Variations in mixture proportions of plasticizers, additives, and crosslinking agents have significant impacts on mechanical performance of starch-based foam materials. In particular, starch/ethylene-vinyl acetate (EVA) foam materials have been developed with improved mechanical strength by optimizing the formulation. There is a lack of numerical correlations that could help analyze the effects of components and provide a predictive method for future research. In this study, we develop simple and accurate predictions for tensile strength and resilience based on mixture proportions of components for starch-based/EVA foam materials. The models constructed might be used to help design mixture proportions of starch-based foam materials. By combining optimization results from the Taguchi method and machine learning approaches, it is expected that more quantitative data can be extracted from fewer experimental trials at the same time.
ZhangYKochCCSchwartzJ. Synthesis of Bi2Sr2CaCu2Oxsuperconductors via direct oxidation of metallic precursors. Superconductor Sci Tech2014; 27(5): 055016. DOI: 10.1088/0953-2048/27/5/055016.
DosmannLP and RN Steel. U.S. Patent1961; 3: 33493.
7.
CoccorulloIDi MaioLMontesanoS, et al.Theoretical and experimental study of foaming process with chain extended recycled PET. Express Polym Lett2009; 3(2): 84–96. DOI: 10.3144/expresspolymlett.2009.12.
8.
Solorza-FeriaJOrtiz-ZaramaMAJimenez-AparicioA, et al.Production and characterization of fully biobased foamed films based on gelatin. Cell Polym2020; 39(2): 69–97. DOI: 10.1177/0262489319897632.
RodriguesNHPde SouzaJTRodriguesRL, et al.Starch-based foam packaging developed from a by-product of potato industrialization (solanum tuberosum L.). Appl Sci2020; 10(7): 2235. DOI: 10.3390/app10072235.
11.
SalgadoPRSchmidtVCMolina OrtizSE, et al.Biodegradable foams based on cassava starch, sunflower proteins and cellulose fibers obtained by a baking process. J Food Eng2008; 85(3): 435–443. DOI: 10.1016/j.jfoodeng.2007.08.005.
12.
WesthoffRPOteyFHMehltretterCL, et al.Starch-filled polyvinyl chloride plastics-preparation and evaluation. Prod R&D1974; 13(2): 123–125. DOI: 10.1021/i360050a008.
13.
EvangelistaRLSungWJaneJL, et al.Effect of compounding and starch modification on properties of starch-filled low-density polyethylene. Ind Eng Chem Res1991; 30(8): 1841–1846. DOI: 10.1021/ie00056a025.
14.
ManiRBhattacharyaM. Properties of injection moulded starch/synthetic polymer blends-III. Effect of amylopectin to amylose ratio in starch. Eur Polym J1998; 34(10): 1467–1475. DOI: 10.1016/S0014-3057(97)00273-5.
15.
ZhouJSongJParkerR. Structure and properties of starch-based foams prepared by microwave heating from extruded pellets. Carbohydr Polym2006; 63(4): 466–475. DOI: 10.1016/j.carbpol.2005.09.019.
16.
PushpadassHABabuGSWeberRW, et al.Extrusion of starch-based loose-fill packaging foams: effects of temperature, moisture and talc on physical properties. Packaging Tech Sci2008; 21(3): 171–183. DOI: 10.1002/pts.809.
17.
ZhangJ-FSunX. Biodegradable foams of poly(lactic acid)/starch. i. extrusion condition and cellular size distribution. J Appl Polym Sci2007; 106(2): 857–862. DOI: 10.1002/app.26715.
18.
HannaSMAHannaMA. Physical, mechanical, and thermal properties of starch-based plastic foams. Trans ASAE1995; 38(2): 567–571. DOI: 10.13031/2013.27867.
19.
AbinaderGLacosteCBaillifML, et al.Effect of the formulation of starch-based foam cushions on the morphology and mechanical properties. J Cell Plastics2015; 51(1): 31–44. DOI: 10.1177/0021955X14527979.
20.
Rodriguez-PerezMASimoesRDRoman-LorzaS, et al.Foaming of EVA/starch blends: characterization of the structure, physical properties, and biodegradability. Polym Eng Sci2012; 52(1): 62–70. DOI: 10.1002/pen.22046.
21.
PolatSUsluM-KAygünA, et al.The effects of the addition of corn husk fibre, kaolin and beeswax on cross-linked corn starch foam. J Food Eng2013; 116(2): 267–276. DOI: 10.1016/j.jfoodeng.2012.12.017.
22.
HassanMMTuckerNLe GuenMJ. Thermal, mechanical and viscoelastic properties of citric acid-crosslinked starch/cellulose composite foams. Carbohydr Polym2020; 230: 115675. DOI: 10.1016/j.carbpol.2019.115675.
23.
MengLLiuHYuL, et al.How water acting as both blowing agent and plasticizer affect on starch-based foam. Ind Crops Prod2019; 134: 43–49. DOI: 10.1016/j.indcrop.2019.03.056.
24.
HannaQHannaMA. Mechanical properties of starch-based foams as affected by ingredient formulations and foam physical characteristics. Trans ASAE2000; 43(6): 1715–1723. DOI: 10.13031/2013.3073.
25.
MaliSDebiagiFGrossmannMVE, et al.Starch, sugarcane bagasse fibre, and polyvinyl alcohol effects on extruded foam properties: a mixture design approach. Ind Crops Prod2010; 32(3): 353–359. DOI: 10.1016/j.indcrop.2010.05.014.
26.
ZhangYXuX. Predicting the delamination factor in carbon fibre reinforced plastic composites during drilling through the gaussian process regression. J Compos Mater2021; 55: 2061–2068. DOI: 10.1177/0021998320984245.
ZhangYXuX. Machine learning glass transition temperature of polyacrylamides using quantum chemical descriptors. Polym Chem2021; 12: 843–851. DOI: 10.1039/d0py01581d.
29.
XiaRHuangXLiM. Starch foam material performance prediction based on a radial basis function artificial neural network trained by bare-bones particle swarm optimization with an adaptive disturbance factor. J Appl Polym Sci2016; 133: 44252. DOI: 10.1002/app.44252.
30.
ZhangYXuX. Predicting the thermal conductivity enhancement of nanofluids using computational intelligence. Phys Lett A2020; 384: 126500. DOI: 10.1016/j.physleta.2020.126500.
31.
ZhangYXuX. Relative cooling power modeling of lanthanum manganites using gaussian process regression. RSC Adv2020; 10: 20646–20653. DOI: 10.1039/D0RA03031G.
32.
RasmussenCEWilliamsCK. Gaussian Processes for Machine Learning. Cambridge, MA: MIT Press, 2006.
33.
ZhangYXuX. Predictions of adsorption energies of methane-related species on cu-based alloys through machine learning. Machine Learn Appl2021; 3: 100010. DOI: 10.1016/j.mlwa.2020.100010.
34.
ZengGSunG. Prediction model and application of biological forming materials based on BP neural network. Acta Materiae Compositae Sinica2014; 31: 107–111.
35.
SiddiqueeANKhanZAGoelP, et al.Optimization of deep drilling process parameters of AISI 321 steel using taguchi method. Proced Mater Sci2014; 6: 1217–1225. DOI: 10.1016/j.mspro.2014.07.195.
36.
ZhangYXuX. Machine learning properties of electrolyte additives: a focus on redox potentials. Ind Eng Chem Res2021; 60(1): 343–354. DOI: 10.1021/acs.iecr.0c05055.
37.
ZhangYXuX. Predicting the material removal rate during electrical discharge diamond grinding using the gaussian process regression: a comparison with the artificial neural network and response surface methodology. Int J Adv Manufacturing Tech2021; 113: 1527–1533. DOI: 10.1007/s00170-021-06701-7.
38.
WillettJL. “Starch in Polymer Compositions,” in Starch. Academic Press, 2009, pp. 715–743. DOI: 10.1016/B978-0-12-746275-2.00019-7.
39.
WangX-LYangK-KWangY-Z. Properties of starch blends with biodegradable polymers. J Macromolecular Sci C: Polym Rev2003; 43(3): 385–409. DOI: 10.1081/MC-120023911.
