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

다국어 초록 (Multilingual 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.

참고문헌 (Reference)

1 Samer Wehbe Katicha, "Wavelet Denoising of TSD Deflection Slope Measurements for Improved Pavement Structural Evaluation" Wiley 29 (29): 399-415, 2013

2 Hooman Nick, "Vibration-Based Damage Identification in Steel Girder Bridges Using Artificial Neural Network Under Noisy Conditions" Springer Science and Business Media LLC 40 (40): 2021

3 Yuequan Bao, "The State of the Art of Data Science and Engineering in Structural Health Monitoring" Elsevier BV 5 (5): 234-242, 2019

4 Yuequan Bao, "The 1st International Project Competition for Structural Health Monitoring (IPC-SHM, 2020): A summary and benchmark problem" SAGE Publications 20 (20): 2229-2239, 2021

5 P.A. Karthick, "Surface electromyography based muscle fatigue detection using high-resolution time-frequency methods and machine learning algorithms" Elsevier BV 154 : 45-56, 2018

6 Achmad Widodo, "Support vector machine in machine condition monitoring and fault diagnosis" Elsevier BV 21 (21): 2560-2574, 2007

7 Mustafa Gul, "Statistical pattern recognition for Structural Health Monitoring using time series modeling: Theory and experimental verifications" Elsevier BV 23 (23): 2192-2204, 2009

8 Kevin Ni, "Sensor network data fault types" Association for Computing Machinery (ACM) 5 (5): 1-29, 2009

9 Yuguang Fu, "Sensor fault management techniques for wireless smart sensor networks in structural health monitoring" Hindawi Limited 26 (26): e2362-, 2019

10 Yayu Peng, "Sensor fault detection and isolation for a wireless sensor network-based remote wind turbine condition monitoring system" IEEE 2017

11 Zeyu Zhang, "Restoring method for missing data of spatial structural stress monitoring based on correlation" Elsevier BV 91 : 266-277, 2017

12 Bishop, C., "Pattern Recognition and Machine Learning" Springer Press 2006

13 Ka-Veng Yuen, "Outlier detection and robust regression for correlated data" Elsevier BV 313 : 632-646, 2017

14 Matej Žvokelj, "Non-linear multivariate and multiscale monitoring and signal denoising strategy using Kernel Principal Component Analysis combined with Ensemble Empirical Mode Decomposition method" Elsevier BV 25 (25): 2631-2653, 2011

15 L. Calabrese, "Noise removal by cluster analysis after long time AE corrosion monitoring of steel reinforcement in concrete" Elsevier BV 34 : 362-371, 2012

16 Lejla Banjanovic-Mehmedovic, "Neural network-based data-driven modelling of anomaly detection in thermal power plant" Informa UK Limited 58 (58): 69-79, 2017

17 Lejla Banjanovic-Mehmedovic, "Neural network-based data-driven modelling of anomaly detection in thermal power plant" Informa UK Limited 58 (58): 69-79, 2017

18 Bishop, C., "Neural Networks for Pattern Recognition" Clarendon Press 1995

19 Hongping Zhu, "Multi-rate data fusion for dynamic displacement measurement of beam-like supertall structures using acceleration and strain sensors" SAGE Publications 19 (19): 520-536, 2019

20 Taskin Kavzoglu, "Increasing the accuracy of neural network classification using refined training data" Elsevier BV 24 (24): 850-858, 2009

21 Yongchao Yang, "Harnessing data structure for recovery of randomly missing structural vibration responses time history: Sparse representation versus low-rank structure" Elsevier BV 74 : 165-182, 2016

22 G. Venugopal, "Extraction and analysis of multiple time window features associated with muscle fatigue conditions using sEMG signals" Elsevier BV 41 (41): 2652-2659, 2014

23 Jyrki Kullaa, "Detection, identification, and quantification of sensor fault in a sensor network" Elsevier BV 40 (40): 208-221, 2013

24 Kay Smarsly, "Decentralized fault detection and isolation in wireless structural health monitoring systems using analytical redundancy" Elsevier BV 73 : 1-10, 2014

25 Y.F. Luo, "Data Missing Mechanism and Missing Data Real-Time Processing Methods in the Construction Monitoring of Steel Structures" SAGE Publications 18 (18): 585-601, 2015

26 Chafiq Titouna, "DODS: A Distributed Outlier Detection Scheme for Wireless Sensor Networks" Elsevier BV 161 : 93-101, 2019

27 Yuequan Bao, "Computer vision and deep learning–based data anomaly detection method for structural health monitoring" SAGE Publications 18 (18): 401-421, 2018

28 Yongchao Yang, "Blind denoising of structural vibration responses with outliers via principal component pursuit" Hindawi Limited 21 (21): 962-978, 2013

29 Xiaomo Jiang, "Bayesian wavelet packet denoising for structural system identification" Hindawi Limited 14 (14): 333-356, 2007

30 Hai-Bin Huang, "Anomaly Identification of Structural Health Monitoring Data Using Dynamic Independent Component Analysis" American Society of Civil Engineers (ASCE) 34 (34): 2020

31 Zhicheng Chen, "Analyzing and modeling inter-sensor relationships for strain monitoring data and missing data imputation: a copula and functional data-analytic approach" SAGE Publications 18 (18): 1168-1188, 2018

32 Wei Tian, "An iterative reduced-order substructuring approach to the calculation of eigensolutions and eigensensitivities" Elsevier BV 130 : 361-377, 2019

33 Saihua Cai, "An efficient approach for outlier detection from uncertain data streams based on maximal frequent patterns" Elsevier BV 160 : 113646-, 2020

34 Alessandra De Paola, "Adaptive Distributed Outlier Detection for WSNs" Institute of Electrical and Electronics Engineers (IEEE) 45 (45): 902-913, 2015

35 Chia-Ming Chang ; Jau-Yu Chou ; Ping Tan ; Lei Wang, "A sensor fault detection strategy for structural health monitoring systems" 국제구조공학회 20 (20): 43-52, 2017

36 Ka-Veng Yuen, "A novel probabilistic method for robust parametric identification and outlier detection" Elsevier BV 30 : 48-59, 2012

37 Zeyu Zhang, "A Survey on Fault Diagnosis in Wireless Sensor Networks" Institute of Electrical and Electronics Engineers (IEEE) 6 : 11349-11364, 2018

38 Yuzhi Wang, "A Deep Learning Approach for Blind Drift Calibration of Sensor Networks" Institute of Electrical and Electronics Engineers (IEEE) 17 (17): 4158-4171, 2017

39 Ming Li, "2D-LDA: A statistical linear discriminant analysis for image matrix" Elsevier BV 26 (26): 527-532, 2005