A convolutional neural network based crystal plasticity finite element framework to predict localised deformation in metals

Ibragimova, Olga; Brahme, Abhijit; Muhammad, Waqas; Connolly, Daniel S.; Lévesque, Julie; Inal, Kaan

doi:10.1016/j.ijplas.2022.103374

Cited by 47 publications

(7 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Acar [ 451 ] proposed a novel ML-based computational framework to predict CP parameters and revealed the relations of these parameters with the texture of Ti alloy, as depicted in Figure 36 . Ibragimova et al [ 452 ] proposed a novel approach to predict the localized deformation in sheet metals by coupling convolutional neural network (CNN) and CPFEM, as depicted in Figure 37 , to predict localized deformation in metals.…”

Section: Evaluation and Modelling Of Forming Limitmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Characterization and Modelling Approaches for Sheet Metal Forming of Lightweight Metallic Materials

Hou

Myung

Park³

et al. 2023

Materials

View full text Add to dashboard Cite

Lightweight sheet metals are attractive for aerospace and automotive applications due to their exceptional properties, such as low density and high strength. Sheet metal forming (SMF) is a key technology to manufacturing lightweight thin-walled complex-shaped components. With the development of SMF, numerical simulation and theoretical modelling are promoted to enhance the performance of new SMF technologies. Thus, it is extraordinarily valuable to present a comprehensive review of historical development in SMF followed by state-of-the-art advanced characterization and modelling approaches for lightweight metallic materials. First, the importance of lightweight materials and their relationship with SMF followed by the historical development of SMF are reviewed. Then, the progress of advanced finite element technologies for simulating metal forming with lightweight alloys is covered. The constitutive modelling of lightweight alloys with an explanation of state-of-the-art advanced characterization to identify the constitutive parameters are presented. Then, the formability of sheet metals with major influencing factors, the techniques for measuring surface strains in SMF and the experimental and modelling approaches for determining the formability limits are clarified. Finally, the review is concluded by affording discussion of the present and future trends which may be used in SMF for lightweight metallic materials.

show abstract

Section: Evaluation and Modelling Of Forming Limitmentioning

confidence: 99%

“… A schematic description of the novel framework proposed by Ibragimova et al [ 452 ] to predict the FLDs of AZ31 and ZE10 Mg sheets. Reprinted from Ref.…”

Section: Figurementioning

confidence: 99%

A Review of Characterization and Modelling Approaches for Sheet Metal Forming of Lightweight Metallic Materials

Hou

Myung

Park³

et al. 2023

Materials

View full text Add to dashboard Cite

show abstract

“…Unlike the phenomenological constitutive theory and multiscale modelling, data-driven models do not require parameter calibration and phenomenological assumptions, neither do they request unaffordable computational resources to infer stress responses from strain paths. Although it is not new to apply neural networks to model the stress-strain relations of concrete and sands (Ellis et al, 1995;Ghaboussi et al, 1991;Ghaboussi and Sidarta, 1998), the revolutionary development of deep learning over recent years re-inspires extensive explorations in data-driven constitutive models (Guan et al, 2023;Ibragimova et al, 2022;Ibragimova et al, 2021;Jordan et al, 2020;Tancogne-Dejean et al, 2021). For example, and developed reinforcement learning and game theory-based deep learning models for the constitutive modelling of granular materials.…”

Section: Introductionmentioning

confidence: 99%

Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling

Guan

Feng

et al. 2023

International Journal of Plasticity

View full text Add to dashboard Cite

“…Thus choosing the appropriate neural network is vital for solving the problem accurately and efficiently. For example, CNN was used to predict- full-field stress and strain evolution of polycrystals for various microstructures and localized deformation was successfully captured [39]. To consider interplay between grains, energy functions based on graph convolution neural networks (GCNNs) for anisotropic hyperelastic materials was also developed [40].…”

Section: Introductionmentioning

confidence: 99%

A data-driven yield criterion for porous ductile single crystals containing spherical voids via physics-informed neural networks

Wu,

Fu,

Sui

et al. 2023

Proc. R. Soc. A.

View full text Add to dashboard Cite

Yield criteria for porous material have been widely used to model the decrease of yield strength caused by porosity during ductile failure which deserves long-term efforts in modelling to remedy the current drawbacks. To improve their accuracy, a method of building yield criteria for porous single crystals based on physics-informed neural networks (PINNs) has been developed, and the newly well-trained yield functions are capable of predicting the yield stress of porous single crystals with different porosity, stress states and crystal orientations. The reliability of the yield functions is guaranteed by the precise datasets generated by the crystal plasticity finite-element method. In particular, through embedding the associated flow rule into the training process, the PINN-based yield function not only achieves higher accuracy in comparison with the analytical methods (e.g. variational nonlinear homogenization or limit analysis) but also avoids the improper appearance of grooves that happens in feed-forward neural networks. The proposed framework enjoys an excellent portability as the yield functions can be rebuilt in the similar non-trivial procedure when new influencing factors must be introduced, which makes us believe in its potential to be extended.

show abstract

A convolutional neural network based crystal plasticity finite element framework to predict localised deformation in metals

Cited by 47 publications

References 73 publications

A Review of Characterization and Modelling Approaches for Sheet Metal Forming of Lightweight Metallic Materials

A Review of Characterization and Modelling Approaches for Sheet Metal Forming of Lightweight Metallic Materials

Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling

A data-driven yield criterion for porous ductile single crystals containing spherical voids via physics-informed neural networks

Contact Info

Product

Resources

About