paper-with-me

홈 › Papers

Fully data-driven inverse hyperelasticity with hyper-network neural ODE fields

2025-06-09 · Vahidullah Taç, Amirhossein Amiri-Hezaveh, Manuel K. Rausch, Grace N. Bechtel, Francisco Sahli Costabal, Adrian Buganza Tepole

We propose a new framework for identifying mechanical properties of heterogeneous materials without a closed-form constitutive equation. Given a full-field measurement of the displacement field, for instance as obtained from digital image correlation (DIC), a continuous approximation of the strain field is obtained by training a neural network that incorporates Fourier features to effectively capture sharp gradients in the data. A physics-based data-driven method built upon ordinary neural differential equations (NODEs) is employed to discover constitutive equations. The NODE framework can represent arbitrary materials while satisfying constraints in the theory of constitutive equations by default. To account for heterogeneity, a hyper-network is defined, where the input is the material coordinate system, and the output is the NODE-based constitutive equation. The parameters of the hyper-network are optimized by minimizing a multi-objective loss function that includes penalty terms for violations of the strong form of the equilibrium equations of elasticity and the associated Neumann boundary conditions. We showcase the framework with several numerical examples, including heterogeneity arising from variations in material parameters, spatial transitions from isotropy to anisotropy, material identification in the presence of noise, and, ultimately, application to experimental data. As the numerical results suggest, the proposed approach is robust and general in identifying the mechanical properties of heterogeneous materials with very few assumptions, making it a suitable alternative to classical inverse methods.

📄 PDF Abstract BibTeX arXiv:2506.08146

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

NODE Neural Oblivious Decision Ensembles (NODE) is a tabular data architecture that consists of differentiable oblivious decision trees (ODT) that are trained end-to-end by…

Similar Papers 제목 키워드 기반

Differentiable Neural-Integrated Meshfree Method for Forward and Inverse Modeling of Finite Strain Hyperelasticity

2024-07-15 · Honghui Du, Binyao Guo, Qizhi He

The present study aims to extend the novel physics-informed machine learning approach, specifically the neural-integrated meshfree (NIM) method, to model finite-strain problems characterized by nonlinear elasticity and l…

GPUPhysics-informed machine learningUnity

Generative Hyperelasticity with Physics-Informed Probabilistic Diffusion Fields

2023-09-11 · Vahidullah Tac, Manuel K Rausch, Ilias Bilionis, Francisco Sahli Costabal 외

Many natural materials exhibit highly complex, nonlinear, anisotropic, and heterogeneous mechanical properties. Recently, it has been demonstrated that data-driven strain energy functions possess the flexibility to captu…

Numerical analysis of the strain distribution in skin domes formed upon the application of hypobaric pressure

2020-10-26 · Daniel Sebastia-Saez, Faiza Benaouda, Charlie Lim, Guoping Lian 외

Suction cups are widely used in applications such as in measurement of mechanical properties of skin in vivo, in drug delivery devices or in acupuncture treatment. Understanding the mechanical response of skin under hypo…

Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks

2024-06-16 · Yizheng Wang, Jia Sun, Jinshuai Bai, Cosmin Anitescu 외

AI for partial differential equations (PDEs) has garnered significant attention, particularly with the emergence of Physics-informed neural networks (PINNs). The recent advent of Kolmogorov-Arnold Network (KAN) indicates…

FormKolmogorov-Arnold Networks

NN-EUCLID: deep-learning hyperelasticity without stress data

2022-05-04 · Prakash Thakolkaran, Akshay Joshi, Yiwen Zheng, Moritz Flaschel 외

We propose a new approach for unsupervised learning of hyperelastic constitutive laws with physics-consistent deep neural networks. In contrast to supervised learning, which assumes the availability of stress-strain pair…

Deep Learning