TY - GEN
T1 - Stochastic modelling of additively manufactured structures using a neural network for identification of random field parameters
AU - Pitz, Emil J.
AU - Rooney, Sean
AU - Pochiraju, Kishore V.
N1 - Publisher Copyright:
© ASC 2020.
PY - 2020
Y1 - 2020
N2 - Heterogeneous materials exhibit considerable spatial variations in properties, impacting structural performance and local stress and strain fields. Recent research has focused on considering material behaviour uncertainties and quantifying the impact of uncertainties on the structural response, requiring the definition of random fields for describing the material variability. In this paper, a stochastic modeling methodology for additively manufactured structures is implemented (forward model). The stochastic parameters are determined from experimental Digital Image Correlation (DIC) images (inverse problem) using a Convolutional Neural Network (CNN), and the CNN is trained using the forward model. Validation of the CNN estimates using previously unseen data shows adequate performance of the network, and consistent predictions are found when estimating the stochastic parameters from experimental results. The proposed methodology allows examination of the stochastic response and uncertainty quantification of additively manufactured structures, while requiring only minor experimental efforts to fully define the random fields. Once the CNN is trained, computational expense for predicting stochastic parameters is minimal.
AB - Heterogeneous materials exhibit considerable spatial variations in properties, impacting structural performance and local stress and strain fields. Recent research has focused on considering material behaviour uncertainties and quantifying the impact of uncertainties on the structural response, requiring the definition of random fields for describing the material variability. In this paper, a stochastic modeling methodology for additively manufactured structures is implemented (forward model). The stochastic parameters are determined from experimental Digital Image Correlation (DIC) images (inverse problem) using a Convolutional Neural Network (CNN), and the CNN is trained using the forward model. Validation of the CNN estimates using previously unseen data shows adequate performance of the network, and consistent predictions are found when estimating the stochastic parameters from experimental results. The proposed methodology allows examination of the stochastic response and uncertainty quantification of additively manufactured structures, while requiring only minor experimental efforts to fully define the random fields. Once the CNN is trained, computational expense for predicting stochastic parameters is minimal.
UR - http://www.scopus.com/inward/record.url?scp=85097278210&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097278210&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85097278210
T3 - Proceedings of the American Society for Composites - 35th Technical Conference, ASC 2020
SP - 1885
EP - 1899
BT - Proceedings of the American Society for Composites - 35th Technical Conference, ASC 2020
A2 - Pochiraju, Kishore
A2 - Gupta, Nikhil
T2 - 35th Annual American Society for Composites Technical Conference, ASC 2020
Y2 - 14 September 2020 through 17 September 2020
ER -