Latent-Energy-Based NNs: An interpretable Neural Network architecture for model-order reduction of nonlinear statics in solid mechanics - Archive ouverte HAL
Journal Articles Journal of the Mechanics and Physics of Solids Year : 2024

Latent-Energy-Based NNs: An interpretable Neural Network architecture for model-order reduction of nonlinear statics in solid mechanics

Abstract

Nonlinear mechanical systems can exhibit non-uniqueness of the displacement field in response to a force field, which is related to the non-convexity of strain energy. This work proposes a Neural Network-based surrogate model capable of capturing this phenomenon while introducing an energy in a latent space of small dimension, that preserves the topology of the strain energy; this feature is a novelty with respect to the state of the art. It is exemplified on two mechanical systems of simple geometry, but challenging strong nonlinearities. The proposed architecture offers an additional advantage over existing ones: it can be used to infer both displacements from forces, or forces from displacements, without being trained in both ways.
Fichier principal
Vignette du fichier
hal_LEBNN.pdf (1.26 Mo) Télécharger le fichier
lebnn_code_and_data.zip (5.24 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Origin Files produced by the author(s)

Dates and versions

hal-04737657 , version 1 (16-10-2024)

Identifiers

Cite

Louen Pottier, Anders Thorin, Francisco Chinesta. Latent-Energy-Based NNs: An interpretable Neural Network architecture for model-order reduction of nonlinear statics in solid mechanics. Journal of the Mechanics and Physics of Solids, 2024, pp.105953. ⟨10.1016/j.jmps.2024.105953⟩. ⟨hal-04737657⟩
28 View
0 Download

Altmetric

Share

More