A comparison of two neural network architectures for fast structural response prediction. Issue 1 (14th December 2021)

• Record Type: Journal Article
• Authors: Thaler, Denny; Bamer, Franz; Markert, Bernd
• Editors: Kaliske, M.
• Is Part Of: Proceedings in applied mathematics and mechanics. Volume 21:Issue 1(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-12-14
• Subjects: Applied mathematics -- Periodicals; Engineering mathematics -- Periodicals; Mathematical physics -- Periodicals; 519
• DOI: 10.1002/pamm.202100137
• Languages: English
• ISSNs: 1617-7061

Abstract

Abstract: In this contribution, we compare two different neural network architectures to predict the response statistics of structures. The overall goal is a significant speed‐up of the numerically expensive Monte Carlo simulation. The first approach is based on a convolutional neural network that learns from the whole excitation history, whereas the second approach is based on a feed‐forward network architecture learning from hand‐designed features. Both procedures use supervised learning: The neural networks learn from an initial subset before the prediction of the response statistics of the Monte Carlo simulation is possible.