Can machine learning accelerate soft material parameter identification from complex mechanical test data?

Kakaletsis, Sotirios; Lejeune, Emma; Rausch, Manuel K.

doi:10.1007/s10237-022-01631-z

Cited by 16 publications

(11 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Constitutive Artificial Neural Networks, with strain invariants as input and free energy functions as output, were first proposed for rubber-like materials almost two decades ago [56], and have recently regained attention in the constitutive modeling community [3, 24, 34, 63]. They are now also increasingly recognized in the soft tissue biomechanics community with applications to skin [57], blood clots [32], arteries [29, 38], and myocardial tissue [32]. A common feature of all these neural networks is to use multiple hidden layers, generic activation functions, and several hundreds, if not thousands of unknowns.…”

Section: Motivationmentioning

confidence: 99%

Automated model discovery for human brain using Constitutive Artificial Neural Networks

Linka

Pierre

Kuhl

2022

Preprint

View full text Add to dashboard Cite

The brain is our softest and most vulnerable organ, and understanding its physics is a challenging but significant task. Massive efforts have been dedicated at testing the human brain, and various competing models have emerged to characterize its response to mechanical loading. However, selecting the best constitutive model remains a heuristic process that strongly depends on user experience and personal preference. Here we challenge the conventional wisdom to first select a constitutive model and then fit its parameters to experimental data. Instead, we propose a new strategy that simultaneously discovers both model and parameters that best describe the data. Towards this goal, we integrate more than a century of knowledge in thermodynamics and state-of-the-art machine learning to build a family of Constitutive Artificial Neural Networks that enable automated model discovery for human brain tissue. Our overall design paradigm is to reverse engineer a Constitutive Artificial Neural Network from a set of functional building blocks that are, by design, a generalization of widely used and commonly accepted constitutive models, including the neo Hooke, Blatz Ko, Mooney Rivlin, Demiray, Gent, and Holzapfel models. By constraining the input, output, activation functions, and architecture, our network a priori satisfies thermodynamic consistency, material objectivity, material symmetry, physical constrains, and polyconvexity. We demonstrate that our network autonomously discovers both model and parameters that best characterize the behavior of human gray and white matter under tension, compression, and shear. Importantly, our network weights translate naturally into physically meaningful material parameters, e.g., shear moduli of 1.82kPa, 0.88kPa, 0.94kPa, and 0.54kPa for the cortex, basal ganglia, corona radiata, and corpus callosum. Our results suggest that Constitutive Artificial Neural Networks have the potential to induce a paradigm shift in soft tissue modeling, from user-defined model selection to automated model discovery. Our source code, data, and examples are available at https://github.com/LivingMatterLab/CANN.

show abstract

Section: Motivationmentioning

confidence: 99%

Automated model discovery for human brain using Constitutive Artificial Neural Networks

Linka

Pierre

Kuhl

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, inverse finite element approaches can be computationally expensive. 39,40 The objective of our current work is to develop an efficient approach that combines the generality of finite element-based methods with the high computational efficiency of machine learning. Thereby, we will provide an open-source tool that identifies the material parameters of biological soft tissuesand other soft materials -from indentation data at a much lower cost than classic inverse finite element approaches.…”

Section: Introductionmentioning

confidence: 99%

AI-dente: an open machine learning based tool to interpret nano-indentation data of soft tissues and materials

Giolando,

Kakaletsis,

Zhang

et al. 2023

Soft Matter

Self Cite

View full text Add to dashboard Cite

show abstract

“…Xu added the physical laws into the ANN and solved the inverse problems in underground structures [33]. Kakaletsis compared two different ways to use ANN when identifying the soft material properties, i.e., as surrogate model of FEM or directly as the predicter [34]. In these applications, a large amount of labelled training data is needed.…”

Section: Introductionmentioning

confidence: 99%

“…In this context, 'labelled' indicates that each data point includes both an input and its corresponding target output. The training data is either from the expensive experiments [29,34], the time-consuming FEM computing [30,32,33], or the low-fidelity surrogate model [31,34].…”

Section: Introductionmentioning

confidence: 99%

Constructing artificial boundary condition of dispersive wave systems by deep learning neural network

Zheng,

Shao,

Zhang

2023

Phys. Scr.

View full text Add to dashboard Cite

To solve one dimensional dispersive wave systems in an unbounded domain, a uniform way to establish localized artificial boundary conditions is proposed. The idea is replacing the half-infinite interval outside the region of interest with a super element which exhibits the same dynamics response. Instead of designing the detailed mechanical structures of the super element, we directly reconstruct its stiffness, mass, and damping matrices by matching its frequency-domain reaction force with the expected one. An artificial neural network architecture is thus specifically tailored for this purpose. It comprises a deep learning part to predict the response of generalized degrees of freedom under different excitation frequencies, along with a simple linear part for computing the external force vectors. The trainable weight matrices of the linear layers correspond to the stiffness, mass, and damping matrices we need for the artificial boundary condition. The training data consists of input frequencies and the corresponding expected frequency domain external force vectors, which can be readily obtained through theoretical means. In order to achieve a good result, the neural network is initialized based on an optimized spring-damper-mass system. The adaptive moment estimation algorithm is then employed to train the parameters of the network. Different kinds of equations are solved as numerical examples. The results show that deep learning neural networks can find some unexpected optimal stiffness/damper/mass matrices of the super element. By just introducing a few additional degrees of freedom to the original truncated system, the localized artificial boundary condition works surprisingly well.

show abstract

Can machine learning accelerate soft material parameter identification from complex mechanical test data?

Cited by 16 publications

References 39 publications

Automated model discovery for human brain using Constitutive Artificial Neural Networks

Automated model discovery for human brain using Constitutive Artificial Neural Networks

AI-dente: an open machine learning based tool to interpret nano-indentation data of soft tissues and materials

Constructing artificial boundary condition of dispersive wave systems by deep learning neural network

Contact Info

Product

Resources

About