TY - GEN
T1 - Predicting nonlinear seismic response of structural braces using machine learning
AU - Bas, Elif Ecem
AU - Aslangil, Denis
AU - Moustafa, Mohamed Aly
N1 - Publisher Copyright:
© 2020 American Society of Mechanical Engineers (ASME). All rights reserved.
PY - 2020
Y1 - 2020
N2 - Numerical modeling of different structural materials that have highly nonlinear behaviors has always been a challenging problem in engineering disciplines. Experimental data is commonly used to characterize this behavior. This study aims to improve the modeling capabilities by using state of the art Machine Learning techniques, and attempts to answer several scientific questions: (i) Which ML algorithm is capable and is more efficient to learn such a complex and nonlinear problem? (ii) Is it possible to artificially reproduce structural brace seismic behavior that can represent real physics? (iii) How can our findings be extended to the different engineering problems that are driven by similar nonlinear dynamics? To answer these questions, the presented methods are validated by using experimental brace data. The paper shows that after proper data preparation, the long-short term memory (LSTM) method is highly capable of capturing the nonlinear behavior of braces. Additionally, the effects of tuning the hyperparameters on the models, such as layer numbers, neuron numbers, and the activation functions, are presented. Finally, the ability to learn nonlinear dynamics by using deep neural network algorithms and their advantages are briefly discussed.
AB - Numerical modeling of different structural materials that have highly nonlinear behaviors has always been a challenging problem in engineering disciplines. Experimental data is commonly used to characterize this behavior. This study aims to improve the modeling capabilities by using state of the art Machine Learning techniques, and attempts to answer several scientific questions: (i) Which ML algorithm is capable and is more efficient to learn such a complex and nonlinear problem? (ii) Is it possible to artificially reproduce structural brace seismic behavior that can represent real physics? (iii) How can our findings be extended to the different engineering problems that are driven by similar nonlinear dynamics? To answer these questions, the presented methods are validated by using experimental brace data. The paper shows that after proper data preparation, the long-short term memory (LSTM) method is highly capable of capturing the nonlinear behavior of braces. Additionally, the effects of tuning the hyperparameters on the models, such as layer numbers, neuron numbers, and the activation functions, are presented. Finally, the ability to learn nonlinear dynamics by using deep neural network algorithms and their advantages are briefly discussed.
KW - LSTM
KW - Machine learning
KW - Nonlinear behavior modeling
KW - Structural brace response behavior
UR - http://www.scopus.com/inward/record.url?scp=85101259769&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85101259769&partnerID=8YFLogxK
U2 - 10.1115/IMECE2020-24014
DO - 10.1115/IMECE2020-24014
M3 - Conference contribution
AN - SCOPUS:85101259769
T3 - ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)
BT - Mechanics of Solids, Structures, and Fluids
PB - American Society of Mechanical Engineers (ASME)
T2 - ASME 2020 International Mechanical Engineering Congress and Exposition, IMECE 2020
Y2 - 16 November 2020 through 19 November 2020
ER -