Deep learning for data anomaly detection and data compression of a long‐span suspension bridge

As intelligent sensing and sensor network systems have made progress and low‐cost online structural health monitoring has become possible and widely implemented, large quantities of highly heterogeneous data can be acquired during the monitoring. This has resulted in exceeding the capacity of traditional data analytics techniques, especially in monitoring large‐scale or critical civil structures. In particular, data storage has become a big challenge, hence, resulting in the emergence of data compression and reconstruction as a new area in structural health monitoring (SHM) of large infrastructure systems. SHM data generally include anomalies that can disturb structural analysis and assessment. The fundamental reasons for the abnormality of data are extremely complex. Therefore, reconstruction of the abnormal data is generally difficult and poses serious challenges to achieve high‐accuracy after data has been compressed. Considering these significant challenges, in this paper, a novel deep‐learning‐enabled data compression and reconstruction framework is proposed that can be divided into two phases: (a) a one‐dimensional Convolutional Neural Network (CNN) that extracts features directly from the input signals is designed to detect abnormal data with validated high accuracy; (b) a new SHM data compression and reconstruction method based on Autoencoder structure is further developed, which can recover the data with high‐accuracy under such a low compression ratio. To validate the proposed approach, acceleration data from the SHM system of a long‐span bridge in China are employed. In the abnormal data detection phase, the results show that the proposed method can detect anomaly with high accuracy. Subsequently, smaller reconstruction errors can be achieved even by using only 10% compression ratio for the normal data.

[1]  Liming Zhou,et al.  A methodology for obtaining spatiotemporal information of the vehicles on bridges based on computer vision , 2019, Comput. Aided Civ. Infrastructure Eng..

[2]  Jian Zhang,et al.  Zernike‐moment measurement of thin‐crack width in images enabled by dual‐scale deep learning , 2018, Comput. Aided Civ. Infrastructure Eng..

[3]  Hui Li,et al.  Convolutional neural network‐based data anomaly detection method using multiple information for structural health monitoring , 2018, Structural Control and Health Monitoring.

[4]  Jian Zhang,et al.  Pixel‐level crack delineation in images with convolutional feature fusion , 2018, Structural Control and Health Monitoring.

[5]  Jun Li,et al.  Structural damage identification based on autoencoder neural networks and deep learning , 2018, Engineering Structures.

[6]  Hui Li,et al.  Compressive sensing of wireless sensors based on group sparse optimization for structural health monitoring , 2018 .

[7]  Hojjat Adeli,et al.  A novel unsupervised deep learning model for global and local health condition assessment of structures , 2018 .

[8]  Ying Wang,et al.  Sparse representation approach to data compression for strain-based traffic load monitoring: A comparative study , 2017, Measurement.

[9]  Yi-Zhou Lin,et al.  Structural Damage Detection with Automatic Feature‐Extraction through Deep Learning , 2017, Comput. Aided Civ. Infrastructure Eng..

[10]  Ting-Hua Yi,et al.  Development of sensor validation methodologies for structural health monitoring: A comprehensive review , 2017 .

[11]  Hojjat Adeli,et al.  A New Neural Dynamic Classification Algorithm , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Oral Büyüköztürk,et al.  Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks , 2017, Comput. Aided Civ. Infrastructure Eng..

[13]  Ting-Hua Yi,et al.  Canonical correlation analysis based fault diagnosis method for structural monitoring sensor networks , 2016 .

[14]  Gangbing Song,et al.  Detection of Shifts in GPS Measurements for a Long-Span Bridge Using CUSUM Chart , 2016 .

[15]  Seunghoon Hong,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[16]  Xigang Zhang,et al.  Research and practice of health monitoring for long-spanbridges in the mainland of China , 2015 .

[17]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[19]  ChangKyoo Yoo,et al.  Evaluation of passenger health risk assessment of sustainable indoor air quality monitoring in metro systems based on a non-Gaussian dynamic sensor validation method. , 2014, Journal of hazardous materials.

[20]  K. Lakshmi,et al.  A Sensor Fault Detection Algorithm for Structural Health Monitoring Using Adaptive Differential Evolution , 2014 .

[21]  Hui Li,et al.  SMC structural health monitoring benchmark problem using monitored data from an actual cable‐stayed bridge , 2014 .

[22]  Sami F. Masri,et al.  Application of statistical monitoring using latent-variable techniques for detection of faults in sensor networks , 2014 .

[23]  Yan Yu,et al.  Compressive sampling–based data loss recovery for wireless sensor networks used in civil structural health monitoring , 2013 .

[24]  Reza Langari,et al.  Sensor fault diagnosis with a probabilistic decision process , 2013 .

[25]  Yann LeCun,et al.  What is the best multi-stage architecture for object recognition? , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[26]  Sami F. Masri,et al.  Multivariate Statistical Analysis for Detection and Identification of Faulty Sensors Using Latent Variable Methods , 2008 .

[27]  E.J. Candes.  Compressive Sampling , 2022 .

[28]  Bhaskar D. Rao,et al.  Sparse Bayesian learning for basis selection , 2004, IEEE Transactions on Signal Processing.