2019
DOI: 10.1115/1.4044097
|View full text |Cite
|
Sign up to set email alerts
|

Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networks

Abstract: The demand for fast and accurate structural analysis is becoming increasingly more prevalent with the advance of generative design and topology optimization technologies. As one step toward accelerating structural analysis, this work explores a deep learning based approach for predicting the stress fields in 2D linear elastic cantilevered structures subjected to external static loads at its free end using convolutional neural networks (CNN). Two different architectures are implemented that take as input the st… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
77
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 160 publications
(77 citation statements)
references
References 44 publications
0
77
0
Order By: Relevance
“…Moreover, in order to support the object-oriented modeling (i.e., constructing design by compositing elements) of morphing materials design, we take inspiration from the GCN in [3,26,34] and use graphical representations in this work. Unlike convolutional neural networks (CNN) [27] that require high-resolution voxelization/pixelization, GCN also takes advantage of the model's intrinsic topology to represent them with fewer yet more effective features and make ML models easier to train.…”
Section: Data-driven Simulationmentioning
confidence: 99%
“…Moreover, in order to support the object-oriented modeling (i.e., constructing design by compositing elements) of morphing materials design, we take inspiration from the GCN in [3,26,34] and use graphical representations in this work. Unlike convolutional neural networks (CNN) [27] that require high-resolution voxelization/pixelization, GCN also takes advantage of the model's intrinsic topology to represent them with fewer yet more effective features and make ML models easier to train.…”
Section: Data-driven Simulationmentioning
confidence: 99%
“…The timestamp indicates the spatiotemporal extension of the image-variate information. Equations (19) to (23) show the kernel equations of convolutional LSTM described in [45].…”
Section: Neural Network Modelmentioning
confidence: 99%
“…Nie et al explored a deep learning strategy to accelerate the computation of constitutive relationships [ 23 ]. Convolutional neural networks (CNNs) are beneficial in determining the FEA stress field regarding a two-dimensional cantilevered structure.…”
Section: Introductionmentioning
confidence: 99%
“…Nash et al 13 reviewed the most recent deep learning methods for detection, modeling, and planning for material deterioration. Nie et al 14 used Encoder-Decoder Structure based on Convolutional Neural Network (CNN) to generate the stress field in cantilevered structures. However, these methods do not consider temporal dynamics of the stress field or fracture within the material.…”
Section: Introductionmentioning
confidence: 99%