Structural Engineering and Mechanics

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Force-deformation relationship prediction of bridge piers through stacked LSTM network using fast and slow cyclic tests

  • Omid Yazdanpanah (Department of Civil and Environmental Engineering, Myongji University) ;
  • Minwoo Chang (Department of Civil and Environmental Engineering, Myongji University) ;
  • Minseok Park (Department of Civil and Environmental Engineering, Myongji University) ;
  • Yunbyeong Chae (Department of Civil and Environmental Engineering, Seoul National University)
  • Received : 2022.10.16
  • Accepted : 2023.01.25
  • Published : 2023.02.25
⟨ Previous Next ⟩

Abstract

A deep recursive bidirectional Cuda Deep Neural Network Long Short Term Memory (Bi-CuDNNLSTM) layer is recruited in this paper to predict the entire force time histories, and the corresponding hysteresis and backbone curves of reinforced concrete (RC) bridge piers using experimental fast and slow cyclic tests. The proposed stacked Bi-CuDNNLSTM layers involve multiple uncertain input variables, including horizontal actuator displacements, vertical actuators axial loads, the effective height of the bridge pier, the moment of inertia, and mass. The functional application programming interface in the Keras Python library is utilized to develop a deep learning model considering all the above various input attributes. To have a robust and reliable prediction, the dataset for both the fast and slow cyclic tests is split into three mutually exclusive subsets of training, validation, and testing (unseen). The whole datasets include 17 RC bridge piers tested experimentally ten for fast and seven for slow cyclic tests. The results bring to light that the mean absolute error, as a loss function, is monotonically decreased to zero for both the training and validation datasets after 5000 epochs, and a high level of correlation is observed between the predicted and the experimentally measured values of the force time histories for all the datasets, more than 90%. It can be concluded that the maximum mean of the normalized error, obtained through Box-Whisker plot and Gaussian distribution of normalized error, associated with unseen data is about 10% and 3% for the fast and slow cyclic tests, respectively. In recapitulation, it brings to an end that the stacked Bi-CuDNNLSTM layer implemented in this study has a myriad of benefits in reducing the time and experimental costs for conducting new fast and slow cyclic tests in the future and results in a fast and accurate insight into hysteretic behavior of bridge piers.

Keywords

Acknowledgement

The authors gratefully acknowledge the financial support provided by the Brain Pool program funded by the Ministry of Science and ICT through the National Research Foundation of Korea (2021H1D3A2A01095957). Moreover, the authors appreciate all the support provided by Hystec's engineers and laborers to provide experimental setups.

References

  1. Alevizakou, E.G. and Pantazis, G. (2017), "A comparative evaluation of various models for prediction of displacements", Appl. Geomat., 9(2), 93-103. https://doi.org/10.1007/s12518-017-0189-8.
  2. AL-Hawarneh, M. and Alam, M.S., (2021), "Lateral cyclic response of RC bridge piers made of recycled concrete: Experimental study", J. Bridge Eng., 26(5), 04021018. https://doi.org/10.1061/(ASCE)BE.1943-5592.0001703.
  3. Asjodi, A.H. and Dolatshahi, K.M. (2022), "Peak drift ratio estimation for unreinforced masonry walls using visual features of damage", Bull. Earthq. Eng., 20(15), 8357-8379. https://doi.org/10.1007/s10518-022-01523-8.
  4. Asjodi, A.H., Dolatshahi, K.M. and Ebrahimkhanlou, A. (2022), "Spatial analysis of damage evolution in cyclic-loaded reinforced concrete shear walls", J. Build. Eng., 49, 104032. https://doi.org/10.1016/j.jobe.2022.104032.
  5. Azadvar, N., Zargaran, M., Rofooei, F.R. and Attari, N.K. (2021), "Experimental comparison of cyclic behavior of RC columns strengthened with TRC and FRP", Bull. Earthq. Eng., 19(7), 2941-2970. https://doi.org/10.1007/s10518-021-01092-2.
  6. Bengio, Y., Simard, P. and Frasconi, P. (1994), "Learning long-term dependencies with gradient descent is difficult", IEEE Trans. Neur. Network., 5(2), 157-166. https://doi.org/10.1109/72.279181.
  7. Brownlee, J. (2017), Long Short-Term Memory Networks with Python: Develop Sequence Prediction Models with Deep Learning, Machine Learning Mastery.
  8. Brownlee, J. (2019a), "How to use the timedistributed layer in Keras", https://machinelearningmastery.com/timedistributedlayer-for-long-short-term-memory-networks-in-python/.
  9. Brownlee, J. (2019b), "How to scale data for long short-term memory networks in Python", https://machinelearningmastery.com/how-to-scale-data-forlong-short-term-memory-networks-in-python/.
  10. Brownlee, J. (2020a), "How to develop LSTM models for time series forecasting", https://machinelearningmastery.com/howto-develop-lstm-models-for-time-series-forecasting/.
  11. Brownlee, J. (2020b), "Time series forecasting with the long shortterm memory network in Python", https://machinelearningmastery.com/time-series-forecastinglong-short-term-memory-network-python/.
  12. Brownlee, J. (2020c), "Multistep Time Series Forecasting with LSTMs in Python", https://machinelearningmastery.com/multistep-time-series-forecasting-long-short-term-memory-networkspython/.
  13. Brownlee, J. (2020d), "How to use data scaling improve deep learning model stability and performance", https://machinelearningmastery.com/how-to-improve-neuralnetwork-stability-and-modeling-performance-with-datascaling/.
  14. Brownlee, J. (2021), "How to develop a bidirectional LSTM for sequence classification in python with Keras", https://machinelearningmastery.com/develop-bidirectional-lstmsequence-classification-pythonkeras/?msclkid=3d98c117cb9411ec83d5ea6f498c018c.
  15. Brownlee, J. (2022a), "Time series prediction with LSTM recurrent neural networks in python with Keras", https://machinelearningmastery.com/time-series-predictionlstm-recurrent-neural-networks-python-keras/.
  16. Brownlee, J. (2022b), "How to grid search hyperparameters for deep learning models in python with Keras", https://machinelearningmastery.com/grid-searchhyperparameters-deep-learning-models-python-keras/.
  17. Chae, Y. and Park, J. (2022), "Multi-axial cyclic loading tests for RC shear walls of nuclear power plant structures", Eng. Struct., 253, 113779. https://doi.org/10.1016/j.engstruct.2021.113779.
  18. Chae, Y., Kazemibidokhti, K. and Ricles, J.M. (2013), "Adaptive time series compensator for delay compensation of servo- hydraulic actuator systems for real-time hybrid simulation", Earthq. Eng. Struct. Dyn., 42(11), 1697-1715. https://doi.org/10.1002/eqe.2294.
  19. Chae, Y., Lee, J., Park, M. and Kim, C.Y. (2018b), "Real-time hybrid simulation for an RC bridge pier subjected to both horizontal and vertical ground motions", Earthq. Eng. Struct. Dyn., 47(7), 1673-1679. https://doi.org/10.1002/eqe.3042.
  20. Chae, Y., Lee, J., Park, M. and Kim, C.Y. (2019), "Fast and slow cyclic tests for reinforced concrete columns with an improved axial force control", J. Struct. Eng., 145(6), 04019044. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002334.
  21. Chae, Y., Park, M., Kim, C.Y. and Park, Y.S. (2017), "Experimental study on the rate-dependency of reinforced concrete structures using slow and real-time hybrid simulations", Eng. Struct., 132, 648-658. https://doi.org/10.1016/j.engstruct.2016.11.065.
  22. Chae, Y., Rabiee, R., Dursun, A. and Kim, C.Y. (2018a), "Real- time force control for servo-hydraulic actuator systems using adaptive time series compensator and compliance springs", Earthq. Eng. Struct. Dyn., 47(4), 854-871. https://doi.org/10.1002/eqe.2994.
  23. Chang, M.K., Kwiatkowski, J.W., Nau, R.F., Oliver, R.M. and Pister, K.S. (1982), "ARMA models for earthquake ground motions", Earthq. Eng. Struct. Dyn., 10(5), 651-662. https://doi.org/10.1002/eqe.4290100503.
  24. Eshkevari, S.S., Cronin, L., Eshkevari, S.S. and Pakzad, S.N. (2022), "Input estimation of nonlinear systems using probabilistic neural network", Mech. Syst. Signal Pr., 166, 108368. https://doi.org/10.1016/j.ymssp.2021.108368.
  25. Fayaz, J. and Galasso, C. (2022), "A generalized ground-motion model for consistent mainshock-aftershock intensity measures using successive recurrent neural networks", Bull. Earthq. Eng., 20(12), 6467-6486. https://doi.org/10.1007/s10518-022-01432-w.
  26. Goller, C. and Kuchler, A. (1996), "Learning task-dependent distributed representations by backpropagation through structure", Proceedings of International Conference on Neural Networks (ICNN'96), 1, 347-352, June. https://doi.org/10.1109/ICNN.1996.548916.
  27. Graves, A. and Schmidhuber, J. (2005), "Framewise phoneme classification with bidirectional LSTM and other neural network architectures", Neur. Network., 18(5-6), 602-610. https://doi.org/10.1016/j.neunet.2005.06.042.
  28. Hamidia, M, Afzali, M. and Jamshidian, S. (2023), "Postearthquake stiffness loss estimation for reinforced concrete columns using fractal analysis of crack patterns", Struct. Concrete. (in Press)
  29. Hamidia, M. and Ganjizadeh, A. (2022a), "Post-earthquake damage evaluation of non-ductile RC moment frames using surface crack patterns", Struct. Control Hlth. Monit., 29(10), e3024. https://doi.org/10.1002/stc.3024.
  30. Hamidia, M. and Ganjizadeh, A. (2022b), "Computer vision-based automated stiffness loss estimation for seismically damaged non-ductile reinforced concrete moment frames", Bull. Earthq. Eng., 20(12), 6635-6658. https://doi.org/10.1007/s10518-022-01408-w.
  31. Hamidia, M., Ganjizadeh, A. and Dolatshahi, K.M. (2022), "Peak drift ratio estimation for RC moment frames using multifractal dimensions of surface crack patterns", Eng. Struct., 255, 113893. https://doi.org/10.1016/j.engstruct.2022.113893
  32. Hochreiter, S. (1991), "Untersuchungen zu dynamischen neuronalen Netzen", Diploma, Technische Universitat Munchen.
  33. Hochreiter, S. (1998), "The vanishing gradient problem during learning recurrent neural nets and problem solutions", Int. J. Uncertain., Fuzz. Knowled.-Bas. Syst., 6(02), 107-116. https://doi.org/10.1142/S0218488598000094.
  34. Hochreiter, S. and Schmidhuber, J. (1997), "Long short-term memory", Neur. Comput., 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735.
  35. Huang, P. and Chen, Z. (2021), "Deep learning for nonlinear seismic responses prediction of subway station", Eng. Struct., 244, 112735. https://doi.org/10.1016/j.engstruct.2021.112735.
  36. Jeon, J.S., Shafieezadeh, A. and DesRoches, R. (2014), "Statistical models for shear strength of RC beam-column joints using machine-learning techniques", Earthq. Eng. Struct. Dyn., 43(14), 2075-2095. https://doi.org/10.1002/eqe.2437.
  37. Jordan, M.I. (1997), "Serial order: A parallel distributed processing approach", Adv. Psychol., 121, 471-495. https://doi.org/10.1016/S0166-4115(97)80111-2.
  38. Kalchbrenner, N. and Blunsom, P. (2013), "Recurrent continuous translation models", Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, October.
  39. Kanwal, A., Lau, M.F., Ng, S.P., Sim, K.Y. and Chandrasekaran, S. (2022), "BiCuDNNLSTM-1dCNN-A hybrid deep learningbased predictive model for stock price prediction", Exp. Syst. Appl., 202, 117123. https://doi.org/10.1016/j.eswa.2022.117123.
  40. Kingma, D.P. and Ba, J. (2014), Adam: A Method for Stochastic Optimization, arXiv Preprint arXiv,1412.6980.
  41. Korea Road and Transportation Association (2012), Bridge Design Specifications (Limit State Design Method), Gunsulbook. (in Korean)
  42. Kundu, A., Ghosh, S. and Chakraborty, S. (2022), "A long shortterm memory based deep learning algorithm for seismic response uncertainty quantification", Prob. Eng. Mech., 67, 103189. https://doi.org/10.1016/j.probengmech.2021.103189.
  43. Lamarche, C.P. and Tremblay, R. (2011), "Seismically induced cyclic buckling of steel columns including residual-stress and strain-rate effects", J. Constr. Steel Res., 67(9), 1401-1410. https://doi.org/10.1016/j.jcsr.2010.10.008.
  44. Mansourdehghan, S., Dolatshahi, K.M. and Asjodi, A.H. (2022), "Data-driven damage assessment of reinforced concrete shear walls using visual features of damage", J. Build. Eng., 53, 104509. https://doi.org/10.1016/j.jobe.2022.104509.
  45. Modhej, A. and Zahrai, S.M. (2022), "Cyclic testing of a new visco-plastic damper subjected to harmonic and quasi-static loading", Struct. Eng. Mech., 81(3), 317-333. https://doi.org/10.12989/sem.2022.81.3.317.
  46. Mousavi, S.M. and Beroza, G.C. (2020), "A machine-learning approach for earthquake magnitude estimation", Geophys. Res. Lett., 47(1), e2019GL085976. https://doi.org/10.1029/2019GL085976.
  47. Oh, B.K., Park, Y. and Park, H.S. (2020), "Seismic response prediction method for building structures using convolutional neural network", Struct. Control Hlth. Monit., 27(5), e2519. https://doi.org/10.1002/stc.2519.
  48. Olah, C. (2015), Understanding LSTM Networks, http://colah.github.io/posts/2015-08-Understanding-LSTMs/.
  49. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, E. (2011), "Scikit-learn: Machine learning in Python", J. Mach. Learn. Res., 12, 2825-2830.
  50. Python Keras Adam optimizer library, https://keras.io/api/optimizers/adam/.
  51. Salehi, M., Valigura, J., Sideris, P. and Liel, A.B. (2021), "Experimental assessment of second-generation hybrid slidingrocking bridge columns under reversed lateral loading for free and fixed end rotation conditions", J. Bridge Eng., 26(10), 04021071. https://doi.org/10.1061/(ASCE)BE.1943-5592.0001773.
  52. Samara, A.K. and Abandah, G.A. (2021), "Investigating fast BiLSTM neural networks for arabic language applications", 2021 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT), 250-255. https://doi.org/10.1109/jeeit53412.2021.9634153.
  53. Schuster, M. and Paliwal, K.K. (1997), "Bidirectional recurrent neural networks", IEEE Trans. Signal Pr., 45(11), 2673-2681. https://doi.org/10.1109/78.650093.
  54. The NVIDIA CUDA® Deep Neural Network Library (cuDNN11.2) (2021). https://developer.nvidia.com/cudnn.
  55. Wang, J. (2021), "An intelligent computer-aided approach for atrial fibrillation and atrial flutter signals classification using modified bidirectional LSTM network", Inform. Sci., 574, 320-332. https://doi.org/10.1016/j.ins.2021.06.009.
  56. Yang, F., Moayedi, H. and Mosavi, A. (2021), "Predicting the degree of dissolved oxygen using three types of multi-layer perceptron-based artificial neural networks", Sustain., 13(17), 9898. https://doi.org/10.3390/su13179898.
  57. Yazdanpanah, O., Chang, M., Park, M. and Kim, C.Y. (2022), "Seismic response prediction of RC bridge piers through stacked long short-term memory network", Struct., 45, 1990-2006. https://doi.org/10.1016/j.istruc.2022.10.015.
  58. Yazdanpanah, O., Dolatshahi, K.M. and Moammer, O. (2021), "Earthquake-induced economic loss estimation of eccentrically braced frames through roof acceleration-based nonmodel approach", J. Constr. Steel Res., 187, 106888. https://doi.org/10.1016/j.jcsr.2021.106888.
  59. Yazdanpanah, O., Dolatshahi, K.M. and Moammer, O. (2023), "Rapid seismic fragility curves assessment of eccentrically braced frames through an output-only nonmodel-based procedure and machine learning techniques", Eng. Struct., 278, 115290. https://doi.org/10.1016/j.engstruct.2022.115290.
  60. Yu, Y., Yang, Y., Xue, Y., Wang, N. and Liu, Y. (2020), "Cyclic tests on RC joints retrofitted with pre-stressed steel strips and bonded steel plates", Struct. Eng. Mech., 75(6), 675-684. https://doi.org/10.12989/sem.2020.75.6.675.
  61. Zhang, R., Chen, Z., Chen, S., Zheng, J., Buyukozturk, O. and Sun, H. (2019), "Deep long short-term memory networks for nonlinear structural seismic response prediction", Comput. Struct., 220, 55-68. https://doi.org/10.1016/j.compstruc.2019.05.006.
  62. Zhang, R., Liu, Y. and Sun, H. (2020), "Physics-informed multiLSTM networks for metamodeling of nonlinear structures", Comput. Meth. Appl. Mech. Eng., 369, 113226. https://doi.org/10.1016/j.cma.2020.113226.