DOI QR코드

DOI QR Code

Deep learning-based anomaly detection in acceleration data of long-span cable-stayed bridges

  • Seungjun Lee (Department of Civil, Urban, Earth, and Environmental Engineering, Ulsan National Institute of Science and Technology (UNIST)) ;
  • Jaebeom Lee (Interdisciplinary Materials Measurement Institute, Korea Research Institute of Standards and Science (KRISS)) ;
  • Minsun Kim (Department of Civil, Urban, Earth, and Environmental Engineering, Ulsan National Institute of Science and Technology (UNIST)) ;
  • Sangmok Lee (Dam Safety Management Center, Korea Water Resources Corporation (K-water)) ;
  • Young-Joo Lee (Department of Civil, Urban, Earth, and Environmental Engineering, Ulsan National Institute of Science and Technology (UNIST))
  • Received : 2023.03.02
  • Accepted : 2023.12.28
  • Published : 2024.02.25

Abstract

Despite the rapid development of sensors, structural health monitoring (SHM) still faces challenges in monitoring due to the degradation of devices and harsh environmental loads. These challenges can lead to measurement errors, missing data, or outliers, which can affect the accuracy and reliability of SHM systems. To address this problem, this study proposes a classification method that detects anomaly patterns in sensor data. The proposed classification method involves several steps. First, data scaling is conducted to adjust the scale of the raw data, which may have different magnitudes and ranges. This step ensures that the data is on the same scale, facilitating the comparison of data across different sensors. Next, informative features in the time and frequency domains are extracted and used as input for a deep neural network model. The model can effectively detect the most probable anomaly pattern, allowing for the timely identification of potential issues. To demonstrate the effectiveness of the proposed method, it was applied to actual data obtained from a long-span cable-stayed bridge in China. The results of the study have successfully verified the proposed method's applicability to practical SHM systems for civil infrastructures. The method has the potential to significantly enhance the safety and reliability of civil infrastructures by detecting potential issues and anomalies at an early stage.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2021R1C1C2008770), and the authors would like to thank the organizers of the 1st International Project Competition for SHM (IPC-SHM, 2020) for providing the invaluable data used in this paper.

References

  1. Abdi, H. and Williams, L.J. (2010), "Principal component analysis", Wiley Interdiscipl. Reviews: Computat. Statist., 2(4), 433-459. https://doi.org/10.1002/wics.101 
  2. Altin, C. and Er, O. (2016), "Comparison of different time and frequency domain feature extraction methods on elbow gesture's EMG", Eur. J. Interdiscipl. Stud., 2(3), 35-44. https://doi.org/10.26417/ejis.v2i3.p35-44 
  3. Ansari, F. (2007), "Practical implementation of optical fiber sensors in civil structural health monitoring", J. Intell. Mater. Syst. Struct., 18(8), 879-889. https://doi.org/10.1177/1045389X06075760 
  4. Arangio, S. and Bontempi, F. (2015), "Structural health monitoring of a cable-stayed bridge with Bayesian neural networks", Struct. Infrastr. Eng., 11(4), 575-587. https://doi.org/10.1080/15732479.2014.951867 
  5. Arul, M. and Kareem, A. (2022), "Data anomaly detection for structural health monitoring of bridges using shapelet transform", Smart Struct. Syst., Int. J., 29(1), 93-103. https://doi.org/10.12989/sss.2022.29.1.093 
  6. Bakar, Z.A., Mohemad, R., Ahmad, A. and Deris, M.M. (2006), "A comparative study for outlier detection techniques in data mining", In: 2006 IEEE Conference on Cybernetics and Intelligent Systems, Bangkok, Thailand, June. 
  7. Bao, Y., Tang, Z., Li, H. and Zhang, Y. (2019), "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 
  8. 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 
  9. 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 
  10. Chou, J.-Y., Fu, Y., Huang, S.-K. and Chang, C.-M. (2022), "SHM data anomaly classification using machine learning strategies: A comparative study", Smart Struct. Syst., Int. J., 29(1), 77-91. https://doi.org/10.12989/sss.2022.29.1.077 
  11. Du, Y., Li, L., Hou, R., Wang, X., Tian, W. and Xia, Y. (2022), "Convolutional neural network-based data anomaly detection considering class imbalance with limited data", Smart Struct. Syst., Int. J., 29(1), 63-75. https://doi.org/10.12989/sss.2022.29.1.063 
  12. Fleming, J.F. and Egeseli, E.A. (1980), "Dynamic behaviour of a cable-stayed bridge", Earthq. Eng. Struct. Dyn., 8(1), 1-16. https://doi.org/10.1002/eqe.4290080102 
  13. 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 Monitor., 26, e2362. https://doi.org/10.1002/stc.2362 
  14. Gao, K., Chen, Z.-D., Weng, S., Zhu, H.-P. and Wu, L.-Y. (2022), "Detection of multi-type data anomaly for structural health monitoring using pattern recognition neural network", Smart Struct. Syst., Int. J., 29(1), 129-140. https://doi.org/10.12989/sss.2022.29.1.129 
  15. Khalid, S., Khalil, T. and Nasreen, S. (2014), "A survey of feature selection and feature extraction techniques in machine learning", In: 2014 Science and Information Conference, London, UK, October. https://doi.org/10.1109/SAI.2014.6918213 
  16. Kullaa, J. (2011), "Distinguishing between sensor fault, structural damage, and environmental or operational effects in structural health monitoring", Mech. Syst. Signal Process., 25(8), 2976-2989. https://doi.org/10.1016/j.ymssp.2011.05.017 
  17. Kullaa, J. (2013), "Detection, identification, and quantification of sensor fault in a sensor network", Mech. Syst. Signal Process., 40(1), 208-221. https://doi.org/10.1016/j.ymssp.2013.05.007 
  18. Kung, S.Y. and Diamantaras, K.I. (1990), "A neural network learning algorithm for adaptive principal component extraction (APEX)", In: International Conference on Acoustics, Speech, and Signal Processing, Albuquerque, NM, USA, August. 
  19. Lee, J., Lee, K.-C., Cho, S. and Sim, S.H. (2017), "Computer vision-based structural displacement measurement robust to light-induced image degradation for in-service bridges", Sensors, 17(10), 2317. https://doi.org/10.3390/s17102317 
  20. Lee, J., Lee, K.-C. and Lee, Y.-J. (2018), "Long-term deflection prediction from computer vision-measured data history for high-speed railway bridges", Sensors, 18(5), 1488. https://doi.org/10.3390/s18051488 
  21. Lee, J., Lee, K.-C., Sim, S.H., Lee, J. and Lee, Y.-J. (2019), "Bayesian Prediction of Pre-Stressed Concrete Bridge Deflection Using Finite Element Analysis", Sensors, 19(22), 4956. https://doi.org/10.3390/s19224956 
  22. Lee, J., Jeong, S., Lee, J., Sim, S.-H., Lee, K.-C. and Lee, Y.-J. (2022), "Sensor data-based probabilistic monitoring of timehistory deflections of railway bridges induced by high-speed trains", Struct. Health Monitor., 21(6), 2518-2530. https://doi.org/10.1177/14759217211063424 
  23. Li, H.N., Ren, L., Jia, Z.G., Yi, T.H. and Li, D.S. (2016), "Stateof-the-art in structural health monitoring of large and complex civil infrastructures", J. Civil Struct. Health Monitor., 6(1), 3-16. https://doi.org/10.1007/s13349-015-0108-9 
  24. Liu, G., Niu, Y., Zhao, W., Duan, Y. and Shu, J. (2022), "Data anomaly detection for structural health monitoring using a combination network of GANomaly and CNN", Smart Struct. Syst., Int. J., 29(1), 53-62. https://doi.org/10.12989/sss.2022.29.1.053 
  25. Manson, G. (2002), "Identifying damage sensitive, environment insensitive features for damage detection", Proceedings of the 3rd International Conference on Identification in Engineering Systems, Swansea, Wales, UK, April 
  26. Martakis, P., Movsessian, A., Reuland, Y., Pai, S.G.S., Quqa, S., Cava, D.G., Tcherniak, D. and Chatzi, E. (2022), "A semisupervised interpretable machine learning framework for sensor fault detection", Smart Struct. Syst., Int. J., 29(1), 251-266. https://doi.org/10.12989/sss.2022.29.1.251 
  27. Mei, H., Haider, M.F., Joseph, R., Migot, A. and Giurgiutiu, V. (2019), "Recent advances in piezoelectric wafer active sensors for structural health monitoring applications", Sensors, 19(2), 383. https://doi.org/10.3390/s19020383 
  28. Ni, F., Zhang, J. and Noori, M.N. (2020), "Deep learning for data anomaly detection and data compression of a long-span suspension bridge", Comput.-Aided Civil Infrastr. Eng., 35, 685-700. https://doi.org/10.1111/mice.12528 
  29. Oh, B.K., Glisic, B., Kim, Y. and Park, H.S. (2020), "Convolutional neural network-based data recovery method for structural health monitoring", Struct. Health Monitor., 19(6), 1821-1838. https://doi.org/10.1177/1475921719897571 
  30. Posenato, D., Kripakaran, P., Inaudi, D. and Smith, I.F. (2010), "Methodologies for model-free data interpretation of civil engineering structures", Comput. Struct., 88(7-8), 467-482. https://doi.org/10.1016/j.compstruc.2010.01.001 
  31. Shajihan, S.A.V., Wang, S., Zhai, G. and Spencer, B.F.J. (2022), "CNN based data anomaly detection using multi-channel imagery for structural health monitoring", Smart Struct. Syst., Int. J., 29(1), 181-193. https://doi.org/10.12989/sss.2022.29.1.181 
  32. Smarsly, K. and Law, K.H. (2014), "Decentralized fault detection and isolation in wireless structural health monitoring systems using analytical redundancy", Adv. Eng. Software, 73, 1-10. https://doi.org/10.1016/j.advengsoft.2014.02.005 
  33. Sohn, H., Farrar, C.R., Hunter, N.F. and Worden, K. (2001), "Structural health monitoring using statistical pattern recognition techniques", J. Dyn. Syst. Measur. Control, 123(4), 706-711. https://doi.org/10.1115/1.1410933 
  34. Sohn, H., Farrar, C.R., Hemez, F.M., Shunk, D.D., Stinemates, D.W., Nadler, B.R. and Czarnecki, J.J. (2003), "A review of structural health monitoring literature: 1996-2001", Los Alamos National Laboratory, USA. 
  35. Son, H., Yoon, C., Kim, Y., Jang, Y., Tran, L. V., Kim, S.-E., Kim, D.J. and Park, J. (2022), "Damaged cable detection with statistical analysis, clustering, and deep learning models", Smart Struct. Syst., Int. J., 29(1), 17-28. https://doi.org/10.12989/sss.2022.29.1.017 
  36. Straser, E.G., Kiremidjian, A.S., Meng, T.H. and Redlefsen, L. (1998), "A modular, wireless network platform for monitoring structures", Proceedings of the International Modal Analysis Conference, Santa Barbara, CA, USA, February. 
  37. Xin, J., Zhou, J., Yang, S.X., Li, X. and Wang, Y. (2018), "Bridge structure deformation prediction based on GNSS data using Kalman-ARIMA-GARCH model", Sensors, 18(1), 298. https://doi.org/10.3390/s18010298E 
  38. Xu, X., Huang, Q., Ren, Y., Zhao, D.-Y. and Yang, J. (2019), "Sensor fault diagnosis for bridge monitoring system using similarity of symmetric responses", Smart Struct. Syst., Int. J., 23(3), 279-293. https://doi.org/10.12989/sss.2019.23.3.279 
  39. Yang, K., Jiang, H., Ding, Y., Wang, M. and Wan, C. (2022), "Data abnormal detection using bidirectional long-short neural network combined with artificial experience", Smart Struct. Syst., Int. J., 29(1), 117-127. https://doi.org/10.12989/sss.2022.29.1.117 
  40. Yi, T.H., Li, H.N., Song, G. and Guo, Q. (2016), "Detection of shifts in GPS measurements for a long span bridge using CUSUM chart", Int. J. Struct. Stab. Dyn., 16(04), 1640024. https://doi.org/10.1142/S0219455416400241 
  41. Yi, T.H., Huang, H.B. and Li, H.N. (2017), "Development of sensor validation methodologies for structural health monitoring: A comprehensive review", Measurement, 109, 200-214. https://doi.org/10.1016/j.measurement.2017.05.064 
  42. Zebari, R., Abdulazeez, A., Zeebaree, D., Zebari, D. and Saeed, J. (2020), "A comprehensive review of dimensionality reduction techniques for feature selection and feature extraction", J. Appl. Sci. Technol. Trends, 1(2), 56-70. https://doi.org/10.38094/jastt1224