ANN-Based Mechanical Property Prediction of Bio-Fibre for Wind Turbine Blade Materials with FEM Validation
DOI:
https://doi.org/10.26877/asset.v8i1.2482Keywords:
Artificial Neural Network (ANN), Finite Element Method (FEM), Bio-Composites, Pineapple Fiber, Wind Turbine BladesAbstract
The increasing demand for renewable energy highlights the need for sustainable materials in wind turbine blade design. Conventional fiberglass blades, while effective, present environmental and disposal challenges, motivating the exploration of bio-composites as greener alternatives. This study aims to develop and validate an integrated framework that combines experimental validation, Finite Element Method (FEM) pre-screening, Artificial Neural Networks (ANN), and Rule of Mixtures (RoM) validation to evaluate the feasibility of bio-fibre wind turbine blades Mechanical properties of flax, hemp, sisal, jute, pineapple fiber, and resin are obtained from previously published experimental studies available in the literature, with resin content fixed at 90% and permutations generated for ANN training. Experimental tensile testing on a 90% resin–10% pineapple fiber composite yields 131 MPa, closely matching the permutation prediction of 118.6 MPa, confirming dataset reliability. FEM simulations are then employed to pre-screen potential maximum performance values within the dataset range, ensuring the physical feasibility of ANN input properties. Using these validated inputs, the ANN predicts feasible bio-composite compositions, which are further compared against RoM estimations. The results show that ANN predictions remain within a 7% deviation from RoM values, demonstrating consistency with micromechanical theory. This integrated framework highlights that FEM-based input screening enhances ANN prediction reliability, and pineapple-based bio-composites can serve as sustainable and technically viable alternatives for wind turbine blade applications.
References
[1] Pender K, Bacharoudis K, Romoli F, Greaves P, Fuller J. Feasibility of Natural Fibre Usage for Wind Turbine Blade Components: A Structural and Environmental Assessment. Sustainability (Switzerland) 2024;16:5533. https://doi.org/10.3390/SU16135533/S1.
[2] Tomczyk A, Sokołowska Z, Boguta P. Biochar physicochemical properties: pyrolysis temperature and feedstock kind effects. Rev Environ Sci Biotechnol 2020;19:191–215. https://doi.org/10.1007/s11157-020-09523-3.
[3] G Schyns ZO, Shaver MP, G Schyns ZO, Shaver MP. Mechanical Recycling of Packaging Plastics: A Review. Macromol Rapid Commun 2021;42:2000415. https://doi.org/10.1002/MARC.202000415.
[4] Jabu MA, Alugongo AA, Maube O, Nkomo NZ. Effects of Hybrid Rubber Particle and Glass Fibre Composite on Mechanical and Vibrational Damping Properties of Railway Sleeper. International Journal of Engineering Trends and Technology 2023;71:28–41. https://doi.org/10.14445/22315381/IJETT-V71I7P203.
[5] Koh R. Bio-based wind turbine blades: Renewable energy meets sustainable materials for clean, green power 2017. https://doi.org/10.7275/10487006.0.
[6] Andrew JJ, Dhakal HN. Sustainable biobased composites for advanced applications: recent trends and future opportunities – A critical review. Composites Part C: Open Access 2022;7:100220. https://doi.org/10.1016/J.JCOMC.2021.100220.
[7] Batu T, Lemu HG, Sirhabizuh B. Study of the Performance of Natural Fiber Reinforced Composites for Wind Turbine Blade Applications. Advances in Science and Technology Research Journal 2020;14:67–75. https://doi.org/10.12913/22998624/118201.
[8] Muyan C, Coker D. Finite element simulations for investigating the strength characteristics of a 5m composite wind turbine blade. Wind Energy Science 2020;5:1339–58. https://doi.org/10.5194/WES-5-1339-2020.
[9] Owen MM, Wong LS, Achukwu EO, Shuib S, Din NBM. Characterization of Resin-Infused Nonwoven Natural Fiber-Reinforced Epoxy Composites for Renewable Energy Structural Applications: Comparative Experimental and Finite Element Analysis. Polym Compos 2025. https://doi.org/10.1002/PC.70064;PAGE:STRING:ARTICLE/CHAPTER.
[10] Shah DU. Natural fibre composites: Comprehensive Ashby-type materials selection charts. Materials & Design (1980-2015) 2014;62:21–31. https://doi.org/https://doi.org/10.1016/j.matdes.2014.05.002.
[11] Wang P, Li Y, Gao X, Ye Y, Li R, Li X, et al. Numerical Analysis on the Static Performance of Gas Journal Bearing by Using Finite Element Method. Nanomanufacturing and Metrology 2024;7:1–20. https://doi.org/10.1007/S41871-023-00219-0/FIGURES/10.
[12] Arini NR, Gilang Muhammad, Joke Pratilastiarso, Setyo Nugroho. Numerical Study of a Wind Turbine Blade Modification Using 30° Angle Winglet on Clark Y Foil. EMITTER International Journal of Engineering Technology 2022:311–9. https://doi.org/10.24003/emitter.v10i2.680.
[13] Corbalán PA, Chiang LE. Fast Power Coefficient vs. Tip–Speed Ratio Curves for Small Wind Turbines with Single-Variable Measurements following a Single Test Run. Energies 2024, Vol 17, Page 1199 2024;17:1199. https://doi.org/10.3390/EN17051199.
[14] Ughapu EI, Adaramola BA, Oke W, Okokpujie IP. Study of the Moment of Drag and Lift on Different Air-foil Shapes and Thickness During Wind Tunnel Application: A Review. E3S Web of Conferences 2023;430:01211. https://doi.org/10.1051/E3SCONF/202343001211.
[15] Maxemow S. That’s a Drag: The Effects of Drag Forces. Undergraduate Journal of Mathematical Modeling: One + Two 2009;2:4. https://doi.org/http://dx.doi.org/10.5038/2326-3652.2.1.4.
[16] Haykin SS. Neural Networks: A Comprehensive Foundation (3rd Edition), 2007.
[17] Moshtaghzadeh M, Aligoodarz MR. Prediction of Wind Turbine Airfoil Performance Using Artificial Neural Network and CFD Approaches. International Journal of Engineering and Technology Innovation 2022;12:275–87. https://doi.org/10.46604/IJETI.2022.9735.
[18] Priyanto, Faisal M, Imamudin M. Artificial Neural Network-Based Forecasting of Rice Yield Using Environmental and Agricultural Data. Advance Sustainable Science Engineering and Technology 2025;7:02503023–02503023. https://doi.org/10.26877/YP286B25.
[19] He J, Li L, Xu J, Zheng C. ReLU Deep Neural Networks and Linear Finite Elements. Journal of Computational Mathematics 2018;38:502–27. https://doi.org/10.4208/jcm.1901-m2018-0160.
[20] Meng S, Chen A, Wang C, Zheng M, Wu F, Chen X, et al. Enhancing Exchange Rate Forecasting with Explainable Deep Learning Models 2024. https://doi.org/10.1109/EIECS63941.2024.10800545.
[21] Jack Feng CX, Yu ZGS, Kingi U, Pervaiz Baig M. Threefold vs. fivefold cross validation in one-hidden-layer and two-hidden-layer predictive neural network modeling of machining surface roughness data. J Manuf Syst 2005;24:93–107. https://doi.org/10.1016/S0278-6125(05)80010-X.
[22] Lee C, Hwang W. Modified rule of mixtures for prediction of tensile strength of unidirectional fiber-reinforced composites. J Mater Sci Lett 1998;17:1601–3. https://doi.org/10.1023/A:1006536431431/METRICS.
[23] Jasti A, Chandra BA, Biswas S. Modified Halpin–Tsai model for predicting the mechanical properties of polymer composites reinforced with different cross-sectional fibers. Mater Today Proc 2023;91:14–8. https://doi.org/10.1016/J.MATPR.2023.04.131.
[24] Brøndsted P, Lilholt H, Lystrup A. Composite materials for wind power turbine blades. Annu Rev Mater Res 2005;35:505–38.
[25] Al-Balushi A, Alam K, Iqbal M, Husain A, Ahmad A, Al-Amrani A. Modelling and Analysis of Deformation and Stresses in Horizontal Axis Wind Turbine. CFD Letters 2023;15:16–24. https://doi.org/10.37934/cfdl.15.2.1624.
