Automated discovery of interpretable hyperelastic material models for human brain tissue with EUCLID
Source abstract
Abstract
We propose an automated computational algorithm for simultaneous model selection and parameter identification for the hyperelastic mechanical characterization of biological tissue and validate it on experimental data stemming from human brain tissue specimens. Following the motive of the recently proposed computational framework EUCLID (Efficient Unsupervised Constitutive Law Identitication and Discovery) and in contrast to conventional parameter calibration methods, we construct an extensive set of candidate hyperelastic models, i.e., a model library including popular models known from the literature, and develop a computational strategy for automatically selecting a model from the library that conforms to the available experimental data while being represented as an interpretable symbolic mathematical expression. This computational strategy comprises sparse regression, i.e., a regression problem that is regularized by a sparsity promoting penalty term that filters out irrelevant models from the model library, and a clustering method for grouping together highly correlated and thus redundant features in the model library. The model selection procedure is driven by data stemming from mechanical tests under different deformation modes, i.e., uniaxial compression/tension and simple torsion. The data is acquired through conventional mechanical tests that deliver labelled one-dimensional data pairs, and thus the method can be interpreted as a supervised counterpart to the originally proposed EUCLID that is informed by full-field displacement data and global reaction forces. The proposed method is verified on synthetical data with artificial noise. In addition, we present for the first time an experimental investigation of the EUCLID framework by validating the proposed method on experimental data acquired through mechanical tests of human brain specimens, proving that the method is capable of discovering hyperelastic models that exhibit both high fitting accuracy to the data as well as concise and thus interpretable mathematical representations.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Elasticity and Material Modeling · Orthopaedic implants and arthroplasty · Cardiac Valve Diseases and Treatments
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (50)
Show source-provided references
1. Automatic generation of interpretable hyperelastic material models by symbolic regression
2. A mechanics-informed artificial neural network approach in data-driven constitutive modeling
3. As’ad · 2022
4. Development of interpretable, data-driven plasticity models with symbolic regression10.1016/j.compstruc.2021.106557 ↗
5. Constitutive models of rubber elasticity: A review10.5254/1.3547602 ↗
6. Discovering governing equations from data by sparse identification of nonlinear dynamical systems10.1073/pnas.1517384113 ↗
7. Fifty shades of brain: A review on the mechanical testing and modeling of brain tissue10.1007/s11831-019-09352-w ↗
8. Mechanical characterization of human brain tissue10.1016/j.actbio.2016.10.036 ↗
9. Polyconvex neural networks for hyperelastic constitutive models: A rectification approach10.1016/j.mechrescom.2022.103993 ↗
10. On the performance of isotropic hyperelastic constitutive models for rubber-like materials: A state of the art review10.1115/1.4050978 ↗
11. Least angle regression10.1214/009053604000000067 ↗
12. Ester, M., Kriegel, H.-P., Xu, X., 1996. A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. In: Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining, Portland. pp. 226–231.
13. Tissue-scale biomechanical testing of brain tissue for the calibration of nonlinear material models
14. Flaschel · 2023
15. Unsupervised discovery of interpretable hyperelastic constitutive laws10.1016/j.cma.2021.113852 ↗
16. Discovering plasticity models without stress data10.1038/s41524-022-00752-4 ↗
17. Automated discovery of generalized standard material models with EUCLID10.1016/j.cma.2022.115867 ↗
18. A statistical view of some chemometrics regression tools10.1080/00401706.1993.10485033 ↗
19. Tensor basis gaussian process models of hyperelastic materials10.1615/JMachLearnModelComput.2020033325 ↗
20. Regularization paths for generalized linear models via coordinate descent10.18637/jss.v033.i01 ↗
21. Forms for the stored (strain) energy function for vulcanized rubber10.1002/pol.1958.1202811814 ↗
22. Knowledge-based modeling of material behavior with neural networks
23. Parameter estimation of hyperelasticity relations of generalized polynomial-type with constraint conditions10.1016/S0020-7683(01)00018-X ↗
24. A comparative study of 85 hyperelastic constitutive models for both unfilled rubber and highly filled rubber nanocomposite material
25. Hinrichsen · 2022
26. Holzapfel · 2000
27. A manifold learning approach to data-driven computational elasticity and inelasticity10.1007/s11831-016-9197-9 ↗
28. Bayesian-EUCLID: Discovering hyperelastic material laws with uncertainties10.1016/j.cma.2022.115225 ↗
29. Application of symbolic regression for constitutive modeling of plastic deformation
30. Automated constitutive modeling of isotropic hyperelasticity based on artificial neural networks10.1007/s00466-021-02090-6 ↗
31. Data-driven computational mechanics10.1016/j.cma.2016.02.001 ↗
32. Polyconvex anisotropic hyperelasticity with neural networks10.1016/j.jmps.2021.104703 ↗
33. Finite electro-elasticity with physics-augmented neural networks10.1016/j.cma.2022.115501 ↗
34. Linka · 2022
35. Unraveling the local relation between tissue composition and human brain mechanics through machine learning10.3389/fbioe.2021.704738 ↗
36. Automated model discovery for human brain using constitutive artificial neural networks10.1016/j.actbio.2023.01.055 ↗
37. Comparison of hyperelastic models for rubber-like materials10.5254/1.3547969 ↗
38. Automated identification of linear viscoelastic constitutive laws with EUCLID10.1016/j.mechmat.2023.104643 ↗
39. Meyer · 2023
40. Large deformation isotropic elasticity – on the correlation of theory and experiment for incompressible rubberlike solids
41. Multiscale constitutive model using data–driven yield function10.1016/j.compositesb.2021.108831 ↗
42. Torsion of a rubber cylinder
43. Principal-stretch-based constitutive neural networks autonomously discover a subclass of ogden models for human brain tissue10.1016/j.brain.2023.100066 ↗
44. Hyperelastic models for rubber-like materials: consistent tangent operators and suitability for Treloar’s data10.1007/s00419-012-0610-z ↗
45. A model of incompressible isotropic hyperelastic material behavior using spline interpolations of tension-compression test data10.1002/cnm.1105 ↗
46. Data-driven tissue mechanics with polyconvex neural ordinary differential equations10.1016/j.cma.2022.115248 ↗
47. NN-EUCLID: Deep-learning hyperelasticity without stress data10.1016/j.jmps.2022.105076 ↗
48. Regression shrinkage and selection via the lasso10.1111/j.2517-6161.1996.tb02080.x ↗
49. Inference of deformation mechanisms and constitutive response of soft material surrogates of biological tissue by full-field characterization and data-driven variational system identification10.1016/j.jmps.2021.104474 ↗
50. Supplementary software for “automated discovery of interpretable hyperelastic material models for human brain tissue with EUCLID”