HAL-MINES ParisTech
Not a member yet
27348 research outputs found
Sort by
Influence of cobalt content on the grain growth and recrystallization kinetics of alloy VDM780
No full textInternational audienc
A Thermodynamics-Constrained Neural Network with Mechanical Encoding for Nonlinear Viscoelastic Modelling from Sparse Data
No full textInternational audienceAccurately predicting the nonlinear viscoelastic behaviour of materials such as polymers remains a key challenge, particularly when only limited experimental data are available. While recurrent neural networks (RNNs) are often used to capture path-dependent material responses, they suffer from training instabilities and poor extrapolation capabilities. This study addresses this gap by developing an alternative approach with a hybrid, thermodynamically-based framework that combines a linear Generalised Maxwell model with a multilayer perceptron (MLP). The Maxwell model acts as a ``physics-based'' encoding layer, providing interpretable internal variables that represent the material's deformation history. Unlike RNNs, MLPs are better suited for capturing complex nonlinear relationships without relying on memory cells, thereby improving generalisation beyond the training domain. The parameters of the mechanical model and the neural network are jointly optimised. A residual connection allows the network to correct the Maxwell model’s output. The proposed model, referred to as Mech-TANN, accurately reproduces nonlinear viscoelastic behaviour using only forty noisy data points from synthetic shear tests. It achieves less than 7% prediction error on test data with a noise level of 2 % of the maximum signal amplitude. With four times the data, the precision improves tenfold. It demonstrates excellent extrapolation to larger strain amplitudes and unseen loading types, including relaxation tests. The combination of mechanical encoding and thermodynamic constraints yields a data-efficient and generalisable modelling framework that benefits from physically motivated inductive bias for complex time-dependent materials
Crystal Plasticity Thermo-Mechanical Simulation in Additive Manufacturing at Part-Scale using Texture Component Approach
No full textInternational audienceA thermo-mechanical framework based on a texture component crystal plasticity method is investigated to identify microstructural effects on parts produced by additive manufacturing (AM). In this approach, a coarse mesh is adopted for the crystal plasticity-based mechanical simulation, with each finite element comprising multiple grains. The texture component method accounts for the multi-grain distribution within each element. The crystal plasticity multi-grain method is first applied to representative volume elements (RVEs) and compared to a simple reduced grain approach [1] to identify the anisotropic mechanical behavior of grain structures with marked textures. Subsequently, thermo-mechanical AM process simulations are performed using the proposed multi-grain method, where a layer-by-layer method is implemented to simulate part construction and multi-grain activation [2]. The stress and distortion predictions from the texture component-based crystal plasticity model are compared with results from the isotropic and reduced grain methods to assess the efficiency of the numerical approaches
Simulation multiphysique du procédé WLAM - Évolutions thermo-hydrauliques du bain et formation des microstructures
No full textInternational audienc
Macro-scale thermal modeling for optimization of preheating strategies during laser powder bed fusion of Inconel 738 parts
No full textInternational audienc
Cost-benefit analysis of technologies and measures for summer comfort – A case study of residential districts in the Paris region
No full textInternational audienc
