Reprint

Recent Advances and Applications of Machine Learning in Metal Forming Processes

Edited by
November 2022
210 pages
  • ISBN978-3-0365-5771-7 (Hardback)
  • ISBN978-3-0365-5772-4 (PDF)

This book is a reprint of the Special Issue Recent Advances and Applications of Machine Learning in Metal Forming Processes that was published in

Chemistry & Materials Science
Engineering
Summary

Machine learning (ML) technologies are emerging in Mechanical Engineering, driven by the increasing availability of datasets, coupled with the exponential growth in computer performance. In fact, there has been a growing interest in evaluating the capabilities of ML algorithms to approach topics related to metal forming processes, such as:

Classification, detection and prediction of forming defects;

Material parameters identification;

Material modelling;

Process classification and selection;

Process design and optimization.

The purpose of this Special Issue is to disseminate state-of-the-art ML applications in metal forming processes, covering 10 papers about the abovementioned and related topics.

Format
  • Hardback
License
© 2022 by the authors; CC BY-NC-ND license
Keywords
sheet metal forming; uncertainty analysis; metamodeling; machine learning; hot rolling strip; edge defects; intelligent recognition; convolutional neural networks; sheet metal forming; deep-drawing; kriging metamodeling; multi-objective optimization; FE (Finite Element) AutoForm robust analysis; defect prediction; mechanical properties prediction; high-dimensional data; feature selection; maximum information coefficient; complex network clustering; ring rolling; process energy estimation; metal forming; thermo-mechanical FEM analysis; machine learning; artificial neural network; aluminum alloy; artificial neural network; mechanical property; UTS; machine learning; topological optimization; metal forming; artificial neural networks (ANN); machine learning (ML); press-brake bending; air-bending; three-point bending test; sheet metal forming; sheet metal; buckling instability; oil canning; artificial intelligence; convolution neural network; hot rolled strip steel; defect classification; generative adversarial network; attention mechanism; deep learning; mechanical constitutive model; machine learning; artificial neural network; finite element analysis; plasticity; parameter identification; full-field measurements; n/a