Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Detection of multi-type data anomaly for structural health monitoring using pattern recognition neural network

  • Gao, Ke (School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology) ;
  • Chen, Zhi-Dan (School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology) ;
  • Weng, Shun (School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology) ;
  • Zhu, Hong-Ping (School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology) ;
  • Wu, Li-Ying (School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology)
  • Received : 2021.04.14
  • Accepted : 2021.08.12
  • Published : 2022.01.25
⟨ Previous Next ⟩

Abstract

The effectiveness of system identification, damage detection, condition assessment and other structural analyses relies heavily on the accuracy and reliability of the measured data in structural health monitoring (SHM) systems. However, data anomalies often occur in SHM systems, leading to inaccurate and untrustworthy analysis results. Therefore, anomalies in the raw data should be detected and cleansed before further analysis. Previous studies on data anomaly detection mainly focused on just single type of data anomaly for denoising or removing outliers, meanwhile, the existing methods of detecting multiple data anomalies are usually time consuming. For these reasons, recognising multiple anomaly patterns for real-time alarm and analysis in field monitoring remains a challenge. Aiming to achieve an efficient and accurate detection for multi-type data anomalies for field SHM, this study proposes a pattern-recognition-based data anomaly detection method that mainly consists of three steps: the feature extraction from the long time-series data samples, the training of a pattern recognition neural network (PRNN) using the features and finally the detection of data anomalies. The feature extraction step remarkably reduces the time cost of the network training, making the detection process very fast. The performance of the proposed method is verified on the basis of the SHM data of two practical long-span bridges. Results indicate that the proposed method recognises multiple data anomalies with very high accuracy and low calculation cost, demonstrating its applicability in field monitoring.

Keywords

Acknowledgement

This work was financially supported by the grants from the National Natural Science Foundation of China (NSFC, contract number: 51922046, 51778258 and 51838006), Research Grants Council of the Hong Kong Special Administrative Region, China (Project No. PolyU 152621/16E), and the Research Funds from China Railway Eryuan Engineering Group CO.LTD (KYY2019029), and the Research Fund of China Railway Siyuan Survey and Design Group CO.LTD (contract number: 2020K006).

References

  1. Alessandra, D., Salvatore, G., Giuseppe, L., Fabrizio, M. and Marco, O. (2015), "Adaptive distributed outlier detection for WSNs", IEEE T. Cybernetics, 45(5), 888-899. https://doi.org/10.1109/TCYB.2014.2338611
  2. Bao, Y., Tang Z., Li, H. and Zhang, Y. (2019a), "Computer vision and deep learning-based data anomaly detection method for structural health monitoring", Struct. Health Monitor., 18(2), 401-421. https://doi.org/10.1177/1475921718757405
  3. Bao, Y., Chen Z., Wei, S., Xu, Y., Tang, Z. and Li, H. (2019b), "The state of the art of data science and engineering in structural health monitoring", Engineering, 5(2), 234-242. https://doi.org/10.1016/j.eng.2018.11.027
  4. Bao, Y., Li, J., Nagayama, T., Xu, Y., Spencer Jr, B.F. and Li, H. (2021), "The 1st International Project Competition for Structural Health Monitoring (IPC-SHM, 2020): A summary and benchmark problem. Struct. Health Monitor., 20(4), 2229-2239. https://doi.org/10.1177/14759217211006485
  5. Banjanovic-Mehmedovic, L., Hajdarevic, A., Kantardzic, M., Mehmedovic, F. and Dzananovic, I. (2017), "Neural network-based data-driven modelling of anomaly detection in thermal power plant", Automatika, 58(1), 69-79. https://doi.org/10.1080/00051144.2017.1343328
  6. Bishop, C. (1995), Neural Networks for Pattern Recognition, Clarendon Press, Oxford, UK.
  7. Bishop, C. (2006), Pattern Recognition and Machine Learning, Springer Press, Cambridge, UK.
  8. Cai, S., Li, L., Li, S., Sun, R. and Yuan, G. (2020), "An efficient approach for outlier detection from uncertain data streams based on maximal frequent patterns", Expert Syst. Appl., 160, 113646. https://doi.org/10.1016/j.eswa.2020.113646
  9. Calabrese, L., Campanella, G. and Proverbio, E. (2012), "Noise removal by cluster analysis after long time AE corrosion monitoring of steel reinforcement in concrete", Constr. Build. Mater., 34, 362-371. https://doi.org/10.1016/j.conbuildmat.2012.02.046
  10. Chang, C., Chou, J., Tan, P. and Wang, L. (2017), "A sensor fault detection strategy for structural health monitoring systems", Smart Struct. Syst., Int. J., 20(1), 43-52. https://doi.org/10.12989/sss.2017.20.1.043
  11. Chen, Z., Li, H. and Bao, Y. (2019), "Analyzing and modeling inter-sensor relationships for strain monitoring data and missing data imputation: a copula and functional data-analytic approach", Struct. Health Monitor., 18(4), 1168-1188. https://doi.org/10.1177/1475921718788703
  12. Fu, Y., Peng, C., Gomez, F., Narazaki, Y. and Spencer Jr., B. (2019), "Sensor fault management techniques for wireless smart sensor networks in structural health monitoring", Struct. Control Health., 26(7), e2362. https://doi.org/10.1002/stc.2362
  13. Gul, M. and Catbas, F. (2009), "Statistical pattern recognition for structural health monitoring using time series modeling: Theory and experimental verifications", Mech. Syst. Signal Process., 23(7), 2192-2204. https://doi.org/10.1016/j.ymssp.2009.02.013
  14. Huang, H., Yi, T. and Li, H. (2020), "Anomaly identification of structural health monitoring data using dynamic independent component analysis", J. Comput. Civil. Eng., 34(5), 04020025. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000905
  15. Jiang, X., Mahadevan, S. and Adeli, H. (2007), "Bayesian wavelet packet denoising for structural system identification", Struct. Control Health., 14(2), 333-356. https://doi.org/10.1002/stc.161
  16. Karthick, P., Ghosh, D.M. and Ramakrishnan, S. (2018), "Surface electromyography based muscle fatigue detection using high-resolution time-frequency methods and machine learning algorithms", Comput. Meth. Prog. Bio., 154, 45-56. https://doi.org/10.1016/j.cmpb.2017.10.024
  17. Katicha, S., Flintsch, G., Bryce, J. and Ferne, B. (2014), "Wavelet denoising of TSD deflection slope measurements for improved pavement structural evaluation", Comput.-Aided Civil Infrastr. Eng., 29(6), 399-415. https://doi.org/10.1111/mice.12052
  18. Kavzoglu, T. (2009), "Increasing the accuracy of neural network classification using refined training data", Environ. Modell. Softw., 24(7), 850-858. https://doi.org/10.1016/j.envsoft.2008.11.012
  19. Kullaa, J. (2013), "Detection, identification, and quantification of sensor fault in a sensor network", Mech. Syst. Signal. Pr., 40(1), 208-221. https://doi.org/10.1016/j.ymssp.2013.05.007
  20. Lejla, B., Amel, H., Mehmed, K., Fahrudin, M. and Izet, D. (2017), "Neural network-based data-driven modelling of anomaly detection in thermal power plant", Automatika, 58(1), 69-79. https://doi.org/10.1080/00051144.2017.1343328
  21. Li, M. and Yuan, B. (2005), "2D-LDA: A statistical linear discriminant analysis for image matrix", Pattern Recogn. Lett., 26(5), 527-532. https://doi.org/10.1016/j.patrec.2004.09.007
  22. Luo, Y., Ye, Z., Guo, X., Qiang, X. and Chen, X. (2015), "Data missing mechanism and missing data real-time processing methods in the construction monitoring of steel structures", Adv. Struct. Eng., 18(4), 585-601. https://doi.org/10.1260/1369-4332.18.4.585
  23. Ni, K., Ramanathan, N., Chehade, M., Balzano, L., Nair, S., Zahedi, S., Kohler, E., Pottie, G., Hansen, M. and Srivastava, M. (2009), "Sensor network data fault types", ACM Transct. Sensor Network, 5(3), 1-29. https://doi.org/10.1145/1525856.1525863
  24. Nick, H. and Aziminejad, A. (2021), "Vibration-Based Damage Identification in Steel Girder Bridges Using Artificial Neural Network Under Noisy Conditions", J. Nondestruct. Eval., 40(1), 15. https://doi.org/10.1007/s10921-020-00744-8
  25. Peng, Y., Qiao, W., Qu, L. and Wang, J. (2018), "Sensor fault detection and isolation for a wireless sensor network-based remote wind turbine condition monitoring system", IEEE Transact. Ind. Appl., 54(2), 1072-1079. https://doi.org/10.1109/IAS.2017.8101845
  26. Smarsly, K. and Law, K. (2014), "Decentralized fault detection and isolation in wireless structural health monitoring systems using analytical redundancy", Adv. Eng. Softw., 73, 1-10. https://doi.org/10.1016/j.advengsoft.2014.02.005
  27. Tian, W., Weng, S., Xia, Y., Zhu, H., Gao, F., Sun, Y. and Li, J. (2019), "An iterative reduced-order substructuring approach to the calculation of eigensolutions and eigensensitivities", Mech. Syst. Signal. Pr., 130, 361-377. https://doi.org/10.1016/j.ymssp.2019.05.006
  28. Titouna, C., Nait-Abdesselam, F. and Khokhar, A. (2019), "DODS: A distributed outlier detection scheme for wireless sensor networks", Comput. Networks, 161, 93-101. https://doi.org/10.1016/j.comnet.2019.06.014
  29. Venugopal, G., Navaneethakrishna, M. and Ramakrishnan, S. (2014), "Extraction and analysis of multiple time window features associated with muscle fatigue conditions using sEMG signals", Expert Syst. Appl., 41(6), 2652-2659. https://doi.org/10.1016/j.eswa.2013.11.009
  30. Wang, Y., Yang, A., Chen, X., Wang, P., Wang, Y. and Yang, H. (2017), "A deep learning approach for blind drift calibration of sensor networks", IEEE Sens. J., 17(13), 4158-4171. https://doi.org/10.1109/JSEN.2017.2703885
  31. Widodo, A. and Yang, B. (2007), "Support vector machine in machine condition monitoring and fault diagnosis", Mech. Syst. Signal. Pr., 21(6), 2560-2574. https://doi.org/10.1016/j.ymssp.2006.12.007
  32. Yang, Y. and Nagarajaiah, S. (2014), "Blind denoising of structural vibration responses with outliers via principal component pursuit", Struct. Control Health., 21(6), 962-978. https://doi.org/10.1002/stc.1624
  33. Yang, Y. and Nagarajaiah, S. (2016), "Harnessing data structure for recovery of randomly missing structural vibration responses time history: Sparse representation versus low-rank structure", Mech. Syst. Signal. Pr., 74, 165-182. https://doi.org/10.1016/j.ymssp.2015.11.009
  34. Yuen, K. and Mu, H. (2012), "A novel probabilistic method for robust parametric identification and outlier detection", Probabilist. Eng. Mech., 30, 48-59. https://doi.org/10.1016/j.probengmech.2012.06.002
  35. Yuen, K. and Ortiz, G. (2017), "Outlier detection and robust regression for correlated data", Comput. Method Appl. Mech. Eng., 313, 632-646. https://doi.org/10.1016/j.cma.2016.10.004
  36. Zhang, Z. and Luo, Y. (2017), "Restoring method for missing data of spatial structural stress monitoring based on correlation", Mech. Syst. Signal. Pr., 91, 266-277. https://doi.org/10.1016/j.ymssp.2017.01.018
  37. Zhang, Z., Mehmood, A., Shu, L., Huo, Z., Zhang, Y. and Mukherjee, M. (2018), "A survey on fault diagnosis in wireless sensor networks", IEEE Access, 6, 11349-11364. https://doi.org/10.1109/ACCESS.2018.2794519
  38. Zhu, H., Gao, K., Xia, Y., Gao, F., Weng, S., Sun, Y. and Hu, Q. (2020), "Multi-rate data fusion for dynamic displacement measurement of beam-like supertall structures using acceleration and strain sensors", Struct. Health Monitor., 19(2), 520-536. https://doi.org/10.1177/1475921719857043
  39. Zvokelj, M., Zupan, S. and Prebil, I. (2011), "Non-linear multivariate and multiscale monitoring and signal denoising strategy using Kernel Principal Component Analysis combined with Ensemble Empirical Mode Decomposition method", Mech. Syst. Signal. Pr., 25, 2631-2653. https://doi.org/10.1016/j.ymssp.2011.03.002