Bio-based sandwich I-joists have attracted increasing attention as sustainable alternatives to conventional load-bearing wood products; however, the bending performance of hybrid lignocellulosic sandwich webs remains insufficiently understood due to the complex interactions among material composition and structural configuration. In this study, the bending behavior of bio-based I-shaped sandwich beams composed of laminated veneer lumber (LVL) flanges and multilayer sandwich web cores made from cattail–poplar particles were systematically investigated. The effects of key structural parameters, including web core density, number of kraft-paper-separated web layers, and jute fabric surface density, on the modulus of rupture (MOR) were evaluated through three-point bending tests. A multivariate nonlinear regression (MNLR) model was developed to explicitly describe the nonlinear dependence of bending strength on the studied parameters, and regularization was applied to improve model stability and limit overfitting. Model performance was assessed using R2, RMSE, and MAE, and the validated MNLR model was subsequently coupled with a genetic algorithm (GA) to identify optimal web architectures that maximize bending performance. The results demonstrate that the number of web layers is the most influential parameter governing MOR, followed by core density, while the contribution of jute surface density is comparatively weaker. Scanning electron microscopy observations further revealed that increasing the number of web layers reduces core porosity and enhances interfacial bonding, thereby promoting more efficient stress transfer under bending loads. Overall, this integrated experimental and data-driven framework provides a reliable basis for predicting and optimizing the bending performance of hybrid lignocellulosic sandwich I-joists.
LeichtiRJFalkRHLaufenbergTL. Prefabricated wood I-joists: an industry overview. For Prod J1990; 40: 15–20.
2.
KodurVSteinJFikeR, et al.Comparative fire performance of traditional lumber and engineered wood joists. J Struct Fire Eng2017; 8: 2–13. https://doi.org/10.1108/jsfe-01-2017-0003
3.
HarteAMBaylorGO’CeallaighC. Evaluation of the mechanical behaviour of novel latticed LVL-Webbed joists. Open Constr Build Technol J2019; 13: 1–10. https://doi.org/10.2174/1874836801913010001
4.
ChenLZhangYChenZ, et al.Biomaterials technology and policies in the building sector: a review. Environ Chem Lett2024; 22: 715–750.
5.
DieyeYTourePMGueyePM, et al.Thermomechanical characterization of particleboards from powder typha leaves. J Sustain Constr Mater Technol2019; 4: 306–317. https://doi.org/10.29187/jscmt.2019.34
6.
WuzellaGMahendranARKandelbauerA. Green composite material made from Typha latifolia fibres bonded with an epoxidized linseed oil/tall oil-based polyamide binder system. J Renew Mater2020; 8: 499–512. https://doi.org/10.32604/jrm.2020.09615
7.
ParvinMShadhinMDulalM, et al.Harnessing cattail biomass for sustainable fibers and engineered bioproducts: a review. Glob Chall2025; 9: 2400183. https://doi.org/10.1002/gch2.202400183
8.
BhuvaneswariVRajeshkumarLSathishkumarTP, et al.Effect of fiber orientation on physical and mechanical properties of Typha angustifolia natural fiber reinforced composites. Appl Sci Eng Prog2023; 16: 6497–6507.
9.
HossainMSRahmanMCicekN. Tensile properties of cattail fibres at various phenological development stages. Polymers2024; 16: 2692. https://doi.org/10.3390/polym16192692
10.
HartungCDandikasVEickenscheidtT, et al.Optimal harvest time for high biogas and biomass yield of Typha latifolia, Typha angustifolia and Phalaris arundinacea. Biomass Bioenerg2023; 175: 106847. https://doi.org/10.1016/j.biombioe.2023.106847
11.
OhsowskiBMReddingCGeddesP, et al.Field-based measurement tools to distinguish clonal Typha taxa and estimate biomass: a resource for conservation and restoration. Front Plant Sci2024; 15: 1348144. https://doi.org/10.3389/fpls.2024.1348144
12.
JeonHCKimYS. Modulated mechanical properties of epoxy-based hybrid composites via layer-by-layer assembly: an experimental and numerical study. Polymers2024; 16: 3559. https://doi.org/10.3390/polym16243559
13.
Sheini DashtgoliDTaghizadehSMacconiL, et al.Comparative analysis of machine learning models for predicting the mechanical behavior of bio-based cellular composite sandwich structures. Materials2024; 17: 3493. https://doi.org/10.3390/ma17143493
14.
KibreteFTrzepiecińskiTGebremedhenHS, et al.Artificial intelligence in predicting mechanical properties of composite materials. J Compos Sci2023; 7: 364. https://doi.org/10.3390/jcs7090364
15.
KarimiSAliABYuJ. Machine learning-based strength prediction of nano-reinforced adhesive and hybrid joints under hygrothermal conditions. Mater Today Commun2024; 41: 111046. https://doi.org/10.1016/j.mtcomm.2024.111046
16.
ZeinaliMRahimiGHosseiniS. Estimation of buckling load in sandwich beams with novel honeycomb core: a non-destructive approach enhanced by machine learning and genetic algorithm optimization. Int J Struct Stab Dyn2025; 0219–4554.
17.
KamarianSGoudarziHHeidarizadiE, et al.Flame-retardant sustainable sandwich beams with 3D-printed peanut-shaped cellular cores and natural composite face sheets: structural analysis. Case Stud Therm Eng2025; 75: 107114. https://doi.org/10.1016/j.csite.2025.107114
18.
Nguyen-HoangSPhung-VanPNatarajanS, et al.A combined scheme of edge-based and node-based smoothed finite element methods for reissner–Mindlin flat shells. Eng Comput2016; 32: 267–284. https://doi.org/10.1007/s00366-015-0416-z
19.
NazerianMAkbarzadehMPapadopoulosAN. Comparative analysis of ANN-MLP, ANFIS-ACOR and MLR modeling approaches for estimation of bending strength of Glulam. J Compos Sci2023; 7: 57. https://doi.org/10.3390/jcs7020057
20.
NikooMMalekabadiRAHafeezG. Estimating the mechanical properties of heat-treated woods using optimization algorithms-based ANN. Measurement2023; 207: 112354. https://doi.org/10.1016/j.measurement.2022.112354
21.
HasanagićR. Optimization of thermal modification of wood by genetic algorithm and classical mathematical analysis. J For Sci2022; 68: 35–45. https://doi.org/10.17221/95/2021-jfs
22.
ChenSShiinaRNakaiK, et al.Potential of machine learning approaches for predicting mechanical properties of spruce wood in the transverse direction. J Wood Sci2023; 69: 22. https://doi.org/10.1186/s10086-023-02096-z
23.
Garcia FernandezFGarcía EstebanLPalacios de PalaciosPD, et al.Prediction of standard particleboard mechanical properties utilizing an artificial neural network and subsequent comparison with a multivariate regression model. Investig Agrar: Sist Rec For2008; 17: 178–187.
24.
ErcumentDBElmoghazyYHAlMZ, et al.Mechanical behaviour and energy absorption performance of modified anti-tri chiral novel auxetic structures through experimental and numerical analysis subjected to surrogate metamodeling. Results Eng2026; 29: 108967. https://doi.org/10.1016/j.rineng.2026.108967
25.
ArabiMFaezipourMGholizadehH. Reducing resin content and board density without adversely affecting the mechanical properties of particleboard through controlling particle size. J For Res2011; 22: 659–664. https://doi.org/10.1007/s11676-011-0207-3
26.
KelleciOKoksalSEAydemirD, et al.Eco-friendly particleboards with low formaldehyde emission and enhanced mechanical properties produced with foamed urea-formaldehyde resins. J Clean Prod2022; 379: 134785. https://doi.org/10.1016/j.jclepro.2022.134785
27.
LeckieFADal BelloDJ. Strength and stiffness of engineering systems. Mechanical Engineering Series. Springer, 2009, p. 696.
28.
ManickamPGovindarajanT. Optimization of process parameters for coloration & antibacterial finishing of silk fabrics using natural fungal extract. Res J Text Apparel2012; 16: 39–46.
29.
DesaiKMSurvaseSASaudagarPS, et al.Comparison of artificial neural network (ANN) and response surface methodology (RSM) in fermentation media optimization: case study of fermentative production of scleroglucan. Biochem Eng J2008; 41: 266–273. https://doi.org/10.1016/j.bej.2008.05.009
30.
LukKCBallJESharmaA. A study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting. J Hydrol2000; 227: 56–65. https://doi.org/10.1016/s0022-1694(99)00165-1
31.
HwangMYParkJHSongJ, et al.Enhanced reverse-engineering method for accurately predicting lamina properties in laminated composites via combined static and dynamic finite element simulations. J Compos Sci2023; 7: 518. https://doi.org/10.3390/jcs7120518
32.
SorourSSSalehCAShazlyM. A review on machine learning implementation for predicting and optimizing the mechanical behaviour of laminated fiber-reinforced polymer composites. Heliyon2024; 10: e33681. https://doi.org/10.1016/j.heliyon.2024.e33681
33.
HuaXCaoYLiuB, et al.Prediction of thermomechanical behavior of wood–plastic composites using machine learning models: emphasis on extreme learning machine. Polymers2025; 17: 1852. https://doi.org/10.3390/polym17131852
34.
SharmaHAroraGSinghMK, et al.Review of machine learning approaches for predicting mechanical behavior of composite materials. Discover Appl Sci2025; 7: 1238. https://doi.org/10.1007/s42452-025-07616-8
35.
BishopC. Pattern recognition and machine learning. Springer, 2006.
36.
HuHWeiQWangT, et al.Experimental and numerical investigation integrated with Machine Learning (ML) for the prediction strategy of DP590/CFRP composite laminates. Polymers2024; 16: 1589. https://doi.org/10.3390/polym16111589
GibsonLJAshbyMFKaramGN, et al.The mechanical properties of natural materials. II. Microstructures for mechanical efficiency. Proc R Soc Lond A1995; 450: 141–162. https://doi.org/10.1098/rspa.1995.0076
39.
UzayCGerenNBoztepeM, et al.Bending behavior of sandwich structures with different fiber facing types and extremely low-density foam cores. Mater Test2019; 61: 220–230. https://doi.org/10.3139/120.111311
BrejchaVBöhmMHolečekT, et al.Comparison of bending properties of sandwich structures using conventional and 3D-printed core with flax fiber reinforcement. J Compos Sci2025; 9: 182. https://doi.org/10.3390/jcs9040182
43.
KumarSSShyamalaPPatiPR, et al.Investigation and machine learning-based prediction of mechanical properties in hybrid natural fiber composites. Sci Rep2025; 15: 33700. https://doi.org/10.1038/s41598-025-18944-5
44.
AyrilmisNKaymakciAAkbulutT, et al.Mechanical performance of composites based on wastes of polyethylene aluminum and lignocellulosics. Compos Part B Eng2013; 47: 150–154. https://doi.org/10.1016/j.compositesb.2012.10.019
45.
GholampourAOzbakkalogluT. A review of natural fiber composites: properties, modification and processing techniques, characterization, applications. J Mater Sci2020; 55: 829–892. https://doi.org/10.1007/s10853-019-03990-y
46.
GeYLuTLiX, et al.Changes in temperature and vapor-pressure behavior of bamboo scrimber in response to hot-pressing parameters. Forests2024; 15: 620. https://doi.org/10.3390/f15040620
