Uncertainty Quantification for System Identification Utilizing the Bayesian Theory and Its Recent Advances

YAN Wang-ji; CAO Shi-ze; REN Wei-xin.

doi:10.21656/1000-0887.370571

Volume 38 Issue 1

Turn off MathJax

Article Contents

Article Navigation > Applied Mathematics and Mechanics > 2017 > 38(1): 44-59

YAN Wang-ji, CAO Shi-ze, REN Wei-xin.. Uncertainty Quantification for System Identification Utilizing the Bayesian Theory and Its Recent Advances[J]. Applied Mathematics and Mechanics, 2017, 38(1): 44-59. doi: 10.21656/1000-0887.370571

Citation:

PDF( 647 KB)

Uncertainty Quantification for System Identification Utilizing the Bayesian Theory and Its Recent Advances

doi: 10.21656/1000-0887.370571

School of Civil Engineering, Hefei University of Technology, Hefei 230009, P.R.China

Funds: The National Natural Science Foundation of China（51408176；51278163）; The National Key Research and Development Project of China(2016YFE0113400)

Received Date: 2016-10-11
Rev Recd Date: 2016-12-10
Publish Date: 2017-01-15

Abstract

Abstract

System identification is inevitably affected by various uncertainties involving measurement error, modeling error, numerical error as well as environmental variation, which indicates that it is of fundamental importance to explore statistical methods to improve the robustness in identification. The Bayesian approach has attracted widespread attention in the field of system identification due to a number of advantages. On the basis of the classic Bayesian theory, this paper systematically outlined the progress of the Bayesian system identification in the context of structural dynamics. In this study, the theoretical framework for the Bayesian system identification with special emphasis on applicable conditions and the limits on the two kinds of uncertainty quantification approaches were presented. In addition, this paper reviewed some theory, implementation and practice of the Bayesian approaches applied to uncertainty quantification for modal analysis, model updating and damage detection. Finally, the trends and challenges of the Bayesian system identification were prospected.
- Bayesian theory,
- system identification,
- uncertainty,
- modal parameter,
- model updating

FullText(HTML)

References(96)

References

[1]	禹丹江. 土木工程结构模态参数识别——理论、实现与应用[D]. 博士学位论文. 福州: 福州大学, 2006.(YU Dan-jiang. Modal parameter identification of civil engineering structures—theory, implementation and application[D]. PhD Thesis. Fuzhou: Fuzhou University, 2006.(in Chinese))
[2]	李炜明, 董莪, 朱宏平. 土木工程系统辨识统计方法的现状与展望[J]. 振动与冲击, 2012,31(11): 42-47.(LI Wei-ming, DONG E, ZHU Hong-ping. Progress of system identification with statistical methods in civil engineering[J]. Journal of Vibration and Shock,2012,31(11): 42-47.(in Chinese))
[3]	Beck J L, Katafygiotis L S. Updating models and their uncertainties—I: Bayesian statistical framework[J]. Journal of Engineering Mechanics,1998,124(4): 455-461.
[4]	Katafygiotis L S, Beck J L. Updating models and their uncertainties—II: model identifiability[J]. Journal of Engineering Mechanics, 1998,124(4):463-467.
[5]	YAN Wang-ji. Wireless sensor network based structural health monitoring accommodating multiple uncertainties[D]. PhD Thesis. Hong Kong: Hong Kong University of Science and Technology, 2013.
[6]	Housner G W, Bergman L A, Caughey T K,et al. Structural control: past, present, and future[J]. Journal of Engineering Mechanics,1997,123(9): 897-971.
[7]	Beck J L. Bayesian system identification based on probability logic[J]. Structural Control and Health Monitoring,2010,17(7): 825-847.
[8]	茆诗松. 贝叶斯统计[M]. 北京：中国统计出版社, 1999.(MAO Shi-song. Bayesian Statistics [M]. Beijing: China Statistics Press, 1999.(in Chinese))
[9]	Bayes T. An essay towards solving a problem in the doctrine of chances[J]. Resonance,2003,8(4): 80-88.
[10]	CHEUNG Sai-hung. Stochastic analysis, model and reliability updating of complex systems with applications to structural dynamics[D]. PhD Thesis. Pasadena, CA: California Institute of Technology, 2009.
[11]	CHING Jian-ye, CHEN Yi-chu. Transitional Markov chain Monte Carlo method for Bayesian model updating, model class selection, and model averaging[J]. Journal of Engineering Mechanics,2007,133(7): 816-832.
[12]	Katafygiotis L S, LAM Heung-fai. Tangential-projection algorithm for manifold representation in unidentifiable model updating problems[J]. Earthquake Engineering & Structural Dynamics,2002,31(4): 791-812.
[13]	YUEN Ka-veng. Structural modal identification using ambient dynamic data[D]. Master Thesis. Hong Kong: Hong Kong University of Science and Technology, 1999.
[14]	YUEN Ka-veng, Katafygiotis L S. Bayesian fast Fourier transform approach for modal updating using ambient data[J]. Advances in Structural Engineering,2003,6(2): 81-95.
[15]	YUEN Ka-veng, Katafygiotis L S, Beck J L. Spectral density estimation of stochastic vector processes[J]. Probabilistic Engineering Mechanics,2002,17(3):265-272.
[16]	Katafygiotis L S, YUEN Ka-veng. Bayesian spectral density approach for modal updating using ambient data[J]. Earthquake Engineering & Structural Dynamics,2001,30(8): 1103-1123.
[17]	YUEN Ka-veng, Katafygiotis L S. Bayesian time-domain approach for modal updating using ambient data[J]. Probabilistic Engineering Mechanics,2001,16(3): 219-231.
[18]	YUEN Ka-veng, Beck J L, Katafygiotis L S. Probabilistic approach for modal identification using non-stationary noisy response measurements only[J]. Earthquake Engineering & Structural Dynamics,2002,31(4): 1007-1023.
[19]	YUEN Ka-veng. Bayesian Methods for Structural Dynamics and Civil Engineering [M]. New York: John Wiley & Sons Ltd, 2010.
[20]	AU Siu-kui. Fast Bayesian FFT method for ambient modal identification with separated modes[J]. Journal of Engineering Mechanics,2011,137(3): 214-226.
[21]	AU Siu-kui. Fast Bayesian ambient modal identification in the frequency domain, part I: posterior most probable value[J]. Mechanical Systems and Signal Processing,2012,26: 60-75.
[22]	AU Siu-kui. Fast Bayesian ambient modal identification in the frequency domain, part II: posterior uncertainty[J]. Mechanical Systems and Signal Processing,2012,26: 76-90.
[23]	AU Siu-kui, ZHANG Feng-liang. On assessing the posterior mode shape uncertainty in ambient modal identification[J]. Probabilistic Engineering Mechanics,2011,26(3): 427-434.
[24]	AU Siu-kui. Uncertainty law in ambient modal identification—part I: theory[J]. Mechanical Systems and Signal Processing,2014,48(1/2): 15-33.
[25]	AU Siu-kui. Uncertainty law in ambient modal identification—part II: implication and field verification[J]. Mechanical Systems and Signal Processing,2014,48(1/2): 34-48.
[26]	AU Siu-kui. Connecting Bayesian and frequentist quantification of parameter uncertainty in system identification[J]. Mechanical Systems and Signal Processing,2012,29:328-342.
[27]	AU Siu-kui, ZHANG Feng-liang, NI Yan-chun. Bayesian operational modal analysis: theory, computation, practice[J]. Computers & Structures,2013,126: 3-14.
[28]	AU Siu-kui, NI Yan-chun. Fast Bayesian modal identification of structures using known single-input forced vibration data[J]. Structural Control and Health Monitoring,2014,21: 381-402.
[29]	ZHANG Feng-liang, NI Yan-chun, AU Siu-kui, et al. Fast Bayesian approach for modal identification using free vibration data, part I: most probable value[J]. Mechanical Systems and Signal Processing,2016,70/71: 209-220.
[30]	NI Yan-chun, ZHANG Feng-liang, LAM Heung-fai, et al. Fast Bayesian approach for modal identification using free vibration data, part II: posterior uncertainty and application[J]. Mechanical Systems and Signal Processing,2016,70/71: 221-244.
[31]	AU Siu-kui. Assembling mode shapes by least squares[J]. Mechanical Systems and Signal Processing,2011,25(1): 163-179.
[32]	AU Siu-kui, ZHANG Feng-liang. Fast Bayesian ambient modal identification incorporating multiple setups[J]. Journal of Engineering Mechanics,2012,138(7): 800-815.
[33]	ZHANG Feng-liang, AU Siu-kui, LAM Heung-fai. Assessing uncertainty in operational modal analysis incorporating multiple setups using a Bayesian approach[J]. Structural Control and Health Monitoring,2015,22(3): 395-416.
[34]	AU Siu-kui, ZHANG Feng-liang. Ambient modal identification of a primary-secondary structure by fast Bayesian FFT method[J]. Mechanical Systems & Signal Processing,2012,28: 280-296.
[35]	AU Siu-kui, NI Yan-chun, ZHANG Feng-liang, et al. Full-scale dynamic testing and modal identification of a coupled floor slab system[J]. Engineering Structures,2012,37(4): 167-178.
[36]	AU Siu-kui, ZHANG Feng-liang, TO Ping. Field observations on modal properties of two tall buildings under strong wind[J]. Journal of Wind Engineering and Industrial Aerodynamics,2012,101: 12-23.
[37]	YAN Wang-ji, Katafygiotis L S. A two-stage fast Bayesian spectral density approach for ambient modal analysis. Part I: posterior most probable value and uncertainty[J]. Mechanical Systems & Signal Processing,2014,54/55: 139-155.
[38]	YAN Wang-ji, Katafygiotis L S. A two-stage fast Bayesian spectral density approach for ambient modal analysis. Part II: mode shape assembly and case studies[J]. Mechanical Systems & Signal Processing,2015,54/55: 156-171.
[39]	万华平. 结构动力不确定性及其随机模型修正方法研究[D]. 博士学位论文. 长沙: 中南大学, 2014.(WAN Hua-ping. Research on structural dynamic uncertainty and its stochastic model updating method[D]. PhD Thesis. Changsha: Central South University.(in Chinese))
[40]	Beck J L, AU Siu-kui, Vanik M W. Monitoring structural health using a probabilistic measure[J]. Computer-Aided Civil and Infrastructure Engineering,2001,16(1): 1-11.
[41]	Vanik M W, Beck J L, Au S K. Bayesian probabilistic approach to structural health monitoring[J]. Journal of Engineering Mechanics,2000,126(7): 738-745.
[42]	CHING Jian-ye, Muto M, Beck J L. Structural model updating and health monitoring with incomplete modal data using Gibbs sampler[J]. Computer-Aided Civil and Infrastructure Engineering,2006,21(4): 242-257.
[43]	CHING Jian-ye, Beck J L. Bayesian analysis of the phase II IASC-ASCE structural health monitoring experimental benchmark data[J]. Journal of Engineering Mechanics,2004,130(10): 1233-1244.
[44]	CHING Jian-ye, Beck J L. New Bayesian model updating algorithm applied to a structural health monitoring benchmark[J]. Structural Health Monitoring,2004,3(4): 313-332.
[45]	YUEN Ka-veng, Beck J L, Katafygiotis L S. Efficient model updating and health monitoring methodology using incomplete modal data without mode matching[J]. Structural Control & Health Monitoring,2006,13(1): 91-107.
[46]	YAN Wang-ji, Katafygiotis L S. A novel Bayesian approach for structural model updating utilizing statistical modal information from multiple setups[J]. Structural Safety,2015,52: 260-271.
[47]	Papadimitriou C, Papadioti D C. Component mode synthesis techniques for finite element model updating[J]. Computers & Structures,2013,126(1):15-28.
[48]	Jensen H A, Millas E, Kusanovic D, et al. Model-reduction techniques for Bayesian finite element model updating using dynamic response data[J]. Computer Methods in Applied Mechanics and Engineering,2014,279: 301-324.
[49]	Papadimitriou C, Papadioti D C. Fast Computing Techniques for Bayesian Uncertainty Quantification in Structural Dynamics [M]//Simmermacher T, Cogan S, Moaveni B, et al, ed. Topics in Model Validation and Uncertainty Quantification.Vol5. New York: Springer, 2013: 25-31.
[50]	Craig Jr R R. Structural Dynamics: An Introduction to Computer Methods [M]. New York: John Wiley and Sons, 1981.
[51]	Wan H P, Ren W X. Stochastic model updating utilizing Bayesian approach and Gaussian process model[J]. Mechanical Systems and Signal Processing,2016,70: 245-268.
[52]	Behmanesh I, Moaveni B, Lombaert G, et al. Hierarchical Bayesian model updating for structural identification[J]. Mechanical Systems & Signal Processing,2015,64: 360-376.
[53]	Gamerman D, Lopes H F. Markov Chain Monte Carlo: Stochastic Simulation for Bayesian Inference [M]. Boca Raton: Chapman & Hall, 2006.
[54]	AU Siu-kui, Beck J L. A new adaptive importance sampling scheme for reliability analysis[J]. Structural Safety,1999,21(2): 135-158.
[55]	Kirkpatrick S, Gelatt C D, Vecchi M P. Optimization by simulated annealing[J]. Science,1983,220(4598): 671-680.
[56]	Beck J L, AU Siu-kui. Bayesian updating of structural models and reliability using Markov chainMonte Carlo simulation[J]. Journal of Engineering Mechanics,2002,128(4): 380-391.
[57]	Goller B, Schuller G I. Investigation of model uncertainties in Bayesian structural model updating[J]. Journal of Sound & Vibration,2011,330(25): 6122-6136.
[58]	ZHENG Wei, YU Yi. Bayesian probabilistic framework for damage identification of steel truss bridges under joint uncertainties[J]. Advances in Civil Engineering,2013,2013: 307171. doi: 10.1155/2013/307171.
[59]	WANG Jia, Katafygiotis L S. Reliability-based optimal design of linear structures subjected to stochastic excitations[J]. Structural Safety,2014,47(2): 29-38.
[60]	Beck J L, Zuev K M. Asymptotically independent Markov sampling: a new Markov chain Monte Carlo scheme for Bayesian inference[J]. International Journal for Uncertainty Quantification,2013,3(5): 445-474.
[61]	CHEUNG Sai-hung, Beck J L. Bayesian model updating using hybrid Monte Carlo simulation with application to structural dynamic models with many uncertain parameters[J]. Journal of Engineering Mechanics,2009,135(4): 243-255.
[62]	Green P L. Bayesian system identification of a nonlinear dynamical system using a novel variant of simulated annealing[J]. Mechanical Systems & Signal Processing,2015,52/53: 133-146.
[63]	Green P L, Cross E J, Worden K. Bayesian system identification of dynamical systems using highly informative training data[J].Mechanical Systems & Signal Processing,2015,56/57: 109-122.
[64]	Marin J M, Pudlo P, Robert C P, et al. Approximate Bayesian computational methods[J]. Statistics & Computing,2012,22(6): 1167-1180.
[65]	Chiachio M, Beck J L, Chiachio J, et al. Approximate Bayesian computation by subset simulation[J]. SIAM Journal on Scientific Computing,2014,36(3): A1339-A1338.
[66]	Vakilzadeh M K, Huang Y, Beck J L, et al. Approximate Bayesian computation by subset simulation using hierarchical state-space models[J]. Mechanical Systems & Signal Processing,2017,84(B): 2-20.
[67]	AU Siu-kui, Beck J L. Estimation of small failure probabilities in high dimensions by subset simulation[J]. Probabilistic Engineering Mechanics,2001,16(4): 263-277.
[68]	Straub D, Papaioannou I. Bayesian updating with structural reliability methods[J]. Journal of Engineering Mechanics,2014,141(3): 04014134.
[69]	DiazDelaO F A, Garbuno-Inigo A, Au S K, et al. Bayesian updating and model class selection with subset simulation[Z]. arXiv preprint arXiv: 1510.06989, 2015.
[70]	LAM Heung-fai, YANG Jia-hua, AU Siu-kui. Bayesian model updating of a coupled-slab system using field test data utilizing an enhanced Markov chain Monte Carlo simulation algorithm[J]. Engineering Structures,2015,102: 144-155.
[71]	SUN Hao, Büyükztürk O. Probabilistic updating of building models using incomplete modal data[J]. Mechanical Systems and Signal Processing,2016,75: 27-40.
[72]	ZHANG Jian, WAN Chun-feng, Sato T. Advanced Markov chain Monte Carlo approach for finite element calibration under uncertainty[J]. Computer-Aided Civil and Infrastructure Engineering,2013,28(7): 522-530.
[73]	Simoen E, De Roeck G, Lombaert G. Dealing with uncertainty in model updating for damage assessment: a review[J]. Mechanical Systems and Signal Processing,2015,56/57: 123-149.
[74]	Collins J D, Hart G C, Haselman T K, et al. Statistical identification of structures[J]. Aiaa Journal,1973,12(2): 185-190.
[75]	Sohn H, Law K H. A Bayesian probabilistic damage detection using load-dependent Ritz vectors[C]// Proceedings of the 16th International Modal Analysis Conference.Santa Barbara, California : Society for Experimental Mechanics, Inc,1998: 374-380．
[76]	Sohn H, Law K H. Bayesian probabilistic damage detection of a reinforced-concrete bridge column[J]. Earthquake Engineering & Structural Dynamics,2000,29(8): 1131-1152.
[77]	Vanik M W. A Bayesian probabilistic approach to structural health monitoring: technical report EERL 97-07[R]. Earthquake Engineering Research Laboratory, California Institute of Technology, Pasadena, CA, 1997.
[78]	YUEN Ka-veng, AU Siu-kui, Beck J L. Two-stage structural health monitoring approach for phase I benchmark studies[J]. Journal of Engineering Mechanics,2004,130(1):16-33.
[79]	YUEN Ka-veng, Katafygiotis L S. Model updating using response measurements without knowledge of the input spectrum[J]. Earthquake Engineering and Structural Dynamics,2005,34(2): 167-187.
[80]	YUEN Ka-veng, Katafygiotis L S. Substructure identification and health monitoring using response measurement only[J]. Computer-Aided Civil and Infrastructure Engineering,2006,21(4): 280-291.
[81]	YAN Wang-ji, Katafygiotis L S. Application of transmissibility matrix and random matrix to Bayesian system identification with response measurements only[J]. Smart Materials and Structures,2016,25(10): 105017.
[82]	Ebrahimian H, Astroza R, Conte J P, et al. Nonlinear finite element model updating for damage identification of civil structures using batch Bayesian estimation[J]. Mechanical Systems & Signal Processing,2017,84(B): 194-222.
[83]	易伟建, 周云, 李浩. 基于贝叶斯统计推断的框架结构损伤诊断研究[J]. 工程力学, 2009,26(5): 121-129.(YI Wei-jian, ZHOU Yun, LI Hao. Damage assessment research on frame structure based on Bayesian statistical inference[J]. Engineering Mechanics,2009,26(5): 121-129.(in Chinese) )
[84]	Lam H F, Yin T. Statistical detection of multiple cracks on thin plates utilizing dynamic response[J]. Engineering Structures,2010,32(10): 3145-3152.
[85]	Lam H F, Lee Y Y, Sun H Y, et al. Application of the spatial wavelet transform and Bayesian approach to the crack detection of a partially obstructed beam[J]. Thin-Walled Structures,2005,43(1): 1-21.
[86]	Lam H F, Ng C T, Veidt M. Experimental characterization of multiple cracks in a cantilever beam utilizing transient vibration data following a probabilistic approach[J]. Journal of Sound and Vibration,2007,305(1): 34-49.
[87]	Lam H F, Wong M T, Yang Y B. A feasibility study on railway ballast damage detection utilizing measured vibration of in situ concrete sleeper[J]. Engineering Structures,2012,45: 284-298.
[88]	Ng C T, Veidt M, Lam H F. Guided wave damage characterisation in beams utilising probabilistic optimisation[J]. Engineering Structures,2009,31(12): 2842-2850.
[89]	Flynn E B, Todd M D, Wilcox P D, et al. Maximum-likelihood estimation of damage location in guided-wave structural health monitoring[J]. Proceedings: Mathematical, Physical and Engineering Sciences,2011,467(2133): 2575-2596.
[90]	YUEN Ka-veng. Recent developments of Bayesian model class selection and applications in civil engineering[J]. Structural Safety,2010,32(5): 338-346.
[91]	Beck J L, YUEN Ka-veng. Model selection using response measurements: Bayesian probabilistic approach[J]. Journal of Engineering Mechanics,2004,130(2): 192-203.
[92]	CHEUNG Sai-hung, Beck J L. Calculation of posterior probabilities for Bayesian model class assessment and averaging from posterior samples based on dynamic system data[J]. Computer-Aided Civil and Infrastructure Engineering,2010,25(5): 304-321.
[93]	Papadimitriou C. Pareto optimal sensor locations for structural identification[J]. Computer Methods in Applied Mechanics and Engineering,2005,194(12): 1655-1673.
[94]	YUEN Ka-veng, KUOK Sin-chi. Efficient Bayesian sensor placement algorithm for structural identification: a general approach for multi-type sensory systems[J]. Earthquake Engineering & Structural Dynamics,2015,44(5): 757-774.
[95]	SUN Hao, FENG Dong-ming, LIU Yang, et al. Statistical regularization for identification of structural parameters and external loadings using state space models[J]. Computer-Aided Civil and Infrastructure Engineering,2015,30(11): 843-858.
[96]	Simoen E, Papadimitriou C, Lombaert G. On prediction error correlation in Bayesian model updating[J]. Journal of Sound and Vibration,2013,332(18): 4136-4152.