$StressNet - Deep learning to predict stress with fracture propagation in brittle materials$
Código QR

StressNet - Deep learning to predict stress with fracture propagation in brittle materials

Abstract Catastrophic failure in brittle materials is often due to the rapid growth and coalescence of cracks aided by high internal stresses. Hence, accurate prediction of maximum internal stress is critical to predicting time to failure and improving the fracture resistance and reliability of mate...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yinan Wang, Diane Oyen, Weihong (Grace) Guo, Anishi Mehta, Cory Braker Scott, Nishant Panda, M. Giselle Fernández-Godino, Gowri Srinivasan, Xiaowei Yue
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492
Acceso en línea:	https://doaj.org/article/47873e5969e84597a0ca8f3758f5d4bf
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:47873e5969e84597a0ca8f3758f5d4bf
record_format	dspace
spelling	oai:doaj.org-article:47873e5969e84597a0ca8f3758f5d4bf2021-12-02T14:11:01ZStressNet - Deep learning to predict stress with fracture propagation in brittle materials10.1038/s41529-021-00151-y2397-2106https://doaj.org/article/47873e5969e84597a0ca8f3758f5d4bf2021-02-01T00:00:00Zhttps://doi.org/10.1038/s41529-021-00151-yhttps://doaj.org/toc/2397-2106Abstract Catastrophic failure in brittle materials is often due to the rapid growth and coalescence of cracks aided by high internal stresses. Hence, accurate prediction of maximum internal stress is critical to predicting time to failure and improving the fracture resistance and reliability of materials. Existing high-fidelity methods, such as the Finite-Discrete Element Model (FDEM), are limited by their high computational cost. Therefore, to reduce computational cost while preserving accuracy, a deep learning model, StressNet, is proposed to predict the entire sequence of maximum internal stress based on fracture propagation and the initial stress data. More specifically, the Temporal Independent Convolutional Neural Network (TI-CNN) is designed to capture the spatial features of fractures like fracture path and spall regions, and the Bidirectional Long Short-term Memory (Bi-LSTM) Network is adapted to capture the temporal features. By fusing these features, the evolution in time of the maximum internal stress can be accurately predicted. Moreover, an adaptive loss function is designed by dynamically integrating the Mean Squared Error (MSE) and the Mean Absolute Percentage Error (MAPE), to reflect the fluctuations in maximum internal stress. After training, the proposed model is able to compute accurate multi-step predictions of maximum internal stress in approximately 20 seconds, as compared to the FDEM run time of 4 h, with an average MAPE of 2% relative to test data.Yinan WangDiane OyenWeihong (Grace) GuoAnishi MehtaCory Braker ScottNishant PandaM. Giselle Fernández-GodinoGowri SrinivasanXiaowei YueNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492ENnpj Materials Degradation, Vol 5, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Yinan Wang Diane Oyen Weihong (Grace) Guo Anishi Mehta Cory Braker Scott Nishant Panda M. Giselle Fernández-Godino Gowri Srinivasan Xiaowei Yue StressNet - Deep learning to predict stress with fracture propagation in brittle materials
description	Abstract Catastrophic failure in brittle materials is often due to the rapid growth and coalescence of cracks aided by high internal stresses. Hence, accurate prediction of maximum internal stress is critical to predicting time to failure and improving the fracture resistance and reliability of materials. Existing high-fidelity methods, such as the Finite-Discrete Element Model (FDEM), are limited by their high computational cost. Therefore, to reduce computational cost while preserving accuracy, a deep learning model, StressNet, is proposed to predict the entire sequence of maximum internal stress based on fracture propagation and the initial stress data. More specifically, the Temporal Independent Convolutional Neural Network (TI-CNN) is designed to capture the spatial features of fractures like fracture path and spall regions, and the Bidirectional Long Short-term Memory (Bi-LSTM) Network is adapted to capture the temporal features. By fusing these features, the evolution in time of the maximum internal stress can be accurately predicted. Moreover, an adaptive loss function is designed by dynamically integrating the Mean Squared Error (MSE) and the Mean Absolute Percentage Error (MAPE), to reflect the fluctuations in maximum internal stress. After training, the proposed model is able to compute accurate multi-step predictions of maximum internal stress in approximately 20 seconds, as compared to the FDEM run time of 4 h, with an average MAPE of 2% relative to test data.
format	article
author	Yinan Wang Diane Oyen Weihong (Grace) Guo Anishi Mehta Cory Braker Scott Nishant Panda M. Giselle Fernández-Godino Gowri Srinivasan Xiaowei Yue
author_facet	Yinan Wang Diane Oyen Weihong (Grace) Guo Anishi Mehta Cory Braker Scott Nishant Panda M. Giselle Fernández-Godino Gowri Srinivasan Xiaowei Yue
author_sort	Yinan Wang
title	StressNet - Deep learning to predict stress with fracture propagation in brittle materials
title_short	StressNet - Deep learning to predict stress with fracture propagation in brittle materials
title_full	StressNet - Deep learning to predict stress with fracture propagation in brittle materials
title_fullStr	StressNet - Deep learning to predict stress with fracture propagation in brittle materials
title_full_unstemmed	StressNet - Deep learning to predict stress with fracture propagation in brittle materials
title_sort	stressnet - deep learning to predict stress with fracture propagation in brittle materials
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/47873e5969e84597a0ca8f3758f5d4bf
work_keys_str_mv	AT yinanwang stressnetdeeplearningtopredictstresswithfracturepropagationinbrittlematerials AT dianeoyen stressnetdeeplearningtopredictstresswithfracturepropagationinbrittlematerials AT weihonggraceguo stressnetdeeplearningtopredictstresswithfracturepropagationinbrittlematerials AT anishimehta stressnetdeeplearningtopredictstresswithfracturepropagationinbrittlematerials AT corybrakerscott stressnetdeeplearningtopredictstresswithfracturepropagationinbrittlematerials AT nishantpanda stressnetdeeplearningtopredictstresswithfracturepropagationinbrittlematerials AT mgisellefernandezgodino stressnetdeeplearningtopredictstresswithfracturepropagationinbrittlematerials AT gowrisrinivasan stressnetdeeplearningtopredictstresswithfracturepropagationinbrittlematerials AT xiaoweiyue stressnetdeeplearningtopredictstresswithfracturepropagationinbrittlematerials
_version_	1718391838308564992

StressNet - Deep learning to predict stress with fracture propagation in brittle materials

Ejemplares similares