Methodologies for predicting natural frequency variation of a suspension bridge

In vibration-based structural health monitoring, changes in the natural frequency of a structure are used to identify changes in the structural conditions due to damage and deterioration. However, natural frequency values also vary with changes in environmental factors such as temperature and wind. Therefore, it is important to differentiate between the effects due to environmental variations and those resulting from structural damage. In this paper, this task is accomplished by predicting the natural frequency of a structure using measurements of environmental conditions. Five methodologies – multiple linear regression, artificial neural networks, support vector regression, regression tree and random forest – are implemented to predict the natural frequencies of the Tamar Suspension Bridge (UK) using measurements taken from 3 years of continuous monitoring. The effects of environmental factors and traffic loading on natural frequencies are also evaluated by measuring the relative importance of input variables in regression analysis. Results show that support vector regression and random forest are the most suitable methods for predicting variations in natural frequencies. In addition, traffic loading and temperature are found to be two important parameters that need to be measured. Results show potential for application to continuously monitored structures that have complex relationships between natural frequencies and parameters such as loading and environmental factors.

[1]  Hojjat Adeli,et al.  Neural Networks in Civil Engineering: 1989–2000 , 2001 .

[2]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[3]  Ian F. C. Smith,et al.  Evaluating two model-free data interpretation methods for measurements that are influenced by temperature , 2011, Adv. Eng. Informatics.

[4]  Alan Julian Izenman,et al.  Modern Multivariate Statistical Techniques: Regression, Classification, and Manifold Learning , 2008 .

[5]  Yi-Qing Ni,et al.  Constructing input to neural networks for modeling temperature-caused modal variability: Mean temperatures, effective temperatures, and principal components of temperatures , 2010 .

[6]  Yi-Qing Ni,et al.  Modeling of Temperature–Frequency Correlation Using Combined Principal Component Analysis and Support Vector Regression Technique , 2007 .

[7]  B. Peeters,et al.  Vibration-based damage detection in civil engineering: excitation sources and temperature effects , 2001 .

[8]  James M. W. Brownjohn,et al.  Development of a Tamar Bridge Finite Element Model , 2011 .

[9]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[10]  Hoon Sohn,et al.  An experimental study of temperature effect on modal parameters of the Alamosa Canyon Bridge , 1999 .

[11]  Chin-Hsiung Loh,et al.  Nonlinear Identification of Dynamic Systems Using Neural Networks , 2001 .

[12]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[13]  John T. DeWolf,et al.  Effect of Temperature on Modal Variability of a Curved Concrete Bridge under Ambient Loads , 2007 .

[14]  Alexander G. Parlos,et al.  Nonlinear dynamic system identification using artificial neural networks (ANNs) , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[15]  Yi-Qing Ni,et al.  Generalization Capability of Neural Network Models for Temperature-Frequency Correlation Using Monitoring Data , 2009 .

[16]  I. Iervolino,et al.  Computer Aided Civil and Infrastructure Engineering , 2009 .

[17]  Kellie J. Archer,et al.  Empirical characterization of random forest variable importance measures , 2008, Comput. Stat. Data Anal..

[18]  Zhao-Dong Xu,et al.  Simulation of the Effect of Temperature Variation on Damage Detection in a Long-span Cable-stayed Bridge , 2007 .

[19]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[20]  Yi-Qing Ni,et al.  Performance of neural networks for simulation and prediction of temperature-induced modal variability , 2005, SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[21]  D. Basak,et al.  Support Vector Regression , 2008 .

[22]  John H. Maindonald,et al.  Modern Multivariate Statistical Techniques: Regression, Classification and Manifold Learning , 2009 .

[23]  Yi-Qing Ni,et al.  Correlating modal properties with temperature using long-term monitoring data and support vector machine technique , 2005 .

[24]  U. Grömping.  Dependence of Variable Importance in Random Forests on the Shape of the Regressor Space , 2009 .

[25]  R. Edrada-Ebel,et al.  A chemometric study of chromatograms of tea extracts by correlation optimization warping in conjunction with PCA, support vector machines and random forest data modeling. , 2009, Analytica chimica acta.

[26]  Ulrike Groemping,et al.  Relative Importance for Linear Regression in R: The Package relaimpo , 2006 .

[27]  Alexander J. Smola,et al.  Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.

[28]  Jan Ming Ko,et al.  Neural Network Novelty Filtering for Anomaly Detection , 1999 .

[29]  Babak Moaveni,et al.  Environmental effects on the identified natural frequencies of the Dowling Hall Footbridge , 2011 .

[30]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[31]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[32]  R. Cole,et al.  Structural health monitoring of the Tamar suspension bridge , 2013 .

[33]  Ian F. C. Smith,et al.  Model-free data interpretation for continuous monitoring of complex structures , 2008, Adv. Eng. Informatics.

[34]  W. J. Langford.  Statistical Methods , 1959, Nature.

[35]  Wolfgang Graf,et al.  Prediction of Time-Dependent Structural Behavior with Recurrent Neural Networks , 2011, ISEC 2011.

[36]  Wolfgang Graf,et al.  Prediction of time-dependent structural behaviour with recurrent neural networks for fuzzy data , 2011 .

[37]  Ian F. C. Smith,et al.  Feature Selection Using Stochastic Search: An Application to System Identification , 2010, J. Comput. Civ. Eng..

[38]  Ka-Veng Yuen,et al.  Ambient interference in long-term monitoring of buildings , 2010 .

[39]  R Cole,et al.  Innovative structural health monitoring for Tamar Suspension Bridge by automated total positioning system , 2010 .

[40]  Guido De Roeck,et al.  One-year monitoring of the Z24-Bridge : environmental effects versus damage events , 2001 .

[41]  Leena A Nylander-French,et al.  Quantifying the Relative Importance of Predictors in Multiple Linear Regression Analyses for Public Health Studies , 2008, Journal of occupational and environmental hygiene.

[42]  Ian F. C. Smith,et al.  Fundamentals of Computer-Aided Engineering , 2003 .

[43]  Jian Zhang,et al.  Experimental verification of the support vector regression based structural identification method by using shaking table test data , 2008 .

[44]  Guido De Roeck,et al.  EFFECT OF TEMPERATURE ON DYNAMIC SYSTEM PARAMETERS OF A HIGHWAY BRIDGE , 1997 .

[45]  Deng Yang,et al.  Structural condition assessment of long-span suspension bridges using long-term monitoring data , 2010 .

[46]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[47]  Masayoshi Tomizuka,et al.  Smart Structures and Materials 2005: Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems , 2005 .

[48]  Ian F. C. Smith,et al.  Methodologies for model-free data interpretation of civil engineering structures , 2010 .

[49]  J. Franklin,et al.  The elements of statistical learning: data mining, inference and prediction , 2005 .

[50]  Chan Ghee Koh,et al.  An improved substructural identification strategy for large structural systems , 2012 .