Machine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matter
A modular pipeline for improving the constitutive modelling of composite materials is proposed.The method is leveraged here for the development of subject-specific spatially-varying brain white matter mechanical properties. For this application, white matter microstructural information is extracted...
| Main Authors: | , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Springer Nature
2021
|
| _version_ | 1826267271363821568 |
|---|---|
| author | Field, D Ammouche, Y Pena, J-M Jerusalem, A |
| author_facet | Field, D Ammouche, Y Pena, J-M Jerusalem, A |
| author_sort | Field, D |
| collection | OXFORD |
| description | A modular pipeline for improving the constitutive modelling of composite materials is proposed.The method
is leveraged here for the development of subject-specific spatially-varying brain white matter mechanical
properties. For this application, white matter microstructural information is extracted from diffusion magnetic resonance imaging (dMRI) scans, and used to generate hundreds of representative volume elements
(RVEs) with randomly distributed fibre properties. By automatically running finite element analyses on
these RVEs, stress-strain curves corresponding to multiple RVE-specific loading cases are produced. A mesoscopic constitutive model homogenising the RVEs’ behaviour is then calibrated for each RVE, producing a
library of calibrated parameters against each set of RVE microstructural characteristics. Finally, a machine
learning layer is implemented to predict the constitutive model parameters directly from any new microstructure. The results show that the methodology can predict calibrated mesoscopic material properties with high
accuracy. More generally, the overall framework allows for the efficient simulation of the spatially-varying mechanical behaviour of composite materials when experimentally measured location-specific fibre geometrical
characteristics are provided. |
| first_indexed | 2024-03-06T20:51:38Z |
| format | Journal article |
| id | oxford-uuid:37c6f445-37a4-4c3f-8757-a550d73c3c2a |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T20:51:38Z |
| publishDate | 2021 |
| publisher | Springer Nature |
| record_format | dspace |
| spelling | oxford-uuid:37c6f445-37a4-4c3f-8757-a550d73c3c2a2022-03-26T13:46:04ZMachine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matterJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:37c6f445-37a4-4c3f-8757-a550d73c3c2aEnglishSymplectic ElementsSpringer Nature2021Field, DAmmouche, YPena, J-MJerusalem, AA modular pipeline for improving the constitutive modelling of composite materials is proposed.The method is leveraged here for the development of subject-specific spatially-varying brain white matter mechanical properties. For this application, white matter microstructural information is extracted from diffusion magnetic resonance imaging (dMRI) scans, and used to generate hundreds of representative volume elements (RVEs) with randomly distributed fibre properties. By automatically running finite element analyses on these RVEs, stress-strain curves corresponding to multiple RVE-specific loading cases are produced. A mesoscopic constitutive model homogenising the RVEs’ behaviour is then calibrated for each RVE, producing a library of calibrated parameters against each set of RVE microstructural characteristics. Finally, a machine learning layer is implemented to predict the constitutive model parameters directly from any new microstructure. The results show that the methodology can predict calibrated mesoscopic material properties with high accuracy. More generally, the overall framework allows for the efficient simulation of the spatially-varying mechanical behaviour of composite materials when experimentally measured location-specific fibre geometrical characteristics are provided. |
| spellingShingle | Field, D Ammouche, Y Pena, J-M Jerusalem, A Machine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matter |
| title | Machine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matter |
| title_full | Machine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matter |
| title_fullStr | Machine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matter |
| title_full_unstemmed | Machine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matter |
| title_short | Machine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matter |
| title_sort | machine learning based multiscale calibration of mesoscopic constitutive models for composite materials application to brain white matter |
| work_keys_str_mv | AT fieldd machinelearningbasedmultiscalecalibrationofmesoscopicconstitutivemodelsforcompositematerialsapplicationtobrainwhitematter AT ammouchey machinelearningbasedmultiscalecalibrationofmesoscopicconstitutivemodelsforcompositematerialsapplicationtobrainwhitematter AT penajm machinelearningbasedmultiscalecalibrationofmesoscopicconstitutivemodelsforcompositematerialsapplicationtobrainwhitematter AT jerusalema machinelearningbasedmultiscalecalibrationofmesoscopicconstitutivemodelsforcompositematerialsapplicationtobrainwhitematter |