شناسایی آسیب در شاه تیرهای بتنی عرشه پل‌ها با استفاده از توزیع زمان-فرکانس مربعی و شبکه عصبی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده فنی و مهندسی، دانشگاه مراغه، مراغه، ایران

2 دانشکده فنی و مهندسی، دانشگاه آزاد اسلامی واحد تهران شمال، تهران، ایران

چکیده

شناسایی آسیب در سازه‌ها به ویژه در چند سال اخیر به شدت مورد توجه قرار گرفته است. در این پژوهش روش جدیدی برای شناسایی آسیب در شاه تیرهای بتنی عرشه پل‌ها ارائه گردیده است. سهولت کاربرد، دقت بالا و کاهش هزینه­های پایش از پیش فرض‌های در نظر گرفته شده برای ارائه روش جدید بوده ­است. در این تحقیق با بهره‌گیری از ابزارهای پردازش سیگنال و هوش مصنوعی، ویژگی‌های حساس به خسارت به گونه‌ای استخراج شده­اند که وجود آسیب، شدت و محل آن تنها با استفاده از سیگنال‌های پاسخ ارتعاش دریافتی از یک حسگر با دقت بسیار بالا و در حدود 99 درصد و درصد خطای کمتر از 1 تعیین گردند. بر اساس روش ارائه شده ابتدا با استفاده از تابع زمان فرکانس مربعی، سیگنال‌های پاسخ دریافتی از سازه با سناریوهای مختلف که در حالات سالم و دارای آسیب با درصدهای متفاوت، مورد پردازش واقع شده، سپس با استفاده از این داده‌ها به عنوان ورودی به شبکه‌ی عصبی و تعیین خروجی‌های متناسب نسبت به آن، شبکه‌ی مورد نظر آموزش داده شده است. به منظور ارزیابی، صحت‌سنجی و اطمینان از عملکرد روش پیشنهادی، از مدل عددی تیر بتنی و همچنین مدل عددی پل شهید مدنی تبریز در حالت‌های عادی و نوفه دار استفاده شده است. نتایج محاسبات بیانگر دقت تشخیص بالای این روش و کمترین میزان خطا در تعیین میزان سلامت سازه و همچنین شناسایی موقعیت المان آسیب دیده می‌باشد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Identifying Damages in girders of Bridges Using Square Time-Frequency Distribution and Neural Network

نویسندگان [English]

  • Hamid Reza Ahmadi 1
  • Ali Mahdi Allahyari 2
  • Hassan Mahdi Allahyari 1
1 Department of Civil Eng.- University of Maragheh
2 Tehran North Branch, Islamic Azad University
چکیده [English]

The detection of damage to structures has received much attention, especially in recent years. In this research paper, a new method for detecting damage in concrete girders of bridge decks is presented. Ease of use, high accuracy, and reduction of monitoring costs are the requirements for the new method. In this research, signal processing tools and artificial intelligence were used to extract damage-sensitive features so that the presence of damage, its intensity, and its location can be determined with very high accuracy based solely on the vibration signals received from a sensor. The accuracy is about 99%, and the error percentage is less than 1. Based on the proposed method, firstly, using the time-frequency function, the response signals from the structure were processed. The neural network was trained, using the processed data. To evaluate, validate and ensure the performance of the proposed method, the numerical model of the concrete girder and the numerical model of the Shahid Madani bridge in Tabriz under normal and disturbed conditions were used. The results show the high diagnostic accuracy of this method and the lowest error rate in determining the condition of the structure and the location of the damaged element.

کلیدواژه‌ها [English]

  • Damage Detection
  • Health Monitoring
  • Neural Network
  • Square Time-Frequency Distribution
  • Bridge
[1] S.W. Doebling, C.R. Farrar, M.B. Prime, D.W. Shevitz, Damage Identification and Health Monitoring of Structural and Mechanical Systems from Changes in Their Vibration Characteristics, A Literature Review, Los Alamos, National Lab, USA, 1996.
[2] H. Sohn, C.R. Farrar, F.M. Hemez, J.J. Czarnecki, A review of structural health monitoring, Los Alamos, National Lab, USA, 2003.
[3] A. Rahaei, A. Mirzazade, N. Sadeghi, seismic assessment of steel frame bridges and comparison with damage indices, Amirkabir Journal of Civil Engineering, 51(4) (2019) 757-766. (in Persian)
[4] H. Iemura, T. Mikami, Demand spectra of yield strength and ductility factor to satisfy the required seismic performance objectives, Proceeding of JSCE, 689 (2001) 333–342.
[5] H.R. Ahmadi, F. Daneshjoo, N. Khaji, New damage indices and algorithm based on square time–frequency distribution for damage detection in concrete piers of railroad bridges, Structural Control and Health Monitoring, 22(1) (2015) 91-106.
[6] H. Wenzel, Health Monitoring of Bridges, John Wiley & Sons Ltd, UK, 2009.
[7] A.A. Mufti, Guidelines for structural health monitoring, ISIS, Canada, 2001.
[8] L. Qiao, Structural damage detection using signal-based pattern recognition, Kansas State University, USA, 2009.
[9] P. Bonato, R. Ceravolo, A. De Stefano, F. Molinari, Use of Cross-Time-Frequency Estimators for Structural Identification in Non-Stationary Conditions and Under Unknown Excitation, Sound and Vibration, 237(5) (2000) 779-791.
[10] F. Daneshjoo, H.R. Ahmadi, G. Mobtaker, Feature identification and damage detection of concrete piers of bridges using timefrequency representation and modified matrix subtraction method, Sharif Journal of Civil Engineering, 29(2) (2013) 37-48. (in Persian)
[11] Y. F‌o‌l‌a‌d‌g‌h‌a‌d‌a‌m, H.R. G‌h‌a‌f‌o‌u‌r‌i, Damage detection in structures by wavelet analysis using modal analysis data, Sharif Journal of Civil Engineering, 31(2) (2015) 111-121. (in Persian)
[12] C.M. Chang, S.K. Huang, Matrix factorization to time-frequency distribution for structural health monitoring, in:  Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2016, SPIE, 2016, pp. 517-532.
[13] G. G‌h‌o‌d‌r‌a‌t‌i A‌m‌i‌r‌i, M. M‌o‌h‌a‌m‌a‌d‌i D‌e‌h‌c‌h‌e‌s‌h‌m‌e‌h, E. D‌a‌r‌v‌i‌s‌h‌a‌n, An artificial neural network based method for estimation of the inelastic response of Single-Degree of Freeedom (S) systems under records of rock, Sharif Journal of Civil Engineering, 31(2) 93-103. (in Persian)
[14] M.R. Kaloop, J.W. Hu, E. Elbeltagi, Time-Series and Frequency-Spectrum Correlation Analysis of Bridge Performance Based on a Real-Time Strain Monitoring System, ISPRS: International Journal of Geo-Information, 5(5) (2016) 61.
[15] H.R. Ahmadi, D. Anvari, New damage index based on least squares distance for damage diagnosis in steel girder of bridge's deck, Structural Control and Health Monitoring, 25(10) (2018) e2232.
[16] S.B. Beheshti aval, V. Ahmadian, E. darvishan, Damage detection of structures using signal processing and artificial neural networks, Journal of Modeling in Engineering, 16 (2018) 253-265. (in Persian)
[17] E. Darvishan; G. Ghodrati Amiri, Damage detection of structures using wavelet packet analysis and dimensionality reduction, Sharif Journal of Civil Engineering, 35(2) (2019). (in Persian)
[18] M. Mohamadi Dehcheshmeh, A. Zare Hosseinzadeh, and G. Ghodrati Amiri, Feasibility study on model-based damage detection in shear frames using pseudo modal strain energy, Smart Structures and Systems, (2020) 47-56.
[19] S. Quqa, L. Landi, P.P. Diotallevi, Automatic identification of dense damage-sensitive features in civil infrastructure using sparse sensor networks, Automation in Construction, 128 (2021) 103740.
[20] S. Yang, Y. Huang, Damage identification method of prestressed concrete beam bridge based on convolutional neural network, Neural Computing and Applications, 33(2) (2021) 535-545.
[21] O.R. De Lautour, Assessment of seismic damage to civil structures using statistical pattern recognition techniques and time series analysis, University of Auckland, New Zealand, 2008.
[22] J. Cheng, D. Yu, Y. Yang, A fault diagnosis approach for gears based on IMF AR model and SVM, EURASIP Journal on Advances in Signal Processing, 2008 (2008).
[23] A. De Stefano, R. Ceravolo, D. Sabia, Output only dynamic identification in time-frequency domain, in:  Proceedings of the 2001 American Control Conference, IEEE, Arlington, VA, USA, 2001, pp. 447-449.
[24] O.R. De Lautour, P. Omenzetter, Prediction of seismic-induced structural damage using artificial neural networks, Engineering Structures, 31(2) (2009) 600-606.
[25] Z. Zhou, L.D. Wegner, B.F. Sparling, Structural health monitoring of precast concrete box girders using selected vibration-based damage detection methods, Advances in Civil Engineering, (2010).
[26] H. Wang, P. Chen, Fuzzy diagnosis method for rotating machinery in variable rotating speed, IEEE Sensors Journal, 11(1) (2011) 23-34.
[27] G.P. Zhang, Time series forecasting using a hybrid ARIMA and neural network model, Neurocomputing, 50 (2003) 159-175.
[28] V. Soltangharaei, R. Anay, L. Assi, M. Bayat, J.R. Rose, P. Ziehl, Analyzing acoustic emission data to identify cracking modes in cement paste using an artificial neural network, Construction and Building Materials, 267 (2020).
[29] R.J. Schalkoff, Artificial Neural Networks, Shahid Chamran University Press, Iran, 2003. (in Persian)
[30] D. Solomatine, L.M. See and R.J. Abrahart, Data-Driven Modelling: Concepts, Approaches and Experiences, in: R.J. Abrahart, L.M. See, D. Solomatine (Ed.) Practical Hydroinformatics, Springer, Berlin, 2009.
[31] H.P. Gavin, The Levenberg-Marquardt method for nonlinear least squares curve-fitting problems, Department of Civil and Environmental Engineering, Duke University, (2020).
[32] J. Sobieszczanski-Sobieski, A. Morris, M. Van Tooren, Multidisciplinary Design Optimization Supported by Knowledge based Engineering, John Wiley & Sons, 2015.
[33] B. Russell, T. Jackson, Introduction to Neural Networks, Institute of Scientific Publications, Sharif University of Technology, Tehran, Iran, 2007. (in Persian)
[34] H. Yu, B.M. Wilamowski, Levenberg-marquardt training, Industrial electronics handbook Intelligent Systems, CRC Press, 2011.
[35] A.G. Chegini, Matlab toolboxes, Naghoos Publication, Tehran, Iran, 2009. (in Persian)
[36] F. Malik, M. Nasereddin, Forecasting output using oil prices: A cascaded artificial neural network approach, Journal of Economics and Business, 58 (2006) 168–180.
[37] X. Zhao, Y. Kinouchi, E. Yasuno, D. Gao, T. Iritani, T. Morimoto, M. Takeuchi, A new method for noninvasive measurement of multilayer tissue conductivity and structure using divided electrodes, IEEE Transactions on Biomedical Engineering, 51(2) (2004) 362 – 370.
[38] H.Z. Alemu, W. Wu, J. Zhao, Feedforward Neural Networks with a Hidden Layer Regularization Method, Symmetry, 10(10) (2018).
[39] H.R. Ahmadi, D. Anvari, Health monitoring of pedestrian truss bridges using cone-shaped kernel distribution, Smart Structures and Systems, 22(6) (2018) 699-709.
[40] A. Rahai, F. Bakhtiari‐Nejad, A. Esfandiari, Damage assessment of structure using incomplete measured mode shapes, Structural Control and Health Monitoring, 14(5) (2007) 808-829.
[41] J.K. Sinha, M.I. Friswell, Model Updating: A Tool for Reliable Modeling, Design Modification and Diagnosis, Shock and Vibration, 34(1) (2002) 27–35.
[42] S.E. Fang, R. Perera, G. De Roeck, Damage Identification of a Reinforced Concrete Frame by Finite Element Model Updating Using Damage Parameterization, Journal of Sound and Vibration, 313(3-5) (2008) 544-559.
[43] A. Teughels, G. DeRoeck, Structural Damage Identification of the Highway Bridge Z24 by FE Model Updating, Journal of Sound and Vibration, 278(3) (2004) 589-610.
[44] B. Jaishi, W.X. Ren, Structural Finite Element Model Updating Using Ambient Vibration Test Results, Journal of structural engineering, 131(4) (2005) 617-628.
[45] M.H. Daneshvar, A. Gharighoran, S.A. Zareei, A. Karamodin, Damage Detection of Bridge by Rayleigh-Ritz Method, Journal of Rehabilitation in Civil Engineering, 8(1) (2020) 149-162.
[46] E.J. OBrien, J. Keenahan, Drive‐by damage detection in bridges using the apparent profile, Structural Control and Health Monitoring, 22(5) (2015) 813-825.
[47] H.R. Ahmadi, N. Mahdavi, M. Bayat, A new index based on short time fourier transform for damage detection in bridge piers, Computers and Concrete, 27(5) (2021) 447-455.
[48] H.R. Ahmadi, N. Mahdavi, M. Bayat, A novel damage identification method based on Short Time Fourier Transform and a new efficient index, Structures, 33 (2021) 3605-3614.