Prediction of mechanical solutions for a laminated LCEs system fusing an analytical model and neural networks
Source abstract
Abstract
This paper presents a convenient and efficient method to predict the mechanical solutions of a laminated Liquid Crystal Elastomers (LCEs) system subjected to combined thermo-mechanical load, based on a back propagation (BP) neural network which is trained by machine learning from a database established by analytical solutions. Firstly, the general solutions of temperature, displacement, and stress of any single layer in the LCEs system are obtained by solving the two-dimensional (2D) governing equations of both heat conduction and thermoelasticity. Then, the unknown coefficients in above general solutions are determined by a transfer-matrix method based on the continuity condition at the interface of adjacent layers and the combined thermo-mechanical loads condition at the surface of the LCEs system. The formula derivation and calculator program are verified through convergence studies and comparisons with FEM results. Finally, a database with displacements of LCEs system in a temperature field subjected to 561 sets of mechanical loads is established based on the presented analytical model. The BP neural network based on above database is further applied to establish the relationship between deformation and mechanical load to predict the elastic deformation of the LCEs system in a temperature field subjected to a mechanical load. Moreover, the BP network can also inverse the coefficients of mechanical load which induces the specific deformation in a temperature field. The numerical examples show that: (1) The deformation of a laminated LCEs system due to thermal load is limited within the range of human temperature changes from 36 °C to 40 °C. (2) The thickness of the LCE is a sensitive parameter on the deformation at the bottom surface of the system. (3) The accuracy of predicted displacements induced by the thermo-mechanical load and the inversed mechanical load based on deformation of the LCEs system in a temperature field using BP neural network reaches 99.6% and 98.5% respectively.
Source: europepmc · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Composite Structure Analysis and Optimization · Structural Analysis of Composite Materials · Advanced Materials and Mechanics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (35)
Show source-provided references
1. Exact solution for nonlinear thermal stability of hybrid laminated composite Timoshenko beams reinforced with SMA fibers10.1016/j.compstruct.2013.09.010 ↗
2. Application of artificial neural networks for the prediction of roll force and roll torque in hot strip rolling process10.1016/j.apm.2012.09.070 ↗
3. An application of neural networks to the prediction of aerodynamic coefficients of aerofoils and wings10.1016/j.apm.2021.03.019 ↗
4. An efficient and simple refined model for temperature analysis in thin laminated composites10.1016/j.compstruct.2005.07.001 ↗
5. Developments, ideas, and evaluations based upon Reissner's mixed variational theorem in the modelling of multilayered plates and shells10.1115/1.1385512 ↗
6. Refined beam theories based on a unified formulation10.1142/S1758825110000500 ↗
7. Carrera · 2016
8. 3D thermoelastic analysis of rotating disks having arbitrary prole based on A variable kinematic 1D finite element method10.1080/01495739.2016.1207119 ↗
9. Material optimization of tri-directional functionally graded plates by using deep neural network and isogeometric multimesh design approach10.1016/j.apm.2020.06.002 ↗
10. Eslami · 2013
11. Un muscle artificiel semi-rapide
12. Artificial muscles based on nematic gels10.1002/masy.19971130107 ↗
13. A thermo-mechanical analysis of functionally graded beams via hierarchical modelling10.1016/j.compstruct.2012.08.013 ↗
14. Hagan · 2002
15. An efficient higher order zigzag theory for composite and sandwich beams subjected to thermal loading10.1016/j.ijsolstr.2003.08.014 ↗
16. An artificial muscle with lamellar structure based on a nematic triblock copolymer10.1002/adma.200400658 ↗
17. A modified NK algorithm based on BP neural network and DEMATEL for evolution path optimization of urban innovation ecosystem
18. Interpenetrating liquid crystal polyurethane/polyacrylate elastomer with ultrastrong mechanical property10.1021/jacs.9b06757 ↗
19. Mitchell · 2003
20. Material model for composites using neural networks10.2514/3.11810 ↗
21. Qian · 2015 · vol. 6 · 2297
22. Elasticity solution of laminated beams subjected to thermo-loads10.1007/s11771-015-2754-9 ↗
23. Thermo-mechanical modeling and experimental validation for multilayered metallic microstructures10.1007/s00542-020-04988-2 ↗
24. Performance evaluation of artificial neural network approaches in forecasting reservoir inflow10.1016/j.apm.2011.09.048 ↗
25. Flexural response of thermoelastic thin beam resonators due to thermal and mechanical loads10.1016/j.ijmecsci.2015.07.014 ↗
26. Carbon coated liquid crystal elastomer film for artificial muscle applications10.1016/S0924-4247(01)00793-2 ↗
27. Prediction of composite laminate residual strength based on a neural network approach
28. Bending and free vibration of functionally graded beams using various higher-order shear deformation beam theories10.1016/j.ijmecsci.2012.05.014 ↗
29. Liquid crystal elastomers with mechanical properties of a muscle10.1021/ma001639q ↗
30. Analysis of bimetal thermostats10.1364/JOSA.11.000233 ↗
31. Enhanced Reddy's beam theory and thermal stress analysis
32. Elasticity solution of multi-span beams with variable thickness under static loads10.1016/j.apm.2008.10.027 ↗
33. Two-dimensional thermoelastic analysis of beams with variable thickness subjected to thermo-mechanical loads10.1016/j.apm.2012.01.048 ↗
34. Analysis of laminated beams with temperature-dependent material properties subjected to thermal and mechanical loads10.1016/j.compstruct.2019.111304 ↗
35. Ziane · 2015