BWIM aided damage detection in bridges using machine learning

In this study, a new, model-free damage detection method is proposed and validated on a simple numerical experiment. The proposed algorithm used vibration data (deck accelerations) and bridge weigh-in-motion data (load magnitude and position) to train a two-stage machine learning setup to classify the data into healthy or damaged. The proposed method is composed in its first stage of an artificial neural network and on the second stage of a gaussian process. The proposed method is applicable to railway bridges, since it takes advantage of the fact that vehicles of known axle configuration cross the bridge regularly, that normally only one train is on the bridge at a time and that the lateral positioning of the loads does not change. The novelty of the proposed algorithm is that it makes use of the data on the load’s position, magnitude and speed that can be obtained from a Bridge Weigh-in-Motion system to improve the accuracy of the damage detection algorithm.

[1]  A. Žnidarič,et al.  Experimental Testing of a Moving Force Identification Bridge Weigh-in-Motion Algorithm , 2009 .

[2]  Billie F. Spencer,et al.  A damage localization method based on the ‘jerk energy’ , 2014 .

[3]  Raid Karoumi,et al.  Implementing bridge weigh-in-motion for railway traffic , 2007 .

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

[5]  Cai Qun,et al.  Structural Health Monitoring and Damage Detection Using Neural Networks , 2013, 2013 Third International Conference on Intelligent System Design and Engineering Applications.

[6]  Teerachai Deesomsuk,et al.  Evaluation of effectiveness of vehicle weight estimations using bridge weigh-in-motion , 2010 .

[7]  Yi-Qing Ni,et al.  Investigation concerning structural health monitoring of an instrumented cable-stayed bridge , 2009 .

[8]  Eugene J. O'Brien,et al.  Investigating the Use of Moving Force Identification Theory in Bridge Damage Detection , 2013 .

[9]  Robert B. Randall,et al.  APPLICATION OF CEPSTRUM ANALYSIS AND ARTIFICIAL NEURAL NETWORKS FOR THE DAMAGE IDENTIFICATION OF A TWO-STOREY FRAMED STRUCTURE BASED ON RESPONSE-ONLY MEASUREMENTS , 2013 .

[10]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[11]  Zhishen Wu,et al.  A model-free damage identification method for flexural structures using dynamic measurements from distributed long-gage macro-strain sensors , 2014 .

[12]  Mahir Ülker-Kaustell,et al.  Seasonal effects on the stiffness properties of a ballasted railway bridge , 2013 .

[13]  Ian F. C. Smith,et al.  Combined Model-Free Data-Interpretation Methodologies for Damage Detection during Continuous Monitoring of Structures , 2013, J. Comput. Civ. Eng..

[14]  Arturo González,et al.  The Virtual Axle concept for detection of localised damage using Bridge Weigh-in-Motion data , 2015 .

[15]  Charles R. Farrar,et al.  A Bayesian approach based on a Markov-chain Monte Carlo method for damage detection under unknown sources of variability , 2014 .

[16]  Peter J. Braspenning,et al.  Artificial Neural Networks: An Introduction to ANN Theory and Practice , 1995, Artificial Neural Networks.

[17]  Christian Cremona,et al.  Static-based early-damage detection using symbolic data analysis and unsupervised learning methods , 2015 .

[18]  Ian F. C. Smith,et al.  Damage detection using data-driven methods applied to moving-load responses , 2013 .

[19]  Soon Gie Lee,et al.  Reference-free damage detection for truss bridge structures by continuous relative wavelet entropy method , 2014 .

[20]  Lu Deng,et al.  Identification of parameters of vehicles moving on bridges , 2009 .

[21]  Jun Xu,et al.  The Theory and Case Study of Axle Load Identification Based on BWIM of Orthotropic Steel Deck , 2012 .

[22]  Jiangpeng Shu,et al.  The application of a damage detection method using Artificial Neural Network and train-induced vibrations on a simplified railway bridge model , 2013 .

[23]  Carl E. Rasmussen,et al.  Gaussian Processes for Machine Learning (GPML) Toolbox , 2010, J. Mach. Learn. Res..

[24]  Raid Karoumi,et al.  Traffic monitoring using a structural health monitoring system , 2015 .

[25]  R.M. da Costa Marques Pimentel,et al.  Hybrid Fiber-Optic/Electrical Measurement System for Characterization of Railway Traffic and Its Effects on a Short Span Bridge , 2008, IEEE Sensors Journal.