Computational mechanics enhanced by deep learning

A Oishi, G Yagawa - Computer Methods in Applied Mechanics and …, 2017 - Elsevier
The present paper describes a method to enhance the capability of, or to broaden the scope
of computational mechanics by using deep learning, which is one of the machine learning …

Physics-based urban earthquake simulation enhanced by 10.7 BlnDOF× 30 K time-step unstructured FE non-linear seismic wave simulation

T Ichimura, K Fujita, S Tanaka, M Hori… - SC'14: Proceedings …, 2014 - ieeexplore.ieee.org
With the aim of dramatically improving the reliability of urban earthquake response analyses,
we developed an unstructured 3-D finite-element-based MPI-OpenMP hybrid seismic wave …

Finite‐element analysis of laminated rubber bearing of building frame under seismic excitation

M Ohsaki, T Miyamura, M Kohiyama… - Earthquake …, 2015 - Wiley Online Library
Finite element analysis is carried out for a building frame supported by laminated rubber
bearings to simultaneously investigate global displacement and local stress responses …

Implicit nonlinear wave simulation with 1.08 T DOF and 0.270 T unstructured finite elements to enhance comprehensive earthquake simulation

T Ichimura, K Fujita, PEB Quinay… - Proceedings of the …, 2015 - dl.acm.org
This paper presents a new heroic computing method for unstructured, low-order, finite-
element, implicit nonlinear wave simulation: 1.97 PFLOPS (18.6% of peak) was attained on …

[HTML][HTML] Development of surrogate predictive models for the nonlinear elasto-plastic response of medium density fibreboard-based sandwich structures

YJ Wong, KB Mustapha, Y Shimizu, A Kamiya… - International Journal of …, 2021 - Elsevier
Medium-density fibreboard (MDF) belongs to a class of engineered wood products
facilitating efficient use of wood wastes. For this class of materials, the development of …

Sustainable computational mechanics assisted by deep learning

A Oishi, G Yagawa - Computer Methods in Applied Mechanics and …, 2022 - Elsevier
This paper proposes a method to promote power saving in the computational mechanics
simulations by deep learning. The method is expected to contribute to the achievement of …

A surface-to-surface contact search method enhanced by deep learning

A Oishi, G Yagawa - Computational Mechanics, 2020 - Springer
This paper describes a new surface-to-surface contact search method for contact problems
between curved surfaces defined by the non-uniform rational B-spline basis functions. The …

Dynamic FE simulation of four‐story steel frame modeled by solid elements and its validation using results of full‐scale shake‐table test

T Miyamura, T Yamashita, H Akiba… - … & Structural Dynamics, 2015 - Wiley Online Library
Dynamic finite element analyses of a four‐story steel building frame modeled as a fine mesh
of solid elements are performed using E‐Simulator, which is a parallel finite element …

Finite elements using neural networks and a posteriori error

A Oishi, G Yagawa - Archives of Computational Methods in Engineering, 2021 - Springer
As the finite element method requires many nodes or elements to obtain accurate results,
the adaptive finite element method has been developed to obtain better results with fewer …

Coupled structural and heat conduction FE analysis of laminated high dam** rubber bearing

T Miyamura, M Ohsaki, J Fujiwara… - … & Structural Dynamics, 2021 - Wiley Online Library
A framework for coupled structural and heat conduction finite element analysis is developed
for laminated high dam** rubber bearings (HDRBs), and coupled analyses are conducted …