journal article·2020-08

Machine learning predictions on fracture toughness of multiscale bio-nano-composites

Vahid Daghigh, Thomas E Lacy, Hamid Daghigh, Grace Gu, Kourosh T Baghaei, Mark F Horstemeyer, Charles U Pittman

Publisher page

Abstract

Tailorability is an important advantage of composites. Incorporating new bio-reinforcements into composites can contribute to using agricultural wastes and creating tougher and more reliable materials. Nevertheless, the huge number of possible natural material combinations works against finding optimal composite designs. Here, machine learning was employed to effectively predict fracture toughness properties of multiscale bio-nano-composites. Charpy impact tests were conducted on composites with various combinations of two new bio fillers, pistachio shell powders, and fractal date seed particles, as well as nano-clays and short latania fibers, all which reinforce a poly(propylene)/ethylene–propylene–diene-monomer matrix. The measured energy absorptions obtained were used to calculate strain energy release rates as a fracture toughness parameter using linear elastic fracture mechanics and finite element analysis approaches. Despite the limited number of training data obtained from these impact tests and finite element analysis, the machine learning results were accurate for prediction and optimal design. This study applied the decision tree regressor and adaptive boosting regressor machine learning methods in contrast to the K-nearest neighbor regressor machine learning approach used in our previous study for heat deflection temperature predictions. Scanning electron microscopy, optical microscopy, and transmission electron microscopy were used to study the nano-clay dispersion and impact fracture morphology.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Natural Fiber Reinforced Composites · Mechanical Behavior of Composites · Bamboo properties and applications

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Aerospace Engineering, Mississippi State University, Mississippi State, USA

J. Mike Walker ‘66 Department of Mechanical Engineering, Texas A&M University, College Station, USA

School of Engineering, University of British Columbia, Kelowna, Canada

Department of Mechanical Engineering, University of California, Berkeley, USA

Department of Computer Science and Engineering, Mississippi State University, Mississippi State, USA

School of Engineering, Liberty University, Lynchburg, USA

Department of Chemistry, Mississippi State University, Mississippi State, USA

References (63)

Show source-provided references
1. Daghigh V, Lacy TEJr, Daghigh H, et al. Heat deflection temperatures of bio-nano-composites using experiments and machine learning prediction. Mater Today Commun 2020; 22: 100789.10.1016/j.mtcomm.2019.100789 ↗
2. 10.1016/j.polymertesting.2006.02.00310.1016/j.polymertesting.2006.02.003 ↗
3. Khalili SMR · Int J Adv Des Manuf Technol · 2013 · 6 · 81
4. 10.1300/J395v04n02_0710.1300/J395v04n02_07 ↗
5. 10.1002/app.1984.07029126610.1002/app.1984.070291266 ↗
6. 10.1016/0032-3861(79)90039-910.1016/0032-3861(79)90039-9 ↗
7. 10.1016/0032-3861(84)90121-610.1016/0032-3861(84)90121-6 ↗
8. 10.1016/0032-3861(82)90054-410.1016/0032-3861(82)90054-4 ↗
9. 10.1080/03602559.2013.84483210.1080/03602559.2013.844832 ↗
10. 10.1002/app.1984.07029111810.1002/app.1984.070291118 ↗
11. 10.1295/polymj.PJ200616610.1295/polymj.PJ2006166 ↗
12. 10.1016/j.polymertesting.2010.04.00310.1016/j.polymertesting.2010.04.003 ↗
13. 10.1016/j.matdes.2013.07.01210.1016/j.matdes.2013.07.012 ↗
14. 10.1177/105678951351197610.1177/1056789513511976 ↗
15. 10.1016/j.compositesb.2016.01.01710.1016/j.compositesb.2016.01.017 ↗
16. 10.1007/s11029-016-9599-710.1007/s11029-016-9599-7 ↗
17. Lamea M · Mech Compos Mater · 2019 · 55 · 110.1007/s11029-019-09787-z ↗
18. 10.1016/j.matdes.2008.09.04410.1016/j.matdes.2008.09.044 ↗
19. 10.1016/j.conbuildmat.2014.11.04310.1016/j.conbuildmat.2014.11.043 ↗
20. 10.1002/pc.2067510.1002/pc.20675 ↗
21. 10.1016/j.compositesb.2012.06.01010.1016/j.compositesb.2012.06.010 ↗
22. 10.1016/j.polymertesting.2013.10.01110.1016/j.polymertesting.2013.10.011 ↗
23. 10.1016/j.polymertesting.2014.02.00210.1016/j.polymertesting.2014.02.002 ↗
24. 10.1016/S0266-3538(03)00096-410.1016/S0266-3538(03)00096-4 ↗
25. 10.1016/j.polymertesting.2014.12.00210.1016/j.polymertesting.2014.12.002 ↗
26. 10.1016/j.polymertesting.2012.05.01110.1016/j.polymertesting.2012.05.011 ↗
27. 10.1016/j.polymertesting.2014.06.00510.1016/j.polymertesting.2014.06.005 ↗
28. 10.1016/j.polymertesting.2014.02.00310.1016/j.polymertesting.2014.02.003 ↗
29. 10.1016/j.polymertesting.2016.10.01610.1016/j.polymertesting.2016.10.016 ↗
30. 10.1177/073168441877711110.1177/0731684418777111 ↗
31. 10.1016/S0032-3861(02)00048-410.1016/S0032-3861(02)00048-4 ↗
32. 10.1016/S0266-3538(03)00115-510.1016/S0266-3538(03)00115-5 ↗
33. 10.1002/app.2280510.1002/app.22805 ↗
34. 10.1016/j.engfracmech.2006.05.01810.1016/j.engfracmech.2006.05.018 ↗
35. 10.1016/j.ijmecsci.2016.01.01010.1016/j.ijmecsci.2016.01.010 ↗
36. 10.1002/pc.2505710.1002/pc.25057 ↗
37. Daghigh H, Daghigh V, Milani A, et al. Nonlocal bending and buckling of agglomerated CNT-reinforced composite nanoplates. Composite Part B 2020; 183: 107716.10.1016/j.compositesb.2019.107716 ↗
38. 10.1007/s10443-005-1130-610.1007/s10443-005-1130-6 ↗
39. 10.1179/174328906X14652210.1179/174328906X146522 ↗
40. 10.1116/1.281569010.1116/1.2815690 ↗
41. 10.1016/S0032-3861(98)00444-310.1016/S0032-3861(98)00444-3 ↗
42. 10.1177/073168441139853510.1177/0731684411398535 ↗
43. Eslami Farsani R · J Mech Res Appl · 2011 · 3 · 29
44. 10.1016/j.compositesa.2006.01.02110.1016/j.compositesa.2006.01.021 ↗
45. 10.1177/002199830809455010.1177/0021998308094550 ↗
46. 10.1016/S0965-9773(99)00170-110.1016/S0965-9773(99)00170-1 ↗
47. 10.1177/0021955X0203800313910.1177/0021955X02038003139 ↗
48. 10.1016/j.compscitech.2005.12.02810.1016/j.compscitech.2005.12.028 ↗
49. 10.14233/ajchem.2017.2055110.14233/ajchem.2017.20551 ↗
50. 10.1177/073168440708658910.1177/0731684407086589 ↗
51. 10.1002/pc.2475210.1002/pc.24752 ↗
52. 10.1016/B978-075063764-0/50004-210.1016/B978-075063764-0/50004-2 ↗
53. Yankov D, DeCoste D, Keogh E. Ensembles of nearest neighbor forecasts. In: Fürnkranz J., Scheffer T., Spiliopoulou M. (eds.) European conference on machine learning , 18 September 2006, pp. 545-556. Berlin, Heidelberg: Springer.10.1007/11871842_51 ↗
54. Breiman L, Friedman H, Stone CJ, et al. Classification and regression trees . Belmont, CA: Wadsworth and Brooks, 1984.
55. Schapire R. Explaining AdaBoost. In: Empirical inference , 2013, pp. 37-52. Berlin, Heidelberg: Springer.10.1007/978-3-642-41136-6_5 ↗
56. Pedregosa F · J Mach Learn Res · 2011 · 12 · 2825
57. 10.1007/s11222-009-9153-810.1007/s11222-009-9153-8 ↗
58. 10.4028/www.scientific.net/AMR.264-265.74310.4028/www.scientific.net/AMR.264-265.743 ↗
59. 10.1016/j.compositesb.2010.12.01310.1016/j.compositesb.2010.12.013 ↗
60. 10.1177/002199831244902810.1177/0021998312449028 ↗
61. 10.1163/156856104241120410.1163/1568561042411204 ↗
62. 10.1021/ie049644w10.1021/ie049644w ↗
63. 10.1016/j.compositesa.2010.11.01110.1016/j.compositesa.2010.11.011 ↗