Special Issues
Table of Content

Computer Aided Simulation in Metallurgy and Material Engineering

Submission Deadline: 31 October 2024 (closed) View: 338 Submit to Special Issue

Guest Editors

Prof. Radim Kocich, VŠB – Technical University of Ostrava, Czech Republic
Assoc. Prof. Lenka Kunčická, VŠB – Technical University of Ostrava, Czech Republic

Summary

Incorporation of computer aided simulations to research and development has introduced indisputable benefits to numerous fields of industry and commerce. Their application in metallurgy and materials engineering has brought numerous advantages and highly effective solutions for sustainable development. Nevertheless, the relevance and accuracy of the acquired predictions are only defined by the robustness and reliability of the input data and defined initial and boundary conditions. The reliability of the used data, and thus of the predicted results, is ensured by conducting properly designed experiments, the results of which are applied to calculate rheology models and define material behaviours during processing. Besides the highly favoured finite element method, suitable to solve numerous tasks, the popularity of neural networks, enabling to generate self-learning algorithms, has recently been on the rise; this trend shifted the possibility of application of computer modelling within the metallurgy and materials engineering research to an entirely new level.  


Keywords

FEM, Rheological law, plastic deformation, metal casting

Published Papers


  • Open Access

    ARTICLE

    Machine Learning Techniques in Predicting Hot Deformation Behavior of Metallic Materials

    Petr Opěla, Josef Walek, Jaromír Kopeček
    CMES-Computer Modeling in Engineering & Sciences, DOI:10.32604/cmes.2024.055219
    (This article belongs to the Special Issue: Computer Aided Simulation in Metallurgy and Material Engineering)
    Abstract In engineering practice, it is often necessary to determine functional relationships between dependent and independent variables. These relationships can be highly nonlinear, and classical regression approaches cannot always provide sufficiently reliable solutions. Nevertheless, Machine Learning (ML) techniques, which offer advanced regression tools to address complicated engineering issues, have been developed and widely explored. This study investigates the selected ML techniques to evaluate their suitability for application in the hot deformation behavior of metallic materials. The ML-based regression methods of Artificial Neural Networks (ANNs), Support Vector Machine (SVM), Decision Tree Regression (DTR), and Gaussian Process Regression More >

Share Link