Tensile Performance Mechanism for Bamboo Fiber-Reinforced, Palm Oil-Based Resin Bio-Composites Using Finite Element Simulation and Machine Learning

Plant fiber-reinforced composites have the advantages of environmental friendliness, sustainability, and high specific strength and modulus. They are widely used as low-carbon emission materials in automobiles, construction, and buildings. The prediction of their mechanical performance is critical for material optimal design and application. However, the variation in the physical structure of plant fibers, the randomness of meso-structures, and the multiple material parameters of composites limit the optimal design of the composite mechanical properties. Based on tensile experiments on bamboo fiber-reinforced, palm oil-based resin composites, finite element simulations were carried out and the effect of material parameters on the tensile performances of the composites was investigated. In addition, machine learning methods were used to predict the tensile properties of the composites. The numerical results showed that the resin type, contact interface, fiber volume fraction, and multi-factor coupling significantly influenced the tensile performance of the composites. The results of the machine learning analysis showed that the gradient boosting decision tree method had the best prediction performance for the tensile strength of the composites (R2 was 0.786) based on numerical simulation data from a small sample size. Furthermore, the machine learning analysis demonstrated that the resin performance and fiber volume fraction were critical parameters for the tensile strength of composites. This study provides an insightful understanding and effective route for investigating the tensile performance of complex bio-composites.

[1]  M. Nehdi,et al.  Hybrid deep learning model for concrete incorporating microencapsulated phase change materials , 2022, Construction and Building Materials.

[2]  K. Liew,et al.  Machine learning and materials informatics approaches for evaluating the interfacial properties of fiber-reinforced composites , 2021 .

[3]  Le Huang,et al.  Knowledge-enhanced data-driven models for quantifying the effectiveness of PP fibers in spalling prevention of ultra-high performance concrete , 2021 .

[4]  Amit Bhasin,et al.  Exploring the use of machine learning to predict metrics related to asphalt mixture performance , 2021 .

[5]  Huu-Tai Thai,et al.  Strength prediction of concrete-filled steel tubular columns using Categorical Gradient Boosting algorithm , 2021, Engineering Structures.

[6]  Tom Iseley,et al.  A multi-objective optimizer-based model for predicting composite material properties , 2021 .

[7]  Huu-Tai Thai,et al.  Efficient machine learning models for prediction of concrete strengths , 2021, Construction and Building Materials.

[8]  Yahui Zhang,et al.  Outdoor bamboo-fiber-reinforced composite: Influence of resin content on water resistance and mechanical properties , 2020 .

[9]  Kushairi Mohd Salleh,et al.  Predicting thermal conductivity and mechanical property of bamboo fibers/polypropylene nonwovens reinforced composites based on regression analysis , 2020 .

[10]  Tingting Chen,et al.  Biocomposites from bamboo fibers and palm oil-based thermosets: Effects of natural phenolic cross-linkers , 2020 .

[11]  Haitao Yang,et al.  AI Applications through the Whole Life Cycle of Material Discovery , 2020, Matter.

[12]  Xiaofeng Sun,et al.  Novel engineered wood and bamboo composites for structural applications: State-of-art of manufacturing technology and mechanical performance evaluation , 2020 .

[13]  Q. Han,et al.  A generalized method to predict the compressive strength of high-performance concrete by improved random forest algorithm , 2019, Construction and Building Materials.

[14]  Q. Ma,et al.  Improvement of Clayey Soils by Combined Bamboo Strip and Flax Fiber Reinforcement , 2019, Advances in Civil Engineering.

[15]  Ge Wang,et al.  Fracture modes of bamboo fiber bundles in three-point bending , 2019, Cellulose.

[16]  R. Qiu,et al.  Properties of natural fiber-reinforced biobased thermoset biocomposites: Effects of fiber type and resin composition , 2019, Composites Part B: Engineering.

[17]  Zehui Jiang,et al.  Analysis of tension and bending fracture behavior in moso bamboo (Phyllostachys pubescens) using synchrotron radiation micro-computed tomography (SRμCT) , 2019, Holzforschung.

[18]  Yili Wu,et al.  Development of a reinforced styrene-free unsaturated polyester composite based on bamboo fibers , 2019, Holzforschung.

[19]  Grace X. Gu,et al.  Machine learning for composite materials , 2019, MRS Communications.

[20]  Frederic E. Bock,et al.  A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics , 2019, Front. Mater..

[21]  L. Appels,et al.  Bamboo fibres sourced from three global locations: A microstructural, mechanical and chemical composition study , 2019, Journal of Reinforced Plastics and Composites.

[22]  J. Qiu,et al.  Concurrent improvements in crosslinking degree and interfacial adhesion of hemp fibers reinforced acrylated epoxidized soybean oil composites , 2018 .

[23]  Anna Veronika Dorogush,et al.  CatBoost: unbiased boosting with categorical features , 2017, NeurIPS.

[24]  S. Patsias,et al.  Numerical predictions of the anisotropic viscoelastic response of uni-directional fibre composites , 2017 .

[25]  Y. Joliff,et al.  Validation of a Representative Volume Element for unidirectional fiber-reinforced composites: Case of a monotonic traction in its cross section , 2016 .

[26]  George Stefanou,et al.  Effect of waviness and orientation of carbon nanotubes on random apparent material properties and RVE size of CNT reinforced composites , 2016 .

[27]  Hui Liu,et al.  Development of RVE-embedded solid elements model for predicting effective elastic constants of discontinuous fiber reinforced composites , 2016 .

[28]  Bernhard Schölkopf,et al.  Domain Adaptation under Target and Conditional Shift , 2013, ICML.

[29]  Anthony M. Waas,et al.  The influence of the representative volume element (RVE) size on the homogenized response of cured fiber composites , 2012 .

[30]  Zhenqing Wang,et al.  Automatic generation of random distribution of fibers in long-fiber-reinforced composites and mesomechanical simulation , 2011 .

[31]  L. Breiman.  Random Forests , 2001, Encyclopedia of Machine Learning and Data Mining.

[32]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[33]  R. Gopi,et al.  A study on mechanical properties of bamboo fiber reinforced polymer composite , 2020 .

[34]  Gobinath Velu Kaliyannan,et al.  Study on mechanical characteristics of woven cotton/bamboo hybrid reinforced composite laminates , 2020 .

[35]  Gang Wu,et al.  Compression Behaviors of Parallel Bamboo Strand Lumber Under Static Loading , 2019, Journal of Renewable Materials.

[36]  Vladimir Vapnik,et al.  Support-vector networks , 2004, Machine Learning.