Machine Learning-Enabled Data-Driven Research on Paper-Reinforced Composite Materials

Paper-reinforced composite materials represent a renewable and biodegradable resource. These composites blend paper fibers with binders to enhance critical mechanical properties, such as compressive strength, compressive strain at rupture, strain energy density for resilience, and strain energy. This research actively promotes the development of eco-friendly materials, reducing reliance on non-biodegradable substances that contribute to environmental pollution and waste. Moreover, this paper delves into the integration of machine learning techniques for predicting material properties, demonstrating their reliability. Among the machine learning models, including Support Vector Machine (SVM), Decision Tree (DT), and k-Nearest Neighbor (KNN), Random Forest (RF) showcased the best performance with 96% accuracy. The analysis included performance parameter assessments and calculations of sensitivity and specificity for mechanical properties. This integration significantly cuts costs and time associated with experimentation and design iterations, enabling researchers to uncover fundamental characteristics of composite materials and in turn, facilitating the development of novel composites with enhanced performance attributes.