مکان‌یابی خرابی بر پایه پاسخ‌‌های دینامیکی در قاب‌های خمشی با استفاده از شبکه عصبی پیچشی

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده فنی مهندسی، دانشگاه خوارزمی، تهران، ایران.

چکیده

در الگوریتم‌های تشخیص خرابی سازه مبتنی بر روش‌های سنتی یادگیری ماشین، استخراج ویژگی‌های حساس به خرابی از داده‌های سری زمانی یک مسئله چالش برانگیز است. همچنین این روش‌ها نیازمند به پیش‌پردازش در داده‌های خام هستند که خود فرایند پردازش را کندتر می‌کند. تلاش‌های زیادی برای غلبه بر این محدودیت‌ها با گسترش یادگیری عمیق در زمینه پایش سلامت سازه صورت گرفته است. با این حال، از آنجایی که اکثر این سیستم‌ها دارای معماری‌های عمیق هستند، به رایانه‌هایی با توان محاسباتی بالا و همینطور میزان قابل توجهی داده در طول مرحله آموزش نیاز دارند که در نتیجه برای کاربردهای برخط مناسب نیستند. برای حل چالش‌های بالا، در این مقاله روشی مبتنی بر شبکه‌های عصبی پیچشی دوبعدی (CNN) به منظور ادغام دو مرحله استخراج ویژگی و طبقه‌بندی سریع به طور همزمان، ارائه می‌شود. این روش از یک CNN کم عمق استفاده می‌کند که سیگنال‌های شتاب خام را به عنوان ورودی شبکه دریافت می‌کند. برای بررسی توانایی الگوریتم پیشنهاد شده از داده‌‌‌‌ی به دست آمده از یک سازه آزمایشگاهی مقیاس بزرگ به عنوان ورودی شبکه استفاده شده است. به طور میانگین روش پیشنهادی دارای دقت 99/8 درصد بر روی داده‌های آموزشی و 99/6 درصد برای داده‌های اعتبارسنجی رسیده است که نشان از توانایی بالای الگویابی آن دارد. همچنین این روش توانسته هر ثانیه از یک سیگنال ورودی را در مدت زمان 2 میلی ثانیه بررسی کند که در استاندارهای پردازش برخط قرار دارد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Vibrational-Based Damage Localization of Bending Frames Using CNNs

نویسندگان [English]

  • Shahin Ghazvineh
  • Gholamreza Nouri
  • seyed hossein hosseini lavassani
Civil Engineering Department, Faculty of Engineering, Kharazmi University
چکیده [English]

The challenge of identifying damage-indicative features that are robust to noise in time-series data has long hindered the effectiveness of traditional machine learning-based structural damage detection methods. The time-consuming preprocessing procedures required by these methods also contributed to reduced accuracy and performance. However, the advent of deep learning has led to an increased exploration of the use of deep architectures in structural health monitoring. Despite these advancements, many deep learning approaches are resource-intensive and require significant data for training, making them less feasible for real-time applications. As a solution, we propose using 2-D convolutional neural networks (2-D CNNs) that integrate feature extraction and classification into a single entity. Our method employs a network of lighted CNNs instead of deep ones and utilizes raw acceleration signals as input, overcoming the limitations of previous approaches. Using lighted CNNs, in which eachone is optimized for a specific element, increases the accuracy and makes the network faster to perform. Also, a new framework is proposed for decreasing the data required in the training phase. We verified our method on Qatar University Grandstand Simulator (QUGS) benchmark data provided by Structural Dynamics Team. The results showed an improvement in accuracy over other methods, and the running time was adequate for real-time applications.

کلیدواژه‌ها [English]

  • Structural Damage Detection
  • Machine Learning
  • Deep Learning
  • Structural Health Monitoring
  • Convolutional Neural Networks
[1] J.M. Ko, Y.Q. Ni, Technology developments in structural health monitoring of large-scale bridges, Engineering Structures, 2005, pp. 1715-1725.
[2] F. Magalhães, A. Cunha, E. Caetano, Vibration based structural health monitoring of an arch bridge: From automated OMA to damage detection, Mechanical Systems and Signal Processing, 2012, pp. 212-228.
[3] A.B. Noel, A. Abdaoui, T. Elfouly, M.H. Ahmed, A. Badawy, M.S. Shehata, Structural Health Monitoring Using Wireless Sensor Networks: A Comprehensive Survey, IEEE Communications Surveys and Tutorials, 2017, pp. 1403-1423.
[4] S. Teng, G. Chen, P. Gong, G. Liu, F. Cui, Structural damage detection using convolutional neural networks combining strain energy and dynamic response, Meccanica, Springer Netherlands, 2020, pp. 945-959.
[5] C.R. Farrar, S.W. Doebling, D.A. Nix, Vibration-based structural damage identification, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2001, pp. 131-149.
[6] W. Fan, P. Qiao, Vibration-based damage identification methods: A review and comparative study, Structural Health Monitoring, SAGE PublicationsSage UK: London, England, 2011, pp. 83-111.
[7] S. Das, P. Saha, S.K. Patro, Vibration-based damage detection techniques used for health monitoring of structures: a review, Journal of Civil Structural Health Monitoring, 6(3) (2016) 477-507.
[8] O. Abdeljaber, O. Avci, S. Kiranyaz, M. Gabbouj, D.J. Inman, Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks, Journal of Sound and Vibration, Elsevier, 2017, pp. 154-170.
[9] H. Liu, Y. Zhang, Deep learning-based brace damage detection for concentrically braced frame structures under seismic loadings, Advances in Structural Engineering, 2019, pp. 3473-3486.
[10] L. Jing, M. Zhao, P. Li, X. Xu, A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox, Measurement: Journal of the International Measurement Confederation, Elsevier B.V., 2017, pp. 1-10.
[11] K. He, X. Zhang, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2016, pp. 770-778.
[12] J. Han, H. Chen, N. Liu, C. Yan, X. Li, CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion, IEEE Transactions on Cybernetics, 2018, pp. 3171-3183.
[13] T.N. Sainath, B. Kingsbury, G. Saon, H. Soltau, A.-r. Mohamed, G. Dahl, B. Ramabhadran, Deep Convolutional Neural Networks for Large-scale Speech Tasks, Neural Networks, 64 (2015) 39-48.
[14] F. Ordóñez, D. Roggen, Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition, Sensors, 2016, pp. 115.
[15] S. Kiranyaz, T. Ince, M. Gabbouj, Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks, IEEE Transactions on Biomedical Engineering, 2016, pp. 664-675.
[16] W. Zhang, C. Li, G. Peng, Y. Chen, Z. Zhang, A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load, Mechanical Systems and Signal Processing, 2018, pp. 439-453.
[17] S. Kiranyaz, O. Avci, O. Abdeljaber, T. Ince, M. Gabbouj, D.J. Inman, 1D convolutional neural networks and applications: A survey, Mechanical Systems and Signal Processing, The Author(s), 2021, pp. 107398.
[18] S. Kiranyaz, T. Ince, O. Abdeljaber, O. Avci, M. Gabbouj, 1-D Convolutional Neural Networks for Signal Processing Applications, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2019, pp. 8360-8364.
[19] S. Sony, K. Dunphy, A. Sadhu, M. Capretz, A systematic review of convolutional neural network-based structural condition assessment techniques, Engineering Structures, Elsevier Ltd, 2021.
[20] C. Modarres, N. Astorga, E.L. Droguett, V. Meruane, Convolutional neural networks for automated damage recognition and damage type identification, Structural Control and Health Monitoring, John Wiley and Sons Ltd, 2018, pp. e2230.
[21] A.S.M. Shihavuddin, X. Chen, V. Fedorov, A.N. Christensen, N.A.B. Riis, K. Branner, A.B. Dahl, R.R. Paulsen, Wind turbine surface damage detection by deep learning aided drone inspection analysis, Energies, MDPI AG, 2019, pp. 676.
[22] K. Lee, N. Byun, D.H. Shin, A Damage Localization Approach for Rahmen Bridge Based on Convolutional Neural Network, KSCE Journal of Civil Engineering, 2020.
[23] Y. Yu, C. Wang, X. Gu, J. Li, A novel deep learning-based method for damage identification of smart building structures, Structural Health Monitoring, 2019, pp. 143-163.
[24] B.K. Oh, S.H. Lee, H.S. Park, Damage localization method for building structures based on the interrelation of dynamic displacement measurements using convolutional neural network, Structural Control and Health Monitoring, 2020, pp. 1-16.
[25] Y.-z. Lin, Z.-h. Nie, H.-w. Ma, Structural Damage Detection with Automatic Feature-Extraction through Deep Learning, Computer-Aided Civil and Infrastructure Engineering, 32(12) (2017) 1025-1046.
[26] T. Zhang, S. Biswal, Y. Wang, SHMnet: Condition assessment of bolted connection with beyond human-level performance, Structural Health Monitoring, 2020, pp. 1188-1201.
[27] M. Azimi, G. Pekcan, Structural health monitoring using extremely compressed data through deep learning, Computer-Aided Civil and Infrastructure Engineering, 2020, pp. 597-614.
[28] H.V. Dang, M. Raza, T.V. Nguyen, T. Bui-Tien, H.X. Nguyen, Deep learning-based detection of structural damage using time-series data, Structure and Infrastructure Engineering, Taylor & Francis, 2020, pp. 1-20.
[29] Z. Mousavi, M.M. Ettefagh, M.H. Sadeghi, S.N. Razavi, Developing deep neural network for damage detection of beam-like structures using dynamic response based on FE model and real healthy state, Applied Acoustics, Elsevier Ltd, 2020, pp. 107402.
[30] T. Guo, L. Wu, C. Wang, Z. Xu, Damage detection in a novel deep-learning framework: a robust method for feature extraction, Structural Health Monitoring, 2020, pp. 424-442.
[31] O. Avci, O. Abdeljaber, S. Kiranyaz, D. Inman, Structural damage detection in real time: Implementation of 1D convolutional neural networks for SHM applications, Conference Proceedings of the Society for Experimental Mechanics Series, 2017, pp. 49-54.
[32] O. Avci, O. Abdeljaber, S. Kiranyaz, M. Hussein, D.J. Inman, Wireless and real-time structural damage detection: A novel decentralized method for wireless sensor networks, Journal of Sound and Vibration, Elsevier Ltd, 2018, pp. 158-172.[33] O. Abdeljaber, O. Avci, M.S. Kiranyaz, B. Boashash, H. Sodano, D.J. Inman, 1-D CNNs for structural damage detection: Verification on a structural health monitoring benchmark data, Neurocomputing, Elsevier B.V., 2018, pp. 1308-1317.
[34] O. Avci, O. Abdeljaber, S. Kiranyaz, D. Inman, Convolutional Neural Networks for Real-Time and Wireless Damage Detection, in, 2020, pp. 129-136.
[35] O. Abdeljaber, A. Younis, O. Avci, N. Catbas, M. Gul, O. Celik, H. Zhang, Dynamic Testing of a Laboratory Stadium Structure, Geotechnical and Structural Engineering Congress 2016, American Society of Civil Engineers, Reston, VA, 2016, pp. 1719-1728.
[36] X. Glorot, A. Bordes, Y. Bengio, Deep Sparse Rectifier Neural Networks, in, JMLR Workshop and Conference Proceedings, 2011, pp. 315-323.
[37] V. Nair, G.E. Hinton, Rectified linear units improve Restricted Boltzmann machines, ICML 2010 - Proceedings, 27th International Conference on Machine Learning, 2010, pp. 807-814.
[38] A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, Communications of the ACM, 2017, pp. 84-90.
[39] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: A simple way to prevent neural networks from overfitting, Journal of Machine Learning Research, 2014, pp. 1929-1958.
[40] B.Y. Goodfellow lan, Courville Aaron, Deep Learning - Ian Goodfellow, Yoshua Bengio, Aaron Courville - Google Books, MIT Press, 2016, pp. 800.
[41] D.P. Kingma, J.L. Ba, Adam: A method for stochastic optimization, 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, International Conference on Learning Representations, ICLR, 2015.
[42] R. Doroudi, S.H.H. Lavassani, M. Shahrouzi, Damage detection for long-span bridges through support vector machine, wavelet transform, and multivariate empirical mode decomposition, Int. J. Struct. Eng., 14(2) (2024) 164-185.