VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/746
Title: | Numerical investigation of an artifcial neural network based identifcation of nonlinear material parameters | Authors: | Chau Minh Vu | Keywords: | Hyperelastic materials;Micro-mechanical;Linear regression;Artifcial neural network | Issue Date: | 2018 | Publisher: | Vietnamese - German University | Abstract: | The hyperelastic materials are classifed in two catalogues namely phenomenological and micro-mechanical. The former model’s strain-energy function, which has the form of polynomial function, is frequently formulated based on strain invariants. This contribution uses two machine learning (ML) approaches such as linear regression (LR) and Artifcial Neural Network (ANN) in order to identify the materials parameters in the incompressible isotropic elastic strain-energy function. By applying a curve ftting procedure on Treloar’s experimental dataset (Treloar, 1976), the optimal materials parameters and their corresponding relative error can be determined by minimizing the least square error between the predicted curve and experimental data. The resulted materials parameters from both methods are nearly the same and ft well with the experimental data. Generalized Rivlin Model (Rivlin and Saunders, 1951) shows the ability to well capture the large strain of Treloar’s rubber-like materials data, and multiple sets of optimal parameters occurred during the ftting process. The relative errors computed using ML methods are better than that of literature around 66,667% of test cases. For this small dataset, LR shows its advantage of over ANN in terms of computational resource. |
URI(1): | http://epub.vgu.edu.vn/handle/dlibvgu/746 |
Appears in Collections: | Computational Engineering (CompEng) |
Files in This Item:
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
Numerical investigation of an artificial neural network based identification of nonlinear material parameters.pdf | 3.2 MB | Adobe PDF |
Page view(s)
65
checked on Apr 26, 2024
Download(s)
13
checked on Apr 26, 2024
Google ScholarTM
Check
Items are protected by © Copyright of Vietnamese - German University Library