Computer Vision with Error Estimation for Reduced Order Modeling of Macroscopic Mechanical Tests

In this paper, computer vision enables recommending a reduced order model for fast stress prediction according to various possible loading environments. This approach is applied on a macroscopic part by using a digital image of a mechanical test. We propose a hybrid approach that simultaneously expl...

Full description

Saved in:
Bibliographic Details
Published in:Complexity (New York, N.Y.) N.Y.), 2018-01, Vol.2018 (2018), p.1-10
Main Authors: Ryckelynck, David, Muñoz, Daniel Pino, Barhli, Selim M., Nguyen, Franck
Format: Article
Language:English
Subjects:
Archives & records
Artificial neural networks
Cable television broadcasting industry
Classification
Clustering
Composite materials
Computer simulation
Computer vision
Condensed Matter
Decomposition
Defects
Dictionaries
Digital imaging
Engineering
Linear algebra
Machine learning
Machine vision
Materials Science
Materials selection
Mechanical properties
Mechanical tests
Mechanics
Medical imaging
Modelling
Neural networks
Numerical analysis
Physics
Principal components analysis
Reduced order models
Tomography
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, computer vision enables recommending a reduced order model for fast stress prediction according to various possible loading environments. This approach is applied on a macroscopic part by using a digital image of a mechanical test. We propose a hybrid approach that simultaneously exploits a data-driven model and a physics-based model, in mechanics of materials. During a machine learning stage, a classification of possible reduced order models is obtained through a clustering of loading environments by using simulation data. The recognition of the suitable reduced order model is performed via a convolutional neural network (CNN) applied to a digital image of the mechanical test. The CNN recommend a convenient mechanical model available in a dictionary of reduced order models. The output of the convolutional neural network being a model, an error estimator, is proposed to assess the accuracy of this output. This article details simple algorithmic choices that allowed a realistic mechanical modeling via computer vision.
ISSN:1076-2787
1099-0526
DOI:10.1155/2018/3791543