TY - JOUR
T1 - Recognition of Nonlinear Hysteretic Behavior by Neural Network using Deep Learning
AU - Mazda, Taiji
AU - Kajita, Yukihide
AU - Akedo, Takashi
AU - Hazama, Tsubasa
N1 - Publisher Copyright:
© Published under licence by IOP Publishing Ltd.
PY - 2020/6/12
Y1 - 2020/6/12
N2 - In Japan, large earthquakes have caused many damages to structures. Cracks in the reinforced concrete and plasticization of the steel bar and steel components resulted in increased damage. In the seismic design, the dynamic response analysis is carried out by using a mathematical model that appropriately evaluates the nonlinearity of the material and the components and the seismic performance is confirmed by performing a dynamic response analysis. However, when applying new materials and components, much time and much effort are required to select a mathematical model. In this study, we focused on the high pattern recognition capability of the neural network. We attempt to directly model using a neural network without replacing the complex nonlinear hysteretic behavior using the mathematical model. By improvement of learning data and introduction of deep learning, it was confirmed that the recognition ability for nonlinear hysteretic behavior of neural network was greatly improved, and its applicability as a numerical operation subroutine for time history response analysis was drastically improved.
AB - In Japan, large earthquakes have caused many damages to structures. Cracks in the reinforced concrete and plasticization of the steel bar and steel components resulted in increased damage. In the seismic design, the dynamic response analysis is carried out by using a mathematical model that appropriately evaluates the nonlinearity of the material and the components and the seismic performance is confirmed by performing a dynamic response analysis. However, when applying new materials and components, much time and much effort are required to select a mathematical model. In this study, we focused on the high pattern recognition capability of the neural network. We attempt to directly model using a neural network without replacing the complex nonlinear hysteretic behavior using the mathematical model. By improvement of learning data and introduction of deep learning, it was confirmed that the recognition ability for nonlinear hysteretic behavior of neural network was greatly improved, and its applicability as a numerical operation subroutine for time history response analysis was drastically improved.
UR - http://www.scopus.com/inward/record.url?scp=85088134603&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85088134603&partnerID=8YFLogxK
U2 - 10.1088/1757-899X/809/1/012010
DO - 10.1088/1757-899X/809/1/012010
M3 - Conference article
AN - SCOPUS:85088134603
VL - 809
JO - IOP Conference Series: Materials Science and Engineering
JF - IOP Conference Series: Materials Science and Engineering
SN - 1757-8981
IS - 1
M1 - 012010
T2 - 2019 5th International Conference on Architecture, Materials and Construction, ICAMC 2019
Y2 - 2 December 2019 through 4 December 2019
ER -