Fatigue Life Prediction of Flax-Epoxy Composite Using Supervised Learning Techniques

<p dir="ltr">Composite materials have gained significant attention in engineering applications due to their lightweight, high strength, and durability properties. This project presents a comprehensive study that predicts the fatigue life cycle of strain-controlled tested flax-epoxy composites compared to stress-controlled conditions. Traditional approaches relying on experimental testing have limitations in accurately capturing the intricate fatigue behaviour of these materials. Therefore, this work introduces a novel approach utilizing machine learning techniques to enhance fatigue life assessment prediction accuracy and efficiency. The study encompasses a detailed analysis of composite material properties, focusing on natural fibre-based composites, specifically flax fibre-reinforced epoxy composites. Natural fibres like flax offer environmental benefits and have shown promise as sustainable alternatives to traditional synthetic fibres. The importance of flax fibres is underscored by referencing seminal works in the field that highlight the unique mechanical and structural attributes of flax-reinforced composites. This project involves collecting a strain-controlled data set that serves as the foundation for training and validating different machine learning algorithms, including but not limited to Xtreme Gradient Boosting (XGB), support vector machines(SVR), and random forests. Integrating machine learning techniques aims to uncover complex relationships and patterns within the fatigue data that might elude traditional analysis methods. By leveraging these techniques, the project seeks to develop predictive models capable of accurately estimating fatigue life cycles under varying loading conditions. The outcomes of this project hold significant implications for engineering design and material selection in industries reliant on composite materials. Implementing machine learning based fatigue life prediction could expedite the design process, reduce costly experimental testing, and enhance the understanding of fatigue behaviour in composite structures. Furthermore, the study contributes to the broader discourse on sustainable materials by highlighting the potential of natural fibre composites, specifically flax-reinforced composites, as environmentally friendly alternatives. </p><p dir="ltr">Keywords: composite materials, fatigue life prediction, machine learning, natural fibres, flax-reinforced composites, sustainable materials, strain-controlled testing, stress-controlled testing, predictive modelling</p>