arrow
Volume 14, Issue 1
Characterising Mechanical Properties of Flowing Microcapsules Using a Deep Convolutional Neural Network

T. Lin, Z. Wang, R. X. Lu, W. Wang & Y. Sui

Adv. Appl. Math. Mech., 14 (2022), pp. 79-100.

Published online: 2021-11

Export citation
  • Abstract

Deformable microcapsules are widely used in industries and also serve as a mechanical model of living biological cells. In this study, we develop a novel method, by integrating a deep convolutional neural network (DCNN) with high-fidelity mechanistic capsule modelling, to identify the membrane constitutive law and estimate associated parameters of a microcapsule from its steady deformed profile in a capillary tube. Compared with conventional inverse methods, the present approach is more accurate and can increase the prediction throughput rate by a few orders of magnitude. It can process capsules with large deformation in inertial flows. Furthermore, the method can predict the capsule membrane shear elasticity, area dilatation modulus and initial inflation from a single steady capsule profile. We explore the mechanism that the DCNN makes decisions by considering its feature maps, and discuss their potential implication on the development of inverse methods. The present method provides a promising tool which may enable high-throughput mechanical characterisation of microcapsules and biological cells in microfluidic flows.

  • AMS Subject Headings

92C10, 76Z99

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{AAMM-14-79, author = {Lin , T.Wang , Z.Lu , R. X.Wang , W. and Sui , Y.}, title = {Characterising Mechanical Properties of Flowing Microcapsules Using a Deep Convolutional Neural Network}, journal = {Advances in Applied Mathematics and Mechanics}, year = {2021}, volume = {14}, number = {1}, pages = {79--100}, abstract = {

Deformable microcapsules are widely used in industries and also serve as a mechanical model of living biological cells. In this study, we develop a novel method, by integrating a deep convolutional neural network (DCNN) with high-fidelity mechanistic capsule modelling, to identify the membrane constitutive law and estimate associated parameters of a microcapsule from its steady deformed profile in a capillary tube. Compared with conventional inverse methods, the present approach is more accurate and can increase the prediction throughput rate by a few orders of magnitude. It can process capsules with large deformation in inertial flows. Furthermore, the method can predict the capsule membrane shear elasticity, area dilatation modulus and initial inflation from a single steady capsule profile. We explore the mechanism that the DCNN makes decisions by considering its feature maps, and discuss their potential implication on the development of inverse methods. The present method provides a promising tool which may enable high-throughput mechanical characterisation of microcapsules and biological cells in microfluidic flows.

}, issn = {2075-1354}, doi = {https://doi.org/10.4208/aamm.OA-2020-0357}, url = {http://global-sci.org/intro/article_detail/aamm/19977.html} }
TY - JOUR T1 - Characterising Mechanical Properties of Flowing Microcapsules Using a Deep Convolutional Neural Network AU - Lin , T. AU - Wang , Z. AU - Lu , R. X. AU - Wang , W. AU - Sui , Y. JO - Advances in Applied Mathematics and Mechanics VL - 1 SP - 79 EP - 100 PY - 2021 DA - 2021/11 SN - 14 DO - http://doi.org/10.4208/aamm.OA-2020-0357 UR - https://global-sci.org/intro/article_detail/aamm/19977.html KW - Microcapsules, flow cytometry, deep convolutional neural network, high throughput, mechanical characterisation. AB -

Deformable microcapsules are widely used in industries and also serve as a mechanical model of living biological cells. In this study, we develop a novel method, by integrating a deep convolutional neural network (DCNN) with high-fidelity mechanistic capsule modelling, to identify the membrane constitutive law and estimate associated parameters of a microcapsule from its steady deformed profile in a capillary tube. Compared with conventional inverse methods, the present approach is more accurate and can increase the prediction throughput rate by a few orders of magnitude. It can process capsules with large deformation in inertial flows. Furthermore, the method can predict the capsule membrane shear elasticity, area dilatation modulus and initial inflation from a single steady capsule profile. We explore the mechanism that the DCNN makes decisions by considering its feature maps, and discuss their potential implication on the development of inverse methods. The present method provides a promising tool which may enable high-throughput mechanical characterisation of microcapsules and biological cells in microfluidic flows.

T. Lin, Z. Wang, R. X. Lu, W. Wang & Y. Sui. (1970). Characterising Mechanical Properties of Flowing Microcapsules Using a Deep Convolutional Neural Network. Advances in Applied Mathematics and Mechanics. 14 (1). 79-100. doi:10.4208/aamm.OA-2020-0357
Copy to clipboard
The citation has been copied to your clipboard