Learning data-driven reduced elastic and inelastic models of spot-welded patches

Reille, Agathe; Champaney, Victor; Daim, Fatima; Tourbier, Yves; Hascoët, Nicolas; González, David; Duval, Jean‐Louis; Chinesta, Francisco

doi:10.1051/meca/2021031

Cited by 10 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Actions applying in the hidden region are accessible from their effects on the observed region. The transient case is a bit more technical, but under certain conditions such a condensed model continues to exist [106], and in the most general case a series of internal variables can be defined and learned. The use of the so-called recurrent-NN [55] generalizes the just referred rationale and even extend them to nonlinear settings.…”

Section: Miscellaneousmentioning

confidence: 99%

Empowering engineering with data, machine learning and artificial intelligence: a short introductive review

Chinesta

2022

Adv. Model. and Simul. in Eng. Sci.

Self Cite

View full text Add to dashboard Cite

Simulation-based engineering has been a major protagonist of the technology of the last century. However, models based on well established physics fail sometimes to describe the observed reality. They often exhibit noticeable differences between physics-based model predictions and measurements. This difference is due to several reasons: practical (uncertainty and variability of the parameters involved in the models) and epistemic (the models themselves are in many cases a crude approximation of a rich reality). On the other side, approaching the reality from experimental data represents a valuable approach because of its generality. However, this approach embraces many difficulties: model and experimental variability; the need of a large number of measurements to accurately represent rich solutions (extremely nonlinear or fluctuating), the associate cost and technical difficulties to perform them; and finally, the difficulty to explain and certify, both constituting key aspects in most engineering applications. This work overviews some of the most remarkable progress in the field in recent years.

show abstract

Section: Miscellaneousmentioning

confidence: 99%

Empowering engineering with data, machine learning and artificial intelligence: a short introductive review

Chinesta

2022

Adv. Model. and Simul. in Eng. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…-In some cases, when the model captures most of the solution complexity, the correction must describe a discrepancy that could exhibits much smaller nonlinearities, as was the case treated in [40,41], where the same amount of data performed better within the hybrid than within the fully data-driven framework. -Sometimes the physics-based model operates very accurately in a part of the domain, whereas the nonlinear behavior localizes in a very small region that can, in that case, be captured by a data-driven learned model, as considered in [39] for addressing the inelastic behavior of spot-welds. -When considering constitutive modeling of materials, different frameworks exist:…”

Section: (Right)mentioning

confidence: 99%

Engineering empowered by physics-based and data-driven hybrid models: A methodological overview

Champaney

Chinesta

2022

Int J Mater Form

Self Cite

View full text Add to dashboard Cite

Smart manufacturing implies creating virtual replicas of the processing operations, taking into account the material dimension and its multi-physics transformation when forming processes operate. Performing efficient, that is, online accurate predictions of the induced properties (including potential defects) of the formed part (to optimally control the process parameters) needs moving beyond usual offline simulation based on nominal models, and proceeds by assimilating data. This will serve, from one side, to keep the model calibrated, and from the other, to enrich the model and its associated predictions, to avoid bias, to improve accuracy or for performing online diagnosis, by advertising on preventive maintenance. For all these purposes, a new alliance between physics-based and data-driven modelling approaches seems a very valuable route for empowering engineering in general, and smart manufacturing in particular. The present paper revisits the main methodologies involved in the construction of the component or system Hybrid Twins.

show abstract

“…High-fidelity simulations of large structures containing many localized features such as spotwelds [1] or bolted joints are still a major scientific and industrial challenge. The mechanical behavior of these localized features has traditionally been addressed using simplified models to circumvent the complexities associated with numerical analysis procedures.…”

Section: Introductionmentioning

confidence: 99%

A neural network-based data-driven local modeling of spotwelded plates under impact

Pulikkathodi,

Lacazedieu,

Chamoin

et al. 2023

Mechanics & Industry

View full text Add to dashboard Cite

Solving large structural problems with multiple complex localized behaviors is extremely challenging. To address this difficulty, both intrusive and non-intrusive Domain Decomposition Methods (DDM) have been developed in the past, where the refined model (local) is solved separately in its own space and time scales. In this work, the Finite Element Method (FEM) at the local scale is replaced with a data-driven Reduced Order Model (ROM) to further decrease computational time. The reduced model aims to create a low-cost, accurate and efficient mapping from interface velocities to interface forces and enable the prediction of their time evolution. The present work proposes a modeling technique based on the Physics-Guided Architecture of Neural Networks (PGANNs), which incorporates physical variables other than input/output variables into the neural network architecture. We develop this approach on a 2D plate with a hole as well as a 3D case with spot-welded plates undergoing fast deformation, representing nonlinear elastoplasticity problems. Neural networks are trained using simulation data generated by explicit dynamic FEM solvers. The PGANN results are in good agreement with the FEM solutions for both test cases, including those in the training dataset as well as the unseen dataset, given the loading type is present in the training set.

show abstract

Learning data-driven reduced elastic and inelastic models of spot-welded patches

Cited by 10 publications

References 19 publications

Empowering engineering with data, machine learning and artificial intelligence: a short introductive review

Empowering engineering with data, machine learning and artificial intelligence: a short introductive review

Engineering empowered by physics-based and data-driven hybrid models: A methodological overview

A neural network-based data-driven local modeling of spotwelded plates under impact

Contact Info

Product

Resources

About