" University of Porto 2011

15 Hao Wang, "Measurement of Wind Effects on a Kilometer-Level Cable-Stayed Bridge during Typhoon Haikui" American Society of Civil Engineers (ASCE) 144 (144): 2018

16 Serdar Soyoz, "Long-Term Monitoring and Identification of Bridge Structural Parameters" Wiley 24 (24): 82-92, 2009

17 Y.Q. Ni, "Investigation of mode identifiability of a cable-stayed bridge: comparison from ambient vibration responses and from typhoon-induced dynamic responses" 국제구조공학회 15 (15): 447-468, 2015

18 Jian-Xiao Mao, "Investigation of dynamic properties of long-span cable-stayed bridges based on one-year monitoring data under normal operating condition" Wiley 25 (25): e2146-, 2018

19 Edwin Reynders, "Fully automated (operational) modal analysis" Elsevier BV 29 : 228-250, 2012

20 Jian-Xiao Mao, "Fatigue Reliability Assessment of a Long-Span Cable-Stayed Bridge Based on One-Year Monitoring Strain Data" American Society of Civil Engineers (ASCE) 24 (24): 2019

21 Yukio Tamura, "Evaluation of amplitude-dependent damping and natural frequency of buildings during strong winds" Elsevier BV 59 (59): 115-130, 1996

22 Guang-Dong Zhou, "Energy-aware wireless sensor placement in structural health monitoring using hybrid discrete firefly algorithm" Wiley 22 (22): 648-666, 2015

23 Hadi Salehi, "Emerging artificial intelligence methods in structural engineering" Elsevier BV 171 : 170-189, 2018

24 Maria Q. Feng, "Damage Assessment of Jacketed RC Columns Using Vibration Tests" American Society of Civil Engineers (ASCE) 125 (125): 265-271, 1999

25 Zijun Cao, "Bayesian model comparison and selection of spatial correlation functions for soil parameters" Elsevier BV 49 : 10-17, 2014

26 Larry Wasserman, "Bayesian Model Selection and Model Averaging" Elsevier BV 44 (44): 92-107, 2000

27 Mahmoud El-Kafafy, "Automatic Tracking of the Modal Parameters of an Offshore Wind Turbine Drivetrain System" MDPI AG 10 (10): 574-, 2017

28 Jian‐Xiao Mao, "Automated modal identification using principal component and cluster analysis: Application to a long‐span cable‐stayed bridge" Wiley 26 (26): e2430-, 2019

29 Alessandro Cabboi, "Automated modal identification and tracking: Application to an iron arch bridge" Wiley 24 (24): e1854-, 2017

30 Venu Gopal Madhav Annamdas, "Applications of structural health monitoring technology in Asia" SAGE Publications 16 (16): 324-346, 2017

31 T. Kanungo, "An efficient k-means clustering algorithm: analysis and implementation" Institute of Electrical and Electronics Engineers (IEEE) 24 (24): 881-892, 2002

32 J.M.W. Brownjohn, "Ambient vibration re-testing and operational modal analysis of the Humber Bridge" Elsevier BV 32 (32): 2003-2018, 2010

33 J. A. Hartigan, "Algorithm AS 136: A K-Means Clustering Algorithm" JSTOR 28 (28): 100-108, 1979

34 P. VERBOVEN, "AUTONOMOUS STRUCTURAL HEALTH MONITORING—PART I: MODAL PARAMETER ESTIMATION AND TRACKING" Elsevier BV 16 (16): 637-657, 2002

35 Rharã Cardoso, "A robust methodology for modal parameters estimation applied to SHM" Elsevier BV 95 : 24-41, 2017

36 Hao Wang, "A monitoring-based approach for evaluating dynamic responses of riding vehicle on long-span bridge under strong winds" Elsevier BV 189 : 35-47, 2019

37 Giacomo Vincenzo Demarie, "A machine learning approach for the automatic long-term structural health monitoring" SAGE Publications 18 (18): 819-837, 2018

38 Y. Huang, "A Gaussian Mixture Model Based Classification Scheme for Myoelectric Control of Powered Upper Limb Prostheses" Institute of Electrical and Electronics Engineers (IEEE) 52 (52): 1801-1811, 2005