TY - JOUR
T1 - Deep learning techniques for predicting nonlinear multi-component seismic responses of structural buildings
AU - Torky, Ahmed A.
AU - Ohno, Susumu
N1 - Funding Information:
The authors would like to acknowledge the support provided by the Building Research Institute (Japan) by providing strong motion records of the BRI annex building. This study was supported by JSPS KAKENHI Grant number 19K22002.
Funding Information:
The authors would like to acknowledge the support provided by the Building Research Institute (Japan) by providing strong motion records of the BRI annex building. This study was supported by JSPS KAKENHI Grant number 19K22002.
Publisher Copyright:
© 2021 Elsevier Ltd
PY - 2021/8
Y1 - 2021/8
N2 - This paper presents a new approach for nonlinear multi-component seismic response prediction of structures using hybrid deep learning techniques. Modern recurrent neural networks map the relationship between acceleration time-series of the base/ground of a building and the superstructure, as a form of nonlinear time-history analysis method. Seismic responses were measured in three components which enables multi-component seismic predictions with adequate deep learning architectures. While long short-term memory (LSTM) neural networks can obtain data from a single component per surrogate model, hybrid convolutional-LSTMs (ConvLSTM) neural networks are utilized for multi-component purposes. A guide for pre-processing data and structuring the architecture of deep neural networks are proposed. Also, two filtering methods are compared, Fast Fourier Transform (FFT) Butterworth filter and discrete wavelet transform (DWT) decomposition. Decimation is implemented to reduce the features to useful values, as a dimension reduction approach. With enhancements to the architecture of the network, training time can be reduced significantly, and accuracy could be further improved. A challenging case study is addressed that covers an industrial level practical building. Results show that proposed hybrid models can even predict the capacity curves of a structure indirectly, providing new prospects for engineers to evaluate the seismic performance of a building.
AB - This paper presents a new approach for nonlinear multi-component seismic response prediction of structures using hybrid deep learning techniques. Modern recurrent neural networks map the relationship between acceleration time-series of the base/ground of a building and the superstructure, as a form of nonlinear time-history analysis method. Seismic responses were measured in three components which enables multi-component seismic predictions with adequate deep learning architectures. While long short-term memory (LSTM) neural networks can obtain data from a single component per surrogate model, hybrid convolutional-LSTMs (ConvLSTM) neural networks are utilized for multi-component purposes. A guide for pre-processing data and structuring the architecture of deep neural networks are proposed. Also, two filtering methods are compared, Fast Fourier Transform (FFT) Butterworth filter and discrete wavelet transform (DWT) decomposition. Decimation is implemented to reduce the features to useful values, as a dimension reduction approach. With enhancements to the architecture of the network, training time can be reduced significantly, and accuracy could be further improved. A challenging case study is addressed that covers an industrial level practical building. Results show that proposed hybrid models can even predict the capacity curves of a structure indirectly, providing new prospects for engineers to evaluate the seismic performance of a building.
KW - Convolutional long short-term memory neural networks
KW - Deep neural networks
KW - Discrete wavelet transforms
KW - Multi-component response
KW - Nonlinear seismic response prediction
UR - http://www.scopus.com/inward/record.url?scp=85107668040&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107668040&partnerID=8YFLogxK
U2 - 10.1016/j.compstruc.2021.106570
DO - 10.1016/j.compstruc.2021.106570
M3 - Article
AN - SCOPUS:85107668040
VL - 252
JO - Computers and Structures
JF - Computers and Structures
SN - 0045-7949
M1 - 106570
ER -