[Paper Review] Evolving Genetic Programming Tree Models for Predicting the Mechanical Properties of Green Fibers for Better Biocomposite Materials

Faris M. AL‐Oqla, Hossam Faris+2 more|arXiv (Cornell University)|Feb 20, 2024

Natural Fiber Reinforced Composites4 citations

TL;DR

This study develops evolving genetic programming tree models to predict the tensile strength, Young's modulus, and elongation at break of natural green fibers using key chemical and structural properties—cellulose, hemicellulose, lignin, moisture content, and microfibrillar angle. The models achieve high predictive accuracy, with the microfibrillar angle contributing 44.7% to tensile strength prediction, significantly reducing the need for costly experimental testing in biocomposite development.

ABSTRACT

Advanced modern technology and industrial sustainability theme have contributed implementing composite materials for various industrial applications. Green composites are among the desired alternatives for the green products. However, to properly control the performance of the green composites, predicting their constituents properties are of paramount importance. This work presents an innovative evolving genetic programming tree models for predicting the mechanical properties of natural fibers based upon several inherent chemical and physical properties. Cellulose, hemicellulose, lignin and moisture contents as well as the Microfibrillar angle of various natural fibers were considered to establish the prediction models. A one-hold-out methodology was applied for training/testing phases. Robust models were developed to predict the tensile strength, Young's modulus, and the elongation at break properties of the natural fibers. It was revealed that Microfibrillar angle was dominant and capable of determining the ultimate tensile strength of the natural fibers by 44.7% comparable to other considered properties, while the impact of cellulose content in the model was only 35.6%. This in order would facilitate utilizing artificial intelligence in predicting the overall mechanical properties of natural fibers without experimental efforts and cost to enhance developing better green composite materials for various industrial applications.

Motivation & Objective

• To develop AI-driven predictive models for mechanical properties of natural green fibers to reduce experimental costs.
• To identify the most influential chemical and structural fiber properties in determining tensile strength, Young’s modulus, and elongation at break.
• To apply evolving genetic programming tree models to establish robust, interpretable relationships between fiber composition and mechanical behavior.
• To support sustainable composite material design by enabling accurate, data-driven prediction of fiber performance.

Proposed method

• Genetic programming (GP) is employed to evolve tree-structured mathematical models that map input fiber properties to mechanical outputs.
• Input features include cellulose, hemicellulose, lignin, moisture content, and microfibrillar angle of various natural fibers.
• A one-hold-out cross-validation strategy is used to split data into training and testing sets for model evaluation.
• Model evolution is guided by fitness functions optimizing R², mean absolute error, and mean squared error on the test set.
• Feature importance is quantified using permutation-based analysis to assess the contribution of each input variable.
• The final models are interpretable, providing explicit mathematical expressions linking input variables to mechanical outputs.

Experimental results

Research questions

• RQ1 Which fiber properties most significantly influence the tensile strength of natural green fibers?
• RQ2 How accurately can genetic programming tree models predict mechanical properties like Young’s modulus and elongation at break?
• RQ3 What is the relative contribution of microfibrillar angle versus chemical composition (e.g., cellulose, lignin) in predicting fiber strength?
• RQ4 Can evolving GP models provide both high accuracy and interpretability in predicting green fiber mechanical behavior?

Key findings

• The microfibrillar angle contributed 44.7% to the prediction of ultimate tensile strength, making it the most influential factor.
• Cellulose content contributed 35.6% to tensile strength prediction, indicating a strong but secondary role compared to microfibrillar angle.
• The developed GP models achieved high predictive accuracy, enabling reliable estimation of mechanical properties without experimental testing.
• The models demonstrated robust generalization on unseen test data, validating their reliability for real-world biocomposite design.
• The interpretability of the evolved tree models allows for clear insight into the physical relationships between fiber structure and mechanical response.