Anomaly detection for large span bridges during operational phase using structural health monitoring data

In view of the limitation of damage detection in practical applications for large scale civil structures, a practical method for anomaly detection is developed. Within the anomaly detection framework, wavelet transform and generalized Pareto distribution (GPD) are adopted for data processing. In detail, to reduce the influence of thermal responses on signal fluctuations induced by anomaly events, wavelet transform is employed to separate thermal effects from raw signals based on the distinguished frequency bandwidths. Subsequently, a two-level anomaly detection method is proposed, i.e. threshold-based anomaly detection and anomaly trend detection. For the threshold-based anomaly detection, the threshold for anomaly detection is determined by GPD analytics, corresponding to a 95% guarantee rate within 100 years. Moreover, the threshold is periodically updated by incorporating the latest monitoring data to model the increase of traffic volumes and gradual degradations of structures. For the anomaly trend detection, the moving fast Fourier transform is adopted for discussion. Finally, the mid-span deflection of Xihoumen Suspension Bridge is selected as the index to validate the effectiveness of the proposed methodology. Two types of anomaly events are assumed in the case study, i.e. the overloading event and structural damage. The two-level anomaly detection is implemented. It is indicated through the case study that the proposed anomaly detection approach (without the influence of temperature) is able to detect three 100 ton overloaded vehicles and damages in main cables. However, the assumed cases subject to 100 ton vehicle and damages in stiffening girders are hardly detected by using the deflection index, owing to the sensitivity of the index to each anomaly event. In the future studies, a structural health monitoring-based multi-index anomaly detection system is promising to ensure the operational and structural safety of large span bridges.

[1]  Yi-Qing Ni,et al.  Damage Localization of Cable-Supported Bridges Using Modal Frequency Data and Probabilistic Neural Network , 2014 .

[2]  Rongrong Hou,et al.  Temperature-induced displacement of supertall structures: A case study , 2018, Advances in Structural Engineering.

[3]  Min Xie,et al.  Development of RVM-Based Multiple-Output Soft Sensors With Serial and Parallel Stacking Strategies , 2019, IEEE Transactions on Control Systems Technology.

[4]  Yi-Qing Ni,et al.  Refinement of damage identification capability of neural network techniques in application to a suspension bridge , 2015 .

[5]  Limin Sun,et al.  Mechanisms of thermally induced deflection of a long-spancable-stayed bridge , 2015 .

[6]  Qiao Huang,et al.  Condition evaluation of suspension bridges for maintenance, repair and rehabilitation: a comprehensive framework , 2019, Structure and Infrastructure Engineering.

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

[8]  Chao Sun,et al.  Vibration based bridge scour evaluation: A data-driven method using support vector machines , 2019 .

[9]  Jian Zhang,et al.  Experimental Study of Thermal Effects on a Long-Span Suspension Bridge , 2017 .

[10]  Fayaz R. Rofooei,et al.  Damage detection in existing reinforced concrete building using forced vibration test based on mode shape data , 2017 .

[11]  Yi-Qing Ni,et al.  Time synchronization for acceleration measurement data of Jiangyin Bridge subjected to a ship collision , 2018 .

[12]  Bo Chen,et al.  Monitoring temperature effect on a long suspension bridge , 2009 .

[13]  Daniele Inaudi,et al.  A temperature-driven MPCA method for structural anomaly detection , 2019, Engineering Structures.

[14]  Linren Zhou,et al.  Field monitoring and numerical simulation of the thermal actions of a supertall structure , 2017 .

[15]  He Xia,et al.  Bridge Damage Identification from Moving Load Induced Deflection Based on Wavelet Transform and Lipschitz Exponent , 2015 .

[16]  Jing Zhou,et al.  A novel transmissibility concept based on wavelet transform for structural damage detection , 2013 .

[17]  O. S. Salawu.  Detection of structural damage through changes in frequency: a review , 1997 .

[18]  Bin Liu,et al.  Stochastic Filtering Approach for Condition-Based Maintenance Considering Sensor Degradation , 2020, IEEE Transactions on Automation Science and Engineering.

[19]  S. Hao,et al.  I-35W Bridge Collapse , 2010 .

[20]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[21]  Yanjie Zhu,et al.  Thermal strain extraction methodologies for bridge structural condition assessment , 2018, Smart Materials and Structures.

[22]  Prakash Kripakaran,et al.  Data-driven approaches for measurement interpretation: analysing integrated thermal and vehicular response in bridge structural health monitoring , 2017, Adv. Eng. Informatics.

[23]  Piotr Omenzetter,et al.  Sequential projection pursuit for optimised vibration-based damage detection in an experimental wind turbine blade , 2018 .

[24]  Xiaoyi Bao,et al.  Wavelet Denoising Method for Improving Detection Performance of Distributed Vibration Sensor , 2012, IEEE Photonics Technology Letters.

[25]  Prakash Kripakaran,et al.  Predicting thermal response of bridges using regression models derived from measurement histories , 2014 .

[26]  L. H. Yam,et al.  Vibration-based damage detection for composite structures using wavelet transform and neural network identification , 2003 .

[27]  Piotr Omenzetter,et al.  Improved statistical damage classification in an experimental wind turbine blade based on vector autoregressive coefficients and sequential projection pursuit , 2018, Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[28]  Sang-Ho Yun,et al.  Long-Term Deflection Monitoring for Bridges Using X and C-Band Time-Series SAR Interferometry , 2019, Remote. Sens..

[29]  He Yi,et al.  Damage identification method for continuous girder bridges based on spatially-distributed long-gauge strain sensing under moving loads , 2018 .

[30]  Yi-Qing Ni,et al.  Damage detection utilising the artificial neural network methods to a benchmark structure , 2011 .

[31]  Wen-Hwa Wu,et al.  Damage detection of a cable-stayed bridge based on the variation of stay cable forces eliminating environmental temperature effects , 2016 .

[32]  C. S. Cai,et al.  Deflection monitoring and assessment for a suspension bridge using a connected pipe system: a case study in China , 2015 .

[33]  C. Cai,et al.  Bridge Scour Identification and Field Application Based on Ambient Vibration Measurements of Superstructures , 2019, Journal of Marine Science and Engineering.

[34]  Yong Huang,et al.  Diagnosis and accuracy enhancement of compressive-sensing signal reconstruction in structural health monitoring using multi-task sparse Bayesian learning , 2019, Smart Materials and Structures.

[35]  Y. Ni,et al.  Mode localization characteristics of damaged quasiperiodically supported beam structures with local weak coupling , 2019, Structural Control and Health Monitoring.

[36]  Youliang Ding,et al.  Structural Damage Warning of a Long-Span Cable-Stayed Bridge Using Novelty Detection Technique Based on Wavelet Packet Analysis , 2010 .

[37]  Kuo-Chun Chang,et al.  Evaluation of bridge instability caused by dynamic scour based on fractal theory , 2013 .

[38]  Suren Chen,et al.  Serviceability assessment for long‐span suspension bridge based on deflection measurements , 2018, Structural Control and Health Monitoring.

[39]  Yuan Ren,et al.  Sensor fault diagnosis for bridge monitoring systemusing similarity of symmetric responses , 2019 .

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

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

[42]  Hongnan Li,et al.  Wireless sensor placement for structural monitoring using information-fusing firefly algorithm , 2017 .

[43]  Keith Worden,et al.  Cointegration: a novel approach for the removal of environmental trends in structural health monitoring data , 2011, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[44]  Li Cheng,et al.  Development in vibration-based structural damage detection technique , 2007 .

[45]  Yi Zhou,et al.  Insights into temperature effects on structural deformation of a cable-stayed bridge based on structural health monitoring , 2018, Structural Health Monitoring.

[46]  Xiang Xu,et al.  Long-term condition evaluation for stay cable systems using dead load–induced cable forces , 2019, Advances in Structural Engineering.

[47]  Aiqun Li,et al.  Investigation of temperature actions on flat steel box girders of long-span bridges with temperature monitoring data , 2018 .

[48]  Youliang Ding,et al.  Research on seasonal correlation of wavelet packet energy spectrum and temperature of Runyang Suspension Bridge , 2009 .

[49]  Wei Lu,et al.  Identification of damage in dome-like structures using hybrid sensor measurements and artificial neural networks , 2013 .

[50]  Qiao Huang,et al.  Modeling and Separation of Thermal Effects from Cable-Stayed Bridge Response , 2019, Journal of Bridge Engineering.

[51]  Franklin Moon,et al.  Temperature-based structural health monitoring baseline for long-span bridges , 2015 .