شناسایی خسارت با هزینه کم پل‌های کابلی با استفاده از پردازش سیگنال و فراگیری ماشین

نوع مقاله : مقاله پژوهشی

نویسنده

استادیار، گروه عمران، واحد رودهن، دانشگاه آزاد اسلامی، رودهن، ایران،

چکیده

امروزه با کمک روش های پایش سالمت سازه ها می توان وقوع خسارت را در همان مراحل اولیه شناسایی کرد و از وقوع خسارت های مالی و جانی جلوگیری کرد. با این حال، یکی از موانع بر سر راه متداول شدن این روش ها در کشور گران قیمت بودن سیستم های پایش سالمت است. هدف از این پژوهش، ارائه یک روش شناسایی خسارت با هزینه کم برای پل ها با استفاده از تکنیک های پردازش سیگنال و فراگیری ماشین است. جهت کاهش هزینه ها تعداد سنسورها جهت پایش ارتعاش سازه به یک سنسور کاهش یافته است. از آنجا که کاهش تعداد سنسورها ممکن است از دقت پایش سالمت سازه ها بکاهد، از بروزترین روش های پردازش سیگنال استفاده شده است. در مرحله اول چند روش پردازش سیگنال دامنه زمان-فرکانس با یکدیگر مقایسه شده اند و روش تبدیل موجک تجربی به عنوان بهترین روش از میان آن ها انتخاب شده است. در مرحله بعد پس از تجزیه سیگنال ها، یک شاخص خسارت جدید بر مبنای تبدیل موجک متقاطع معرفی شده و سپس با استفاده از ماشین بردار پشتیبان شاخص های خسارت طبقه بندی شده اند تا قابلیت تفکیک حالت سالم و خسارت فراهم شود. نتایج نشان می دهد روش فوق با دقت باال می تواند خسارت را در سازه شناسایی کند.

کلیدواژه‌ها


عنوان مقاله [English]

Low-Cost Damage Detection of Cable-Stayed Bridges Using Signal Processing and Machine Learning

نویسنده [English]

  • Ehsan Darvishan
Assistant Professor, Department of Civil Engineering, Roudehen Branch, Islamic Azad University, Roudehen, Iran
چکیده [English]

Today, it is possible to detect damage in the early stages with the aim of structural health monitoring (SHM) techniques and prevent financial losses and loss of lives. However, high prices of SHM systems has caused that such systems do not gain popularity in our country. The aim of this study is providing a low-cost damage detection technique for bridges based on signal processing and machine learning. In order to reduce expenses, the number of sensors to monitor the vibration of the structure was decreased. Since sensor number reduction can lead to a drop in damage detection accuracy, most up to date signal processing methods were used. In the first step of the paper, several time-frequency signal processing techniques were compared and EWT was selected as the best method. In the next step, after decomposition of signals by time-frequency techniques, a new damage index was introduced base on cross wavelet transform (CWT) and then calculated damaged indices were classified using support vector machine (SVM) to be able to distinguish healthy and damage states. Results showed that the proposed method can detect damage with high accuracy.

کلیدواژه‌ها [English]

  • Damage detection
  • Structural health monitoring
  • Signal processing
  • Cross wavelet
  • Support vector machine
[1]    H. Sohn, C.R. Farrar, F.M. Hemez, J.J. Czarnecki, A review of structural health review of structural health monitoring literature 1996-2001 (No. LAUR-02-2095), Los Alamos National Laboratory, (2002).
[2]    J.P. Lynch, K.J. Loh, A summary review of wireless sensors and sensor networks for structural health monitoring, Shock and Vibration Digest, 38(2) (2006) 91-130.
[3]    T.D. Tan, N.T. Anh, G.Q Anh, Low-cost Structural Health Monitoring Scheme Using MEMS-based Accelerometers, Intelligent Systems, Modelling and Simulation (ISMS), 2011 Second International Conference on (pp. 217-220). IEEE, 2011.
[4]    Y.S Lee, B. Phares, T. Wipf, Development of a lowcost, continuous structural health monitoring system for bridges and components, Proceedings of the 2007 Mid-Continent Transportation Research Symposium, 2007.
[5]    S. Jang, B.F. Spencer Jr, Structural health monitoring for bridge structures using smart sensors, Newmark Structural Engineering Laboratory, University of Illinois at Urbana-Champaign, (2015).
[6]    G. Park, T. Rosing, M.D. Todd, C.R Farrar, W. Hodgkiss, Energy harvesting for structural health monitoring sensor networks, Journal of Infrastructure Systems, 14(1) (2008) 64-79.
[7]    X. Hu, B. Wang, H. Ji, A wireless sensor network‐based structural health monitoring system for highway bridges, Computer‐Aided Civil and Infrastructure Engineering, 28(3) (2013)193-209.
[8]    A. Depari, P. Ferrari, A. Flammini, S. Rinaldi, M. Rizzi, E. Sisinni, Development and evaluation of a WSN for real-time structural health monitoring and testing, Procedia Engineering, 87 (2014) 680-683.
[9]    C.H. Lin, S.Y. Chen, C.C. Yang, C.M. Wu, C.M. Huang, C.T. Kuo, Y.D. Huang, Structural health monitoring of bridges using cost-effective 1-axis accelerometers, Sensors Applications Symposium (SAS), 2014 IEEE (pp. 24-27), IEEE, 2014.
[10] S.W. Doebling, C.R. Farrar, M.B. Prime, A summary review of vibration-based damage identification methods, Shock and vibration digest, 30(2) (1998) 91-105.
[11] Q. Cheng-Zhong, L. Xu-Wei, Damage identification for transmission towers based on HHT. Energy Procedia, 17 (2012) 1390-1394.
[12] C. Bao, H. Hao, Z.X. Li, Multi-stage identification scheme for detecting damage in structures under ambient excitations, Smart Materials and Structures, 22(4) (2013) 045006.
[13] N. Roveri, A. Carcaterra, Damage detection in structures under traveling loads by Hilbert– Huang transform, Mechanical Systems and Signal Processing, 28 (2012) 128-144.
[14] J.P. Amezquita-Sanchez, H.S. Park, H. Adeli, A novel methodology for modal parameters identification of large smart structures using MUSIC, empirical wavelet transform, and Hilbert transform, Engineering Structures, 147 (2017) 148-159.
[15] A. Kunwar, R. Jha, M. Whelan, K. Janoyan, Damage detection in an experimental bridge model using Hilbert–Huang transform of transient vibrations, Structural Control and Health Monitoring, 20(1) (2013) 1-15.
[16] N.E. Huang, Z. Shen, S.R. Long, M.C. Wu, H.H. Shih, Q. Zheng, N.C. Yen, C.C. Tung, H.H. Liu, The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Nonstationary Time Series Analysis, Proceeding of the Royal Society London, A: 454, 1998.
[17] T. Oberlin, S. Meignen, V. Perrier, An alternative formulation for the empirical mode decomposition. IEEE Transactions on Signal Processing, 60(5) (2012) 2236-2246.
[18] H. Li, Z. Li, W. Mo, A time varying filter approach for empirical mode decomposition, Signal Processing, 138 (2017) 146-158.
[19] J. Gilles, Empirical wavelet transform, IEEE transactions on signal processing, 61(16) (2013) 3999-4010.
[20] G.H. James, T.G. Carne, J.P. Lauffer, The natural excitation technique (NExT) for modal parameter extraction from operating structures, Modal Analysis-the International Journal of Analytical and Experimental Modal Analysis, 10(4) (1995) 260.
[21] A. Prokoph, H. El Bilali, Cross-wavelet analysis: a tool for detection of relationships between paleoclimate proxy records, Mathematical geosciences, 40(5) (2008) 575-586.
[22] M.A. Hearst, S.T. Dumais, E. Osuna, J. Platt, B. Scholkopf, Support vector machines. IEEE Intelligent Systems and their applications, 13(4) (1998) 18-28.
[23] S. Li, H. Li, Y. Liu, C. Lan, W. Zhou, J. Ou, SMC structural health monitoring benchmark problem using monitored data from an actual cable‐stayed bridge, Structural Control and Health Monitoring, 1;21(2) (2014)156-72.
[24] W. Zhou, S. Li, H. Li, Damage detection for SMC benchmark problem: A subspace-based approach, International Journal of Structural Stability and Dynamics, 16(04) (2016) 1640025.