Constructing input to neural networks for modeling temperature-caused modal variability: Mean temperatures, effective temperatures, and principal components of temperatures

Abstract In this study, the construction of appropriate input to neural networks for modeling the temperature-caused modal variability is addressed with intent to enhance the reproduction and prediction capabilities of the formulated correlation models. Available for this study are 770 h modal frequency and temperature data that were obtained from the instrumented cable-stayed Ting Kau Bridge in Hong Kong. With the temperature data measured at different portions of the bridge, three kinds of input, i.e., mean temperatures, effective temperatures, and principal components (PCs) of temperatures, are constructed as input to neural networks for modeling the correlation between the modal frequencies and environmental temperatures. By dividing the 770 h modal frequency and temperature data into training data set, validation data set and testing data set, an optimally configured back-propagation neural network (BPNN) is formulated for each kind of input, in which the validation data are utilized to determine the optimal number of hidden nodes while the early stopping technique is applied to optimize the BPNN parameters. Then the reproduction and prediction performance of the BPNNs configured with the three kinds of input is examined and compared in respect of the seen training data set and the unseen testing data set, respectively. It is revealed that the temperature profile characterized by the effective temperatures is insufficient for formulating a good correlation model between the modal frequencies and temperatures. When a sufficient number of PCs are used, the BPNN with input of the PCs of temperatures performs better than the BPNN with input of the mean temperatures in both reproduction and prediction capabilities.

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

[2]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[3]  Darryll J. Pines,et al.  Status of structural health monitoring of long-span bridges in the United States , 2002 .

[4]  H. Hao,et al.  Long term vibration monitoring of an RC slab: Temperature and humidity effect , 2006 .

[5]  Norris Stubbs,et al.  Documentation of Changes in Modal Properties of a Concrete Box‐Girder Bridge Due to Environmental and Internal Conditions , 2001 .

[6]  Kai-Yuen Wong,et al.  Instrumentation and health monitoring of cable‐supported bridges , 2004 .

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

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

[9]  Dongning Li,et al.  Thermal design criteria for deep prestressed concrete girders based on data from Confederation Bridge , 2004 .

[10]  I. Jolliffe.  Principal Component Analysis , 2002 .

[11]  S. Alampalli,et al.  EFFECTS OF TESTING, ANALYSIS, DAMAGE, AND ENVIRONMENT ON MODAL PARAMETERS , 2000 .

[12]  Hyun-Man Cho,et al.  Vibration-Based Damage Monitoring in Model Plate-Girder Bridges under Uncertain Temperature Conditions , 2007 .

[13]  Hoon Sohn,et al.  Environmental variability of modal properties , 1999 .

[14]  Walter H. Dilger,et al.  Extreme values of thermal loading parameters in concrete bridges , 1992 .

[15]  Jin-Hak Yi,et al.  Temperature effects on frequency-based damage detection in plate-girder bridges , 2003 .

[16]  Jan Ming Ko,et al.  Automatic modal identification and variability in measured modal vectors of a cable-stayed bridge , 2005 .

[17]  Charles R. Farrar,et al.  Variability of modal parameters measured on the alamosa canyon bridge , 1996 .

[18]  Klaus-Robert Müller,et al.  Asymptotic statistical theory of overtraining and cross-validation , 1997, IEEE Trans. Neural Networks.

[19]  Yi-Qing Ni,et al.  Technology developments in structural health monitoring of large-scale bridges , 2005 .

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

[21]  Yi-Qing Ni,et al.  Assessment of Bridge Expansion Joints Using Long-Term Displacement and Temperature Measurement , 2007 .

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

[23]  J. E. Harding,et al.  Bridge Management: Inspection, Maintenance, Assessment and Repair , 1990 .

[24]  Yozo Fujino,et al.  System identification of suspension bridge from ambient vibration response , 2008 .

[25]  Yozo Fujino,et al.  Structural Health Monitoring and Intelligent Infrastructure , 2005 .

[26]  Hervé Bourlard,et al.  Generalization and Parameter Estimation in Feedforward Netws: Some Experiments , 1989, NIPS.

[27]  Michael Schlaich,et al.  Ting Kau Bridge, Hong Kong , 1996 .

[28]  Jm Ko,et al.  Eliminating temperature effect in structural damage alarming using auto-associative neural networks , 2007 .

[29]  Ming L. Wang,et al.  Observed Variations of Mode Frequencies of a Prestressed Concrete Bridge with Temperature , 2000 .

[30]  Fu-Kuo Chang,et al.  Structural Health Monitoring 2007: Quantification, Validation and Implementation , 2007 .

[31]  John H G Macdonald,et al.  Variation of modal parameters of a cable-stayed bridge identified from ambient vibration measurements and FE modelling , 2005 .

[32]  Charles R. Farrar,et al.  Comparative study of damage identification algorithms applied to a bridge: I. Experiment , 1998 .

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

[34]  Filipe Magalhães,et al.  Dynamic monitoring of a long span arch bridge , 2008 .

[35]  Jeong-Ho Kim,et al.  Development of a baseline for structural health monitoring for a curved post-tensioned concrete box–girder bridge , 2009 .

[36]  Rolf G. Rohrmann,et al.  Structural causes of temperature affected modal data of civil structures obtained by long time monitoring , 2000 .

[37]  G P Roberts,et al.  DYNAMIC MONITORING AS A TOOL FOR LONG SPAN BRIDGES , 1996 .

[38]  Kai-Yuen Wong,et al.  Design of a structural health monitoring system for long-span bridges , 2007 .