شناسایی و عیب‌یابی سازه تیری‌شکل با استفاده از سیگنال‌های ارتعاشی بر پایه مدل شبیه‌سازی‌شده، حالت سالم واقعی و شبکه عصبی کانولوشنال عمیق

نوع مقاله : مقاله پژوهشی

نویسندگان

1 تبریز*مهندسی مکانیک

2 دانشگاه تبریز

چکیده

پایش وضعیت سیستم‌های مکانیکی اعم از سازه‌ها، ماشین‌های دوار همواره یکی از چالش‌های مهم محسوب می‌شود. در این مقاله روش جدیدی برای شناسایی و عیب‌یابی سازه تیری شکل در حضور عدم‌ قطعیت‌هایی مانند خطاهای مدل‌سازی، خطاهای اندازه‌گیری، تغییرات بارگذاری‌ و نویزهای محیطی بر پایه مدل شبیه‌سازی‌شده و حالت سالم واقعی ارائه شده است. در این روش، داده‌های سیستم سالم واقعی برای به‌روزرسانی پارامترهای مدل شبیه‌سازی‌شده استفاده شده است. برخی از بخش‌های سیگنال‌ که مربوط به ذات سیستم نیستند با استفاده از روش تجزیه مود تجربی دسته‌ای کامل، حذف شده‌اند. یک شبکه عصبی کانولوشنال عمیق، به‌منظور یادگیری ویژگی‌های حساس به عیب از داده خام فرکانسی مدل شبیه‌سازی‌شده و حالت سالم واقعی طراحی شده است. داده‌های خام فرکانسی با استفاده از روش چگالی طیفی توان از سیگنال‌های ارتعاشی استخراج شده‌اند. به‌منظور آموزش شبکه عمیق پیشنهادی از داده‌های خام فرکانسی مدل شبیه‌سازی‌‌شده و حالت سالم واقعی استفاده می‌شود. پس‌ازآن داده‌های خام فرکانسی مدل واقعی برای ارزیابی شبکه عمیق پیشنهادی استفاده می‌شود. روش پیشنهادی با استفاده از سازه تیری شکل آزمایشگاهی ارزیابی شده است. نتایج حاصل نشان می‌دهد که استفاده از الگوریتم پیشنهادی برای شناسایی و عیب‌یابی سازه تیری‌شکل صحت بالاتری نسبت به سایر روش‌های مقایسه‌ای دارد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Identification and damage detection of beam-like structure using vibration signals based on simulated model, real healthy state and deep convolutional neural network

نویسندگان [English]

  • zohreh mousavi 1
  • Mir Mohammad Ettefagh 1
  • Morteza Sadeghi 1
  • seyed nacer razavi 2
1 university of tabriz
2 university of tabriz
چکیده [English]

Condition monitoring of mechanical systems, such as structures and rotating machines is always a major challenge. This paper is presented a new method for damage detection of real mechanical systems in presence of the uncertainties such as modeling errors, measurement errors, varying loading conditions, and environmental noises based on a simulated model and real healthy state. In this method, data of a real healthy system is used to updating the parameters of the simulated model. Some parts of the signals that are not related to the nature of the system are removed using the complete ensemble empirical mode decomposition method. A deep convolutional network is designed to learn damage-sensitive features from raw frequency data of simulated model and real healthy state. Raw frequency data is extracted from vibration signals using the power spectral density method. In order to train the proposed deep network, raw frequency data of the simulated model andreal healthy state are used. Then, raw frequency data of the real model are used to test the proposed deep network. The proposed method is validated using an experimental beam structure. The results show that using the proposed algorithm for identification and damage detection of the beam-like structure has more accuracy with respect to the other comparative methods

کلیدواژه‌ها [English]

  • Condition monitoring
  • Beam-like Structure
  • Vibration signal
  • Deep neural Network
[1] H. Adeli, X. Jiang, Intelligent infrastructure: neural networks, wavelets, and chaos theory for intelligent transportation systems and smart structures, CRC press, 2008.
[2] R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, R.X. Gao, Deep learning and its applications to machine health monitoring, Mechanical Systems and Signal Processing, 115 (2019) 213-237.
[3] 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, 111 (2017) 1-10.
[4] F. Jia, Y. Lei, J. Lin, X. Zhou, N. Lu, Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data, Mechanical Systems and Signal Processing, 72 (2016) 303-315.
[5] 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, 388 (2017) 154-170.
[6] F. Jia, Y. Lei, L. Guo, J. Lin, S. Xing, A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines, Neurocomputing, 272 (2018) 619-628.
[7] W. Zhang, G. Peng, C. Li, Y. Chen, Z. Zhang, A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals, Sensors, 17(2) (2017) 425.
[8] M. Turner, Stiffness and deflection analysis of complex structures, journal of the Aeronautical Sciences, 23(9) (1956) 805-823.
[9] 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.
[10] J. Guo, J. Wu, J. Guo, Z. Jiang, A Damage Identification Approach for Offshore Jacket Platforms Using Partial Modal Results and Artificial Neural Networks, Applied Sciences, 8(11) (2018) 2173.
[11] J. Gu, M. Gul, X. Wu, Damage detection under varying temperature using artificial neural networks, Structural Control and Health Monitoring, 24(11) (2017) e1998.
[12] Y. Chen, G. Peng, C. Xie, W. Zhang, C. Li, S. Liu, ACDIN: Bridging the gap between artificial and real bearing damages for bearing fault diagnosis, Neurocomputing, 294 (2018) 61-71.
[13] M. Fallahian, F. Khoshnoudian, V. Meruane, Ensemble classification method for structural damage assessment under varying temperature, Structural Health Monitoring, 17(4) (2018) 747-762.
[14] W. Weaver Jr, P.R. Johnston, Structural dynamics by finite elements, Prentice-Hall Englewood Cliffs (NJ), 1987.
[15] I. Chowdhury, S.P. Dasgupta, Computation of Rayleigh damping coefficients for large systems, The Electronic Journal of Geotechnical Engineering, 8(0) (2003) 1-11.
[16] S. Wu, S. Law, Vehicle axle load identification on bridge deck with irregular road surface profile, Engineering Structures, 33(2) (2011) 591-601.
[17] S. Varahram, P. Jalali, M.H. Sadeghi, S. Lotfan, Experimental Study on the Effect of Excitation Type on the Output-Only Modal Analysis Results, Transactions of FAMENA, 43(3) (2019) 37-52.
[18] M.E. Torres, M.A. Colominas, G. Schlotthauer, P. Flandrin, A complete ensemble empirical mode decomposition with adaptive noise, in: 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, 2011, pp. 4144-4147.
[19] I. Goodfellow, Y. Bengio, A. Courville, Deep learning, MIT press, 2016.
[20] S.-L. Hung, H. Adeli, Parallel backpropagation learning algorithms on Cray Y-MP8/864 supercomputer, Neurocomputing, 5(6) (1993) 287-302.
[21] Z. Mousavi, T.Y. Rezaii, S. Sheykhivand, A. Farzamnia, S. Razavi, Deep convolutional neural network for classification of sleep stages from single-channel EEG signals, Journal of neuroscience methods, (2019) 108312.
[22] 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, 100 (2018) 439-453.
[23] A. Mojtahedi, M.L. Yaghin, Y. Hassanzadeh, M. Ettefagh, M. Aminfar, A. Aghdam, Developing a robust SHM method for offshore jacket platform using model updating and fuzzy logic system, Applied Ocean Research, 33(4) (2011) 398-411.
[24] A. Mosallam, T. Zirakian, A. Abdelaal, A. Bayraktar, Health monitoring of a steel moment-resisting frame subjected to seismic loads, Journal of Constructional Steel Research, 140 (2018) 34-46.
[25] Z. Ding, J. Li, H. Hao, Z.-R. Lu, Structural damage identification with uncertain modelling error and measurement noise by clustering based tree seeds algorithm, Engineering Structures, 185 (2019) 301-314.
[26] E. Barton, C. Middleton, K. Koo, L. Crocker, J. Brownjohn, Structural finite element model updating using vibration tests and modal analysis for NPL Footbridge–SHM demonstrator, in:  Journal of Physics: Conference Series, IOP Publishing, 2011, pp. 012105.
[27] E. Giampieri, D. Remondini, M.G. Bacalini, P. Garagnani, C. Pirazzini, S.L. Yani, C. Giuliani, G. Menichetti, I. Zironi, C. Sala, Statistical strategies and stochastic predictive models for the MARK-AGE data, Mechanisms of ageing and development, 151 (2015) 45-53.
[28] S.S. Rao, F.F. YAP, Upper Saddle River: Mechanical vibrations, in, Prentice Hall, 2011.
[29] S. Kim, J.-H. Choi, Convolutional neural network for gear fault diagnosis based on signal segmentation approach, Structural Health Monitoring, 18(5-6) (2019) 1401-1415.
[30] M. Hagan, H. Demuth, M. Beale, O. De Jesús, Neural network design vol. 20: Pws Pub, in, Boston, 1996.
[31] V.N. Ghate, S.V. Dudul, Optimal MLP neural network classifier for fault detection of three phase induction motor, Expert Systems with Applications, 37(4) (2010) 3468-3481.