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

Simple item page
dc.contributor.authorWang, Yinanen
dc.contributor.authorOyen, Dianeen
dc.contributor.authorGuo, Weihong (Grace)en
dc.contributor.authorMehta, Anishien
dc.contributor.authorScott, Cory Brakeren
dc.contributor.authorPanda, Nishanten
dc.contributor.authorFernandez-Godino, M. Giselleen
dc.contributor.authorSrinivasan, Gowrien
dc.contributor.authorYue, Xiaoweien
dc.contributor.departmentIndustrial and Systems Engineeringen
dc.date.accessioned2021-05-19T13:02:58Zen
dc.date.available2021-05-19T13:02:58Zen
dc.date.issued2021-02-10en
dc.description.abstractCatastrophic 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 20seconds, as compared to the FDEM run time of 4h, with an average MAPE of 2% relative to test data.en
dc.description.notesD.O., N.P., and G.S. were supported by the Laboratory Directed Research and Development program of Los Alamos National Laboratory under project number 20170103DR; Y.W. was supported by the LANL Applied Machine Learning Summer Research Fellowship; X.Y. were partially supported by the National Science Foundation under project number 1855651.en
dc.description.sponsorshipLaboratory Directed Research and Development program of Los Alamos National Laboratory [20170103DR]; LANL Applied Machine Learning Summer Research Fellowship; National Science FoundationNational Science Foundation (NSF) [1855651]en
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.1038/s41529-021-00151-yen
dc.identifier.eissn2397-2106en
dc.identifier.issue1en
dc.identifier.other6en
dc.identifier.urihttp://hdl.handle.net/10919/103377en
dc.identifier.volume5en
dc.language.isoenen
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.titleStressNet - Deep learning to predict stress with fracture propagation in brittle materialsen
dc.title.serialNpj Materials Degradationen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.dcmitypeStillImageen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
s41529-021-00151-y.pdf
Size:
2.09 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

Scholarly Works, Industrial and Systems Engineering
Open Access Subvention Fund Articles