Search

Your search keyword '"Todoroki, Akira"' showing total 2,038 results
Start Over Author "Todoroki, Akira"
2,038 results on '"Todoroki, Akira"'

7. Convolutional Neural Network-based Topology Optimization (CNN-TO) By Estimating Sensitivity of Compliance from Material Distribution

Author

Takahashi, Yusuke, Suzuki, Yoshiro, and Todoroki, Akira

Subjects
Computer Science - Machine Learning, Computer Science - Computational Engineering, Finance, and Science
Abstract

This paper proposes a new topology optimization method that applies a convolutional neural network (CNN), which is one deep learning technique for topology optimization problems. Using this method, we acquire a structure with a little higher performance that could not be obtained by the previous topology optimization method. In particular, in this paper, we solve a topology optimization problem aimed at maximizing stiffness with a mass constraint, which is a common type of topology optimization. In this paper, we first formulate the conventional topology optimization by the solid isotropic material with penalization method. Next, we formulate the topology optimization using CNN. Finally, we show the effectiveness of the proposed topology optimization method by solving a verification example, namely a topology optimization problem aimed at maximizing stiffness. In this research, as a result of solving the verification example for a small design area of 16x32 element, we obtain the solution different from the previous topology optimization method. This result suggests that stiffness information of structure can be extracted and analyzed for structural design by analyzing the density distribution using CNN like an image. This suggests that CNN technology can be utilized in the structural design and topology optimization.

Published
2019

11. Design optimization of bio-inspired 3D printing by machine learning.

Author

Goto, Daiki, Matsuzaki, Ryosuke, and Todoroki, Akira

Subjects
ARTIFICIAL neural networks, THREE-dimensional printing, MATHEMATICAL optimization, STIFFNERS, MACHINE learning, QUADRATIC programming
Abstract

In this study, the stiffener geometry was optimized using curvilinear 3D printing to enhance the buckling resistance. A bio-inspired skin/stiffener composite that mimicked spider-web structures was generated. A dataset was formulated for the regression analysis, covering buckling stresses under distinct feature values. The regression equations, crafted using a deep neural network trained on the dataset, were evaluated. The derived regression equation was subjected to sequential quadratic programming, a mathematical optimization, to determine the optimal value of the explanatory variable. This was aimed at maximizing the buckling stress-to-stiffener volume ratio, which is the objective variable. The optimized arrangement exhibited significantly improved buckling resistance, with approximately 163% higher buckling stress than conventionally designed structures with straight stiffeners of similar weight. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

19. Effects of fiber orientation and resin-rich layers in carbon fiber reinforced thermoplastics on electromagnetic induction testing.

Author

Matsunaga, Wataru, Imai, Satoshi, Mizutani, Yoshihiro, and Todoroki, Akira

Subjects
ELECTROMAGNETIC testing, CARBON fiber testing, FIBER orientation, NONDESTRUCTIVE testing, ELECTROMAGNETIC induction
Abstract

In this study, we evaluated the effects of the fiber orientation and the presence of resin-rich layers on electromagnetic induction testing (EIT) of carbon fiber reinforced thermoplastics (CFRTPs). First, a finite-element analysis was performed to evaluate the distribution and path of the eddy and displacement currents induced in interlaminar conductive and interlaminar non-conductive CFRTP specimens. Second, interlaminar electrically conductive and interlaminar non-electrically conductive specimens of unidirectional CFRTP and cross-ply laminated CFRTP were fabricated using a 3D printer, with control of the number of PA-6 layers and fiber orientation. EIT of the specimens revealed that the presence of resin-rich layers and fiber orientation affected the measured EIT output. The results also indicated that the EIT of CFRTP with resin-rich layers requires penetration of displacement currents between the layers. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

38. Kink band orientation of 3D printed continuous carbon fiber composites under compressive loading.

Author

Bin Zakaria, Ahmad Zuhair, Takahashi, Takuya, Todoroki, Akira, and Ueda, Masahito

Subjects
CARBON composites, FIBROUS composites, COMPRESSION loads, CARBON fiber-reinforced plastics, FRACTURE mechanics
Abstract

For continuous carbon fiber-reinforced plastic (cCFRP), in the case of loading in the longitudinal direction, occurrence of kink band failure causes compression strength to be lower than the tensile strength. Furthermore, 3D-printed cCFRP may exhibit intrinsic compressive behavior depending on the printing orientation. In this study, two types of rectangular specimens were fabricated using the Markforged Mark Two > 3D printer. The first was the in-plane specimen, whose width direction was parallel to the print bed and thickness direction was along the layup direction. The second was the out-of-plane specimen, whose width direction was the layup direction and thickness direction was parallel to the print bed. Compression tests were performed, and the experimental results were compared. As a result, the compressive strengths of both types were similar, and the kink bands always grew in the lay-up direction. For the out-of-plane specimens, nonlinear stress–strain curves were observed. This may be due to the delamination crack growth caused by the low strength in the lay-up direction and the existence of initial defects. This study experimentally investigated the effect of two different printing orientations of 3D printed cCFRP to its strength and failure mode, and this work shows the importance of considering structural deformation due to compression loading in 3D printed cCFRP. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results