TU Darmstadt / ULB / TUprints

A Machine Learning Enabled Image‐data‐driven End‐to‐end Mechanical Field Predictor For Dual‐Phase Steel

Lin, Binbin ; Medghalchi, Setareh ; Korte-Kerzel, Sandra ; Xu, Bai-Xiang (2023)
A Machine Learning Enabled Image‐data‐driven End‐to‐end Mechanical Field Predictor For Dual‐Phase Steel.
In: PAMM - Proceedings in Applied Mathematics & Mechanics, 2023, 22 (1)
doi: 10.26083/tuprints-00023695
Article, Secondary publication, Publisher's Version

[img] Text
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (9MB)
Item Type: Article
Type of entry: Secondary publication
Title: A Machine Learning Enabled Image‐data‐driven End‐to‐end Mechanical Field Predictor For Dual‐Phase Steel
Language: English
Date: 27 November 2023
Place of Publication: Darmstadt
Year of primary publication: 2023
Place of primary publication: Weinheim
Publisher: Wiley-VCH
Journal or Publication Title: PAMM - Proceedings in Applied Mathematics & Mechanics
Volume of the journal: 22
Issue Number: 1
Collation: 6 Seiten
DOI: 10.26083/tuprints-00023695
Corresponding Links:
Origin: Secondary publication DeepGreen

This contribution presents convolutional neural nets (CNN) based surrogate models for prediction of von Mises stress and equivalent plastic strain fields of commonly used Dual‐Phase (DP) steels in automotive applications. The models predict field quantities in an end‐to‐end manner, driven by segmented phase images from real experimental scanning electron micrographs as inputs and FEM calculations as outputs. Hereby, we train CNN models with the U‐net neural network structure based on around 900 elastoplastic FEM simulations of various DP steel microstructure samples under tensile test. The trained CNN models are validated and tested on 250 and 50 samples, respectively. Thereby CNN models are employed sequentially for different tasks , from the real micrographs to segmented phase maps, then from segmented phase maps to stress, strain field predictions, in an end‐to‐end manner. The field predictor model results show good agreement with the test data and convincing performance on unseen microstructural dataset. This work demonstrates the large potential of a Machine Learning model to make accumulatively use of the physics‐based simulation data of large number of boundary value problems with varying microstructure. It recaptures not only the physics, implied in each simulation training data obtained from the partial different governing equations of mechanics, but also the overarching correlation between the microstructure and the stress and strain field responses.

Identification Number: e202200110
Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-236954
Additional Information:

Special Issue: 92nd Annual Meeting of the International Association of Applied Mathematics and Mechanics (GAMM)

Classification DDC: 600 Technology, medicine, applied sciences > 620 Engineering and machine engineering
Divisions: 11 Department of Materials and Earth Sciences > Material Science > Mechanics of functional Materials
Date Deposited: 27 Nov 2023 13:48
Last Modified: 05 Jan 2024 08:22
SWORD Depositor: Deep Green
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/23695
PPN: 514469013
Actions (login required)
View Item View Item