A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis

Liang, Liang; Liu, Minliang; Martin, Caitlin; Sun, Wei

doi:10.1098/rsif.2017.0844

Cited by 301 publications

(154 citation statements)

References 51 publications

Supporting

Mentioning

154

Contrasting

Order By: Relevance

“…This is also possible according as we increase the number of predictors in the model, as indicated by Kohavi et al [44], or using reinforced learning algorithms, however in both cases it would imply having more patient data, being a very difficult task to fulfill, although undoubtedly, these results may be used as support for neurosurgeons. Respect to the time-computing limitations (considering both the CFD and training simulations), we may improve it using a deep learning approach to estimate the TAWSS [45], and then, to use the results in a new model to predict the rupture risk.…”

Section: Machine Learning Results and Discussionmentioning

confidence: 99%

Untitled

2016

MLAIJ

View full text Add to dashboard Cite

show abstract

Section: Machine Learning Results and Discussionmentioning

confidence: 99%

Untitled

2016

MLAIJ

View full text Add to dashboard Cite

show abstract

“…Khadilkar et al [41] use CNN to predict the stress field for the bottom-up SLA 3D printing process. In an inspiring work, Liang et al [23] develop a three-module convolutional network for aortic wall stress prediction to accelerate the patient-specific FEA. The network takes as input the tube-shaped geometry and outputs the stress field.…”

Section: Background and Related Workmentioning

confidence: 99%

Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networks

Nie

Jiang

Kara

2019

Journal of Computing and Information Science in Engineering

125

View full text Add to dashboard Cite

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 structure geometry, external loads, and displacement boundary conditions, and output the predicted von Mises stress field. The first is a single input channel network called SCSNet as the baseline architecture, and the second is the multi-channel input network called StressNet. Accuracy analysis shows that StressNet results in significantly lower prediction errors than SCSNet on three loss functions, with a mean relative error of 2.04% for testing. These results suggest that deep learning models may offer a promising alternative to classical methods in structural design and topology optimization. Code and dataset are available at https: // github. com/ zhenguonie/ stress_ net

show abstract

“…In addition to the field of AI, DNN has also been utilized in diverse scientific disciplines, including the fields of biomedicine (Liang et al, 2018;Shashikumar et al, 2018), economics (Singh & Srivastava, 2017;Yong et al, 2017), chemistry (Fooshee et al, 2018;Sun et al, 2019), and physics (Bhimji et al, 2018;Sadowski & Baldi, 2018). Despite the numerous successes obtained with DNN, limitations remain concerning the application of DNN in numerous scientific problems due to the following reasons: First, a large amount of data is usually requisite to guarantee model accuracy.…”

Section: Introductionmentioning

confidence: 99%

Deep learning of subsurface flow via theory-guided neural network

Wang

Zhang

Chang

et al. 2020

Journal of Hydrology

169

View full text Add to dashboard Cite

Active researches are currently being performed to incorporate the wealth of scientific knowledge into data-driven approaches (e.g., neural networks) in order to improve the latter's effectiveness. In this study, the Theory-guided Neural Network (TgNN) is proposed for deep learning of subsurface flow. In the TgNN, as supervised learning, the neural network is trained with available observations or simulation data while being simultaneously guided by theory (e.g., governing equations, other physical constraints, engineering controls, and expert knowledge) of the underlying problem. The TgNN can achieve higher accuracy than the ordinary Artificial Neural Network (ANN) because the former provides physically feasible predictions and can be more readily generalized beyond the regimes covered with the training data. Furthermore, the TgNN model is proposed for subsurface flow with heterogeneous model parameters. Several numerical cases of two-dimensional transient saturated flow are introduced to test the performance of the TgNN. In the learning process, the loss function contains data mismatch, as well as PDE constraint, engineering control, and expert knowledge. After obtaining the parameters of the neural network by minimizing the loss function, a TgNN model is built that not only fits the data, but also adheres to physical/engineering constraints. Predicting the future response can be easily realized by the TgNN model. In addition, the TgNN model is tested in more complicated scenarios, such as prediction with changed boundary conditions, learning from noisy data or outliers, transfer learning, and engineering controls. Numerical results demonstrate that the TgNN model achieves much better predictability, reliability, and generalizability than ANN models due to the physical/engineering constraints in the former.

show abstract

A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis

Cited by 301 publications

References 51 publications

Untitled

Untitled

Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networks

Deep learning of subsurface flow via theory-guided neural network

Contact Info

Product

Resources

About