Integrating experiments, finite element analysis, and interpretable machine learning to evaluate the auxetic response of 3D printed re-entrant metamaterials
Source abstract
Abstract
Metamaterials have received extensive attention in fundamental and applied research over the past two decades due to their unique mechanical behavior. This paper presents an interpretable machine learning (ML) approach for efficient response prediction of three-dimensional (3D)-printed metamaterials. However, developing such an ML-based model requires a large consistent, representative, balanced, and complete dataset. To this extent, an experimentally validated finite element analysis (FEA) approach is implemented to generate 8096 non-self-intersecting re-entrant honeycomb structures by varying the mesoscale geometrical features to obtain the corresponding Poisson's ratios. This dataset is leveraged to develop a feed-forward multilayer perceptron-based predictive model. The developed ML model shows excellent predictive efficacy on the unseen test dataset. Shapely additive explanation (SHAP) is then used for model interpretation. SHAP results show that the slant cell length is the dominant input feature dictating the model output whereas cell angle and vertical cell length show mixed trends signifying that other input features influence their effect on the model output. Moreover, cell thickness does not significantly influence the model output when compared to other input features. Overall, the integrated numerical simulation-experiment-interpretable ML-based predictive approach presented here can be leveraged to design and develop metamaterials for a wide range of engineering applications.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Cellular and Composite Structures · Additive Manufacturing and 3D Printing Technologies · Polymer composites and self-healing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (85)
Show source-provided references
1. 3D printed auxetic mechanical metamaterial with chiral cells and Re-entrant cores10.1038/s41598-018-20795-2 ↗
2. Auxetic metamaterials and structures: a review
3. A novel 3D printable multimaterial auxetic metamaterial with reinforced structure: improved stiffness and retained auxetic behavior10.1080/15376494.2020.1774690 ↗
4. Mechanical behaviour of auxetic cellular structures built from inverted tetrapods at high strain rates10.1016/j.ijimpeng.2018.08.001 ↗
5. Foam structures with a negative Poisson's ratio10.1126/science.235.4792.1038 ↗
6. Elastic properties of an additive manufactured three-dimensional vertex-based hierarchical re-entrant structure10.1016/j.matdes.2022.110527 ↗
7. Elucidating the auxetic behavior of cementitious cellular composites using finite element analysis and interpretable machine learning10.1016/j.matdes.2021.110341 ↗
8. Study on the mechanical properties of CFRP composite auxetic structures consist of corrugated sheets and tubes10.1016/j.compstruct.2022.115655 ↗
9. Designing 2D auxetic structures using multi-objective topology optimization10.1016/j.msea.2020.139914 ↗
10. Fabrication and characterization of nonwoven auxetic polymer stent
11. Poisson's ratio and modern materials10.1038/nmat3134 ↗
12. Negative and positive stiffness in auxetic magneto-mechanical metamaterials10.1098/rspa.2018.0003 ↗
13. Ultralight, ultrastiff mechanical metamaterials10.1126/science.1252291 ↗
14. Namvar · 2022
15. The fracture toughness of composite laminates with a negative Poisson's ratio10.1002/pssb.200982031 ↗
16. Tensile behavior of an auxetic structure: analytical modeling and finite element analysis10.1016/j.ijmecsci.2017.12.029 ↗
17. Low-cycle fatigue life of thin-plate auxetic cellular structures made from aluminium alloy 7075-T65110.1111/ffe.12966 ↗
18. Fabrication of multi-scale and tunable auxetic scaffolds for tissue engineering10.1016/j.matdes.2020.109277 ↗
19. Auxetic fibrous structures and their composites: a review10.1016/j.compstruct.2022.115530 ↗
20. Development and mechanical characterization of weave design based 2D woven auxetic fabrics for protective textiles10.1007/s12221-018-8627-8 ↗
21. Design of small auxetic springs for furniture10.1016/j.matdes.2013.04.075 ↗
22. MXene/polyurethane auxetic composite foam for electromagnetic interference shielding and impact attenuation10.1016/j.compositesa.2021.106430 ↗
23. Design and modeling of a novel three dimensional auxetic reentrant honeycomb structure for energy absorption10.1016/j.compstruct.2021.114882 ↗
24. Shape optimization of bowtie-shaped auxetic structures using beam theory10.1016/j.compstruct.2019.111020 ↗
25. Auxetic mechanical metamaterials10.1039/C6RA27333E ↗
26. On the auxetic properties of generic rotating rigid triangles10.1098/rspa.2011.0273 ↗
27. Failure analysis of auxetic lattice structures under crush load10.1016/j.prostr.2021.12.070 ↗
28. Analysis of additively manufactured (3D printed) dual-material auxetic structures under compression
29. Ballistic impact responses and failure mechanism of composite double-arrow auxetic structure10.1016/j.tws.2022.109087 ↗
30. On the auxetic properties of `Rotating rectangles' with different connectivity10.1143/JPSJ.74.2866 ↗
31. A lightweight rotationally arranged auxetic structure with excellent energy absorption performance10.1016/j.mechmat.2022.104244 ↗
32. A new auxetic structure with significantly reduced stress concentration effects10.1016/j.matdes.2019.107779 ↗
33. Geometric design classification of kirigami-inspired metastructures and metamaterials10.1016/j.istruc.2021.06.072 ↗
34. A twofold-symmetric kirigami pattern and its mobile tessellations10.1016/j.mechmachtheory.2022.104916 ↗
35. AUXHEX – a Kirigami inspired zero Poisson's ratio cellular structure10.1016/j.compstruct.2017.05.050 ↗
36. Thickness effect on mechanical behavior of auxetic sintered metal fiber sheets10.1016/j.matdes.2019.107635 ↗
37. Indentation resistance of brittle auxetic structures: combining discrete representation and continuum model10.1016/j.engfracmech.2021.107824 ↗
38. Deformation behaviour of advanced textile composites with auxetic structure10.1016/j.compstruct.2020.112761 ↗
39. Modeling deformation of auxetic and non-auxetic polymer gels10.1016/j.apm.2019.04.050 ↗
40. A review on additive/subtractive hybrid manufacturing of directed energy deposition (DED) process
41. Smart manufacturing and intelligent manufacturing: a comparative review10.1016/j.eng.2020.07.017 ↗
42. Large deformation and energy absorption of additively manufactured auxetic materials and structures: a review10.1016/j.compositesb.2020.108340 ↗
43. Novel hybrid auxetic structures for improved in- plane mechanical properties via additive manufacturing10.1016/j.mechmat.2021.103890 ↗
44. Strain sensing behavior of FDM 3D printed carbon black filled TPU with periodic configurations and flexible substrates10.1016/j.jmapro.2021.12.020 ↗
45. Melt exit flow modelling and experimental validation for fused filament fabrication: from Newtonian to non-Newtonian effects10.1016/j.jmapro.2022.03.002 ↗
46. Nonparametric Bayesian framework for material and process optimization with nanocomposite fused filament fabrication
47. Polymers for additive manufacturing and 4D-printing: materials, methodologies, and biomedical applications10.1016/j.progpolymsci.2019.03.001 ↗
48. Investigation of influence of printing parameters on the quality of 3D printed composite structures10.1016/j.compstruct.2021.115061 ↗
49. Experimental and numerical analysis of 3D printed polymer tetra-petal auxetic structures under compression10.3390/app112110362 ↗
50. TPU/CNTs flexible strain sensor with auxetic structure via a novel hybrid manufacturing process of fused deposition modeling 3D printing and ultrasonic cavitation-enabled treatment10.1016/j.sna.2022.113526 ↗
51. 4D printed TPU/PLA/CNT wave structural composite with intelligent thermal-induced shape memory effect and synergistically enhanced mechanical properties10.1016/j.compositesa.2022.106946 ↗
52. Influence of 3D-printed TPU properties for the design of elastic products10.3390/polym13152519 ↗
53. Selective laser sintering 3D printing: a way to construct 3D electrically conductive segregated network in polymer matrix10.1002/mame.201700211 ↗
54. Fabrication and characterization of flexible medical-grade TPU filament for fused deposition modeling 3DP technology10.3390/polym10121304 ↗
55. Electro-induced shape memory effect of 4D printed auxetic composite using PLA/TPU/CNT filament embedded synergistically with continuous carbon fiber: a theoretical & experimental analysis10.1016/j.compositesb.2021.108994 ↗
56. Flame retarded Thermoplastic Polyurethane (TPU) for cable jacketing application10.1016/j.polymdegradstab.2012.07.011 ↗
57. Assembled mechanical metamaterials with transformable shape and auxeticity10.1016/j.conbuildmat.2023.131181 ↗
58. Experimental and numerical analysis of a novel assembled auxetic structure with two-stage programmable mechanical properties10.1016/j.tws.2023.110555 ↗
59. In-plane compressive properties of assembled auxetic chiral honeycomb composed of slotted wave plate10.1016/j.matdes.2022.110956 ↗
60. A novel auxetic metamaterial with enhanced mechanical properties and tunable auxeticity10.1016/j.tws.2022.109162 ↗
61. Effective elastic properties of irregular auxetic structures10.1016/j.compstruct.2022.115269 ↗
62. Size effects of elastic properties for auxetic cellular structures: bending energy-based method
63. A review of physics-based machine learning in civil engineering10.1016/j.rineng.2021.100316 ↗
64. Corrosion assessment of some buried metal pipes using neural network algorithm10.5815/ijem.2017.06.03 ↗
65. An interpretable machine learning approach for engineering change management decision support in automotive industry10.1016/j.compind.2022.103633 ↗
66. Machine learning for structural engineering: a state-of-the-art review10.1016/j.istruc.2022.02.003 ↗
67. Hybrid machine-learning and finite-element design for flexible metamaterial wings10.1016/j.matdes.2022.110709 ↗
68. Mechanical performance of bio-inspired hierarchical honeycomb metamaterials
69. Fabrication method and dynamic responses of composite sandwich structure with reentrant honeycomb cores10.1016/j.compstruct.2022.116084 ↗
70. The impact responses and failure mechanism of composite gradient reentrant honeycomb structure10.1016/j.tws.2022.110228 ↗
71. Free vibration behaviours of composite sandwich plates with reentrant honeycomb cores10.1016/j.apm.2022.12.004 ↗
72. A finite strain quadrilateral based on least-squares assumed strains10.1016/j.engstruct.2015.05.035 ↗
73. GitHub: Sample Abaqus files: FEA-based numerical evaluation of auxetic response for re-entrant metamaterials. https://github.com/bolaji1/Sample-Abaqus-files-FEA-based-numerical-evaluation-of-auxetic-response-for-reentrant-metamaterials.
74. Transverse isotropic behavior identification using digital image correlation of a pre-structured material manufactured by 3D printing10.1016/j.prostr.2020.11.112 ↗
75. Multiscale strain field characterization in flexible planar auxetic metamaterials with rotating squares
76. 2009
77. Neural network ensemble-based sensitivity analysis in structural engineering: comparison of selected methods and the influence of statistical correlation10.1016/j.compstruc.2020.106376 ↗
78. ReLU-type Hopfield neural network with analog hardware implementation10.1016/j.chaos.2022.113068 ↗
79. Kingma · 2015
80. Abadi · 2016
81. Machine learning algorithms for breast cancer prediction and diagnosis10.1016/j.procs.2021.07.062 ↗
82. On over-fitting in model selection and subsequent selection bias in performance evaluation
83. Predicting the young's modulus of silicate glasses using high-throughput molecular dynamics simulations and machine learning10.1038/s41598-019-45344-3 ↗
84. Machine-learning interpretability techniques for seismic performance assessment of infrastructure systems10.1016/j.engstruct.2021.112883 ↗
85. Bhattoo · 2021