Prediction of the Fracture Toughness of Silicafilled Epoxy Composites using K-Nearest Neighbor (KNN) Method

Abstract

The mechanical behavior of particle reinforced polymer composites depends largely on the properties of the particles used to reinforce it. Geometrical properties such as shape and size (aspect ratio) have a vital part in deciding the behavior of the composite material when it is subjected to impact loading. Generally, increase in aspect ratio results in increased energy absorption capability which further results in higher fracture toughness. But investigating the fracture toughness of particle reinforced composites experimentally for varying aspect ratio is cumbersome. Therefore, the presented work focuses on investigating the applicability of K- Nearest Neighbor (KNN) algorithm in predicting the fracture toughness of polymer composites reinforced with silica particles. The aim of this work is to predict the results with utmost accuracy with limited experimentation. The current approach utilizes four model parameters viz. aspect ratio, time, volume fraction of the fillers and elastic modulus to predict the Stress Intensity Factor (SIF) which directly gives the measure of fracture toughness. KNN has been implemented to predict the fracture behavior of the composite corresponding to different values of aspect ratios. The proposed model predicts the results with an accuracy of ~96%, as around 4% was found to be the mean absolute percentage error. This work is an effort to expand the scope of applying the machine learning technique in the field of material and design for the structural parts subjected to impact loading situations.