Deep long short-term memory networks for nonlinear structural seismic response prediction

Abstract This paper presents a comprehensive study on developing advanced deep learning approaches for nonlinear structural response modeling and prediction. Two schemes of the long short-term memory (LSTM) network are proposed for data-driven structural seismic response modeling. The proposed deep learning model, trained on available datasets, is capable of accurately predicting both elastic and inelastic response of building structures in a data-driven fashion as opposed to the classical physics-based nonlinear time history analysis using numerical methods. In addition, an unsupervised learning algorithm based on a proposed dynamic K-means clustering approach is established to cluster the seismic inputs in order to (1) generate the least but the most informative datasets for training the LSTM and (2) improve the prediction accuracy and robustness of the model trained with limited data. The performance of the proposed approach is successfully demonstrated through three proof-of-concept studies that include a nonlinear hysteretic system, a real-world building with field sensing data, and a steel moment resisting frame. The results show that the proposed LSTM network is a promising, reliable and computationally efficient approach for nonlinear structural response prediction, and offers significant potential in seismic fragility analysis of buildings for reliability assessment.

[1]  Hoon Sohn,et al.  A review of structural health monitoring literature 1996-2001 , 2002 .

[2]  Stephen A. Billings,et al.  International Journal of Control , 2004 .

[3]  Lennart Ljung,et al.  Nonlinear black-box modeling in system identification: a unified overview , 1995, Autom..

[4]  K. Worden,et al.  Past, present and future of nonlinear system identification in structural dynamics , 2006 .

[5]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[6]  Jian Zhang,et al.  Advanced Markov Chain Monte Carlo Approach for Finite Element Calibration under Uncertainty , 2013, Comput. Aided Civ. Infrastructure Eng..

[7]  Raimondo Betti,et al.  A Hybrid Optimization Algorithm with Bayesian Inference for Probabilistic Model Updating , 2015, Comput. Aided Civ. Infrastructure Eng..

[8]  D. Dickey,et al.  Testing for unit roots in autoregressive-moving average models of unknown order , 1984 .

[9]  V. Ediger,et al.  ARIMA forecasting of primary energy demand by fuel in Turkey , 2007 .

[10]  Ting-Hua Yi,et al.  Multi-stage structural damage diagnosis method based on "energy-damage" theory , 2013 .

[11]  Lakhmi C. Jain,et al.  Recurrent Neural Networks: Design and Applications , 1999 .

[12]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[13]  Dimitrios Vamvatsikos,et al.  Incremental dynamic analysis for estimating seismic performance sensitivity and uncertainty , 2010 .

[14]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[15]  J. Ricles,et al.  Development of Direct Integration Algorithms for Structural Dynamics Using Discrete Control Theory , 2008 .

[16]  James E. Braun,et al.  An Inverse Gray-Box Model for Transient Building Load Prediction , 2002 .

[17]  P. A. Fishwick.  Neural network models in simulation: a comparison with traditional modeling approaches , 1989, WSC '89.

[18]  Nick Gregor,et al.  NGA Project Strong-Motion Database , 2008 .

[19]  Raimondo Betti,et al.  Identification of structural models using a modified Artificial Bee Colony algorithm , 2013 .

[20]  Hong Chen,et al.  Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networks , 1993, IEEE Trans. Neural Networks.

[21]  Michael Beer,et al.  An artificial neural network approach for stochastic process power spectrum estimation subject to missing data , 2015 .

[22]  François M. Hemez,et al.  Uncertainty and Sensitivity Analysis of Damage Identification Results Obtained Using Finite Element Model Updating , 2009, Comput. Aided Civ. Infrastructure Eng..

[23]  Ole Winther,et al.  Artificial Neural Networks for Nonlinear Dynamic Response Simulation in Mechanical Systems , 2011 .

[24]  James M. W. Brownjohn,et al.  Dynamic Assessment of Curved Cable-Stayed Bridge by Model Updating , 2000 .

[25]  Xiuyu Gao,et al.  Computational Tool for Real-Time Hybrid Simulation of Seismically Excited Steel Frame Structures , 2015 .

[26]  George W. Irwin,et al.  Multi-layer perceptron based modelling of nonlinear systems , 1996, Fuzzy Sets Syst..

[27]  Manolis Papadrakakis,et al.  Neural network based prediction schemes of the non-linear seismic response of 3D buildings , 2012, Adv. Eng. Softw..

[28]  Ruiyang Zhang,et al.  Shake table real‐time hybrid simulation techniques for the performance evaluation of buildings with inter‐story isolation , 2017 .

[29]  Dimitrios Vamvatsikos,et al.  Incremental dynamic analysis , 2002 .

[30]  H. Akaike.  Fitting autoregressive models for prediction , 1969 .

[31]  Raymond Y. K. Lau,et al.  Time series k-means: A new k-means type smooth subspace clustering for time series data , 2016, Inf. Sci..

[32]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[33]  Kai Qi,et al.  Adaptive H ∞ Filter: Its Application to Structural Identification , 1998 .

[34]  J. Durbin.  EFFICIENT ESTIMATION OF PARAMETERS IN MOVING-AVERAGE MODELS , 1959 .

[35]  Luis Volnei Sudati Sagrilo,et al.  Neural networks in the dynamic response analysis of slender marine structures , 2007 .

[36]  C. M. Wen,et al.  A neural network approach for structural identification and diagnosis of a building from seismic response data , 2003 .

[37]  Rih-Teng Wu,et al.  Deep Convolutional Neural Network for Structural Dynamic Response Estimation and System Identification , 2019, Journal of Engineering Mechanics.

[38]  John E. Mottershead,et al.  Finite Element Model Updating in Structural Dynamics , 1995 .

[39]  Ying Lei,et al.  Identification, Model Updating, and Response Prediction of an Instrumented 15-Story Steel-Frame Building , 2006 .

[40]  Danilo P. Mandic,et al.  Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability , 2001 .

[41]  Andreas Stavridis,et al.  System identification and modeling of a dynamically tested and gradually damaged 10‐story reinforced concrete building , 2018 .

[42]  Richard Sause,et al.  Seismic Response and Damage of Reduced-Strength Steel MRF Structures with Nonlinear Viscous Dampers , 2018, Journal of Structural Engineering.

[43]  W. Zielichowski-Haber.  Sensitivity analysis of uncertain structures subject to stochastic load in the framework of SFEM , 2005 .

[44]  Y. Wen.  Method for Random Vibration of Hysteretic Systems , 1976 .

[45]  Andrea Belleri,et al.  Damage assessment through structural identification of a three‐story large‐scale precast concrete structure , 2014 .

[46]  Ting-Hua Yi,et al.  Clustering Number Determination for Sparse Component Analysis during Output-Only Modal Identification , 2019, Journal of Engineering Mechanics.

[47]  Masanobu Shinozuka,et al.  Simulation of Nonstationary Stochastic Processes by Spectral Representation , 2007 .

[48]  Si-Da Zhou,et al.  A Data-Driven Response Virtual Sensor Technique with Partial Vibration Measurements Using Convolutional Neural Network , 2017, Sensors.

[49]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[50]  Lucia Tirca,et al.  Improving the Seismic Resilience of Existing Braced-Frame Office Buildings , 2016 .

[51]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[52]  George Deodatis,et al.  A multi-modal analytical non-stationary spectral model for characterization and stochastic simulation of earthquake ground motions , 2016 .

[53]  Wang Ying,et al.  Artificial Neural Network Prediction for Seismic Response of Bridge Structure , 2009, 2009 International Conference on Artificial Intelligence and Computational Intelligence.

[54]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[55]  M. Di Paola,et al.  Stochastic seismic analysis of MDOF structures with nonlinear viscous dampers , 2009 .