Browse > Article
http://dx.doi.org/10.12989/sss.2021.27.2.241

Bridge weigh-in-motion through bidirectional Recurrent Neural Network with long short-term memory and attention mechanism  

Wang, Zhichao (School of Civil and Environmental Engineering, Georgia Institute of Technology)
Wang, Yang (School of Civil and Environmental Engineering, Georgia Institute of Technology)
Publication Information
Smart Structures and Systems / v.27, no.2, 2021 , pp. 241-256 More about this Journal
Abstract
In bridge weigh-in-motion (BWIM), dynamic bridge response is measured during traffic and used to identify overloaded vehicles. Most past studies of BWIM use mechanics-based algorithms to estimate axle weights. This research instead investigates deep learning, specifically the recurrent neural network (RNN), toward BWIM. In order to acquire the large data volume to train a RNN network that uses bridge response to estimate axle weights, a finite element bridge model is built through the commercial software package LS-DYNA. To mimic everyday traffic scenarios, tens of thousands of randomized vehicle formations are simulated, with different combinations of vehicle types, spacings, speeds, axle weights, axle distances, etc. Dynamic response from each of the randomized traffic scenarios is recorded for training the RNN. In this paper we propose a 3-stage Bidirectional RNN toward BWIM. Long short-term memory (LSTM) and attention mechanism are embedded in the BRNN to further improve the network performance. Additional test data indicates that the BRNN network achieves high accuracy in estimating axle weights, in comparison with a conventional moving force identification (MFI) method.
Keywords
bridge weigh-in-motion; deep learning; bidirectional recurrent neural network; attention mechanism; long short-term memory;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Skokandic, D., Znidaric, A., Mandic-Ivankovic, A. and Kreslin, M. (2017), "Application of bridge weigh-in-motion measurements in assessment of existing road bridges", Proceedings of the Value of Structural Health Monitoring for the Reliable Bridge Management, Zagreb, Croatia, March.
2 Zhang, Q.R., Zhang, M., Chen, T.H., Sun, Z.F., Ma, Y.Z. and Yu, B. (2019), "Recent advances in convolutional neural network acceleration", Neurocomputing, 323, 37-51. https://doi.org/10.1016/j.neucom.2018.09.038   DOI
3 Law, S.S., Chan, T.H.T. and Zeng, Q.H. (1999), "Moving force identification-a frequency and time domains analysis", J. Dyn. Syst. Measure. Control ASME, 121(3), 394-401. https://doi.org/10.1115/1.2802487   DOI
4 Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R. (2014), "Dropout: a simple way to prevent neural networks from overfitting", J. Mach. Learn. Res., 15(56), 1929-1958.
5 LeCun, Y., Bengio, Y. and Hinton, G. (2015), "Deep learning", Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539   DOI
6 Chan, T.H.T., Law, S.S., Yung, T.H. and Yuan, X.R. (1999), "An interpretive method for moving force identification", J. Sound Vib., 219(3), 503-524. https://doi.org/10.1006/jsvi.1998.1904   DOI
7 Kim, S., Lee, J., Park, M.-S. and Jo, B.-W. (2009), "Vehicle signal analysis using artificial neural networks for a bridge weigh-in-motion system", IEEE Sensors J., 9(10), 7943-7956. https://doi.org/10.3390/s91007943   DOI
8 Das, P. and Deka, G. (2016), History and Evolution of GPU Architecture, IGI Global, Hershey, PA, USA.
9 Cho, K., Merrienboer, B., Bahdanau, D. and Bengio, Y. (2014), "On the properties of neural machine translation: encoderdecoder approaches", Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, Doha, Qatar, October.
10 Chung, J., Gulcehre, C., Cho, K. and Bengio, Y. (2014), "Empirical evaluation of gated recurrent neural networks on sequence modeling", Deep Learning and Representation Learning Workshop: NIPS 2014, Montreal, QC, Canada.
11 Fu, G. and Hag-Elsafi, O. (2000), "Vehicular overloads: load model, bridge safety, and permit checking", J. Bridge Eng. ASCE, 5(1), 49-57. https://doi.org/10.1061/(ASCE)1084-0702(2000)5:1(49)   DOI
12 O'Connor, C. and Chan, T.H.T. (1988), "Dynamic wheel loads from bridge strains", J. Struct. Eng. ASCE, 114(8), 1703-1723. https://doi.org/10.1061/(ASCE)0733-9445(1988)114:8(1703)   DOI
13 Lydon, M., Taylor, S.E., Robinson, D., Mufti, A. and Brien, E.J.O. (2016), "Recent developments in bridge weigh in motion (B-Wim)", J. Civil Struct. Health Monitor., 6(1), 69-81. https://doi.org/10.1007/s13349-015-0119-6   DOI
14 Minsky, M. and Papert, S. (1969), Perceptrons: An Introduction to Computational Geometry, MIT Press, Cambridge, MA, USA.
15 Moses, F. (1979), "Weigh-in-motion system using instrumented bridges", J. Transport. Eng., 105(3), 233-249.
16 Quilligan, M. (2003), "Bridge weigh-in motion : development of a 2-D multi-vehicle algorithm", Trita-BKN. Bulletin, 69, pp. viii, 144, Byggvetenskap, Stockholm, Sweden.
17 Rosenblatt, F. (1957), The Perceptron - a Perceiving and Recognizing Automaton, Cornell Aeronautical Laboratory.
18 Rumelhart, D.E., Hinton, G.E. and Williams, R.J. (1986), "Learning representations by back-propagating errors", Nature, 323, 533-536. https://doi.org/10.1038/323533a0   DOI
19 Schuster, M. and Paliwal, K.K. (1997), "Bidirectional recurrent neural networks", IEEE Transact. Signal Process., 45(11), 2673-2681. https://doi.org/10.1109/78.650093   DOI
20 Selfridge, O.G. (1959), "Pandemonium: a paradigm for learning", In: Neurocomputing: Foundations of Research, pp. 115-122.
21 Sutskever, I., Vinyals, O. and Le, Q.V. (2014), "Sequence to sequence learning with neural networks", Proceedings of 2014 Advances in Neural Information Processing Systems, Montreal, QC, Canada, December.
22 Yu, Y., Cai, C.S. and Deng, L. (2016), "State-of-the-art review on bridge weigh-in-motion technology", Adv. Struct. Eng. SAGE, 19(9), 1514-1530. https://doi.org/10.1177/1369433216655922   DOI
23 Chorowski, J., Bahdanau, D., Cho, K. and Bengio, Y. (2014), "End-to-end continuous speech recognition using attention-based recurrent NN: first results", Deep Learning and Representation Learning Workshop: NIPS 2014, Montreal, QC, Canada, December.
24 Tikhonov, A.N. and Arsenin, V.Y. (1977), Solutions of Ill-Posed Problems, Kluwer Academic Publishers.
25 GDOT (2020), Highways, bridges and ferries, in Government of Georgia (ed.), Official Code of Georgia.
26 Wu, S. and Shi, Z. (2006), "Identification of vehicle axle loads based on FEM-Wavelet-Galerkin method", J. Vib. Eng., 19(4), 494-498.   DOI
27 Yang, J.C., Yu, K., Gong, Y.H. and Huang, T. (2009), "Linear spatial pyramid matching using sparse coding for image classification", Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, June. https://doi.org/10.1109/CVPR.2009.5206757   DOI
28 Zhang, R., Lv, W. and Guo, Y. (2010), "A vehicle weigh-in-motion system based on Hopfield neural network adaptive filter", Proceedings of 2010 International Conference on Communications and Mobile Computing, Shenzhen, Guangdong, China, April. https://doi.org/10.1109/CMC.2010.11   DOI
29 Gonzalez, A., Rowley, C. and OBrien, E. (2008), "A general solution to the identification of moving vehicle forces on a bridge", Int. J. Numer. Methods Eng., 75, 335-354. https://doi.org/10.1002/nme.2262   DOI
30 Zhu, X.Q. and Law, S.S. (2015), "Structural health monitoring based on vehicle-bridge interaction: accomplishments and challenges", Adv. Struct. Eng. SAGE, 18(12), 1999-2015. https://doi.org/10.1260/1369-4332.18.12.1999   DOI
31 Goodfellow, I., Bengio, Y. and Courville, A. (2016), Deep Learning, MIT Press, Cambridge, MA, USA.
32 Krizhevsky, A., Sutskever, I. and Hinton, G. (2012), "ImageNet classification with deep convolutional neural networks", Commun. ACM, 60(6), 84-90. https://doi.org/10.1145/3065386   DOI
33 Zhu, X.Q. and Law, S.S. (2016), "Recent developments in inverse problems of vehicle-bridge interaction dynamics", J. Civil Struct. Health Monitor., 6(1), 107-128. https://doi.org/10.1007/s13349-016-0155-x   DOI
34 Zhu, X.Q., Law, S.S. and Bu, J.Q. (2006), "A state space formulation for moving loads identification", J. Vib. Acoust. ASME, 128(4), 509-520. https://doi.org/10.1115/1.2202149   DOI
35 Graves, A., Mohamed, A. and Hinton, G. (2013), "Speech recognition with deep recurrent neural networks", Proceedings of 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, May.
36 Hochreiter, S. and Schmidhuber, J. (1997), "Long short-term memory", Neural Computat., 9, 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735   DOI
37 Kawakatsu, T., Aihara, K., Takasu, A. and Adachi, J. (2019), "Deep sensing approach to single-sensor vehicle weighing system on bridges", IEEE Sensors J., 19(1), 243-256. https://doi.org/10.1109/JSEN.2018.2872839   DOI
38 Law, S.S. and Fang, Y.L. (2001), "Moving force identification: optimal state estimation approach", J. Sound Vib., 239(2), 233-254. https://doi.org/10.1006/jsvi.2000.3118   DOI
39 Law, S.S., Chan, T.H.T. and Zeng, Q.H. (1997), "Moving force identification: a time domain method", J. Sound Vib., 201(1), 1-22. https://doi.org/10.1006/jsvi.1996.0774   DOI
40 LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P. (1998), "Gradient-based learning applied to document recognition", Proceedings of the IEEE, 86, 2278-2324. https://doi.org/10.1109/5.726791   DOI