IMPACT LOADING ANALYSIS OF PARTICULATE POLYMER COMPOSITES WITH AN EFFICIENT HYBRID MACHINE LEARNING APPROACH

Aug 5, 2026

Upload by Anda

Fracture behaviour of particle polymer composites under impact loading is modeled using a hybrid machine learning strategy termed Hybrid Artificial Neural Networks and Random Forest (HANN-RF), targeting mode-I cracking. A dataset is constructed with compositional properties and impact-loading scenario inputs to relate variables to crack initiation histories, fracture toughness, and stress intensity factor (SIF) intensity. The HANN-RF scheme integrates Random Forest and an Artificial Neural Network to improve robustness and predictive accuracy. Evaluation uses MAE, MAPE and accuracy metrics, showing effective forecasting of mode-I fracture response and providing insight into resilience and longevity for engineering applications.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages6

Reading Time15 min

AccessFree to download

Abstract

Introduction

Mode-I fracture and key metrics

Factors affecting fracture behaviour

Experimental and computational approaches

Motivation and contribution

Related Works

Dimensional analysis and ML for glass-filled epoxy

Neural-network prediction under impact loading

Vol. 05, No. S1 (2023) 97-102, doi: 10.24874/PES.SI.01.012 Proceedings on Engineering Sciences [www.pesjournal.net](www.pesjournal.net) IMPACT LOADING ANALYSIS OF PARTICULATE POLYMER COMPOSITES WITH AN EFFICIENT HYBRID MACHINE LEARNING APPROACH Soumya A. K.1 Ritu Shree Received 29.04.2023. Anu Sharma Accepted 30.06.2023. Keywords: Particulate polymer composites, machine learning, hybrid artificial neural network, and random forest (HANN-RF). A B S T R A C T The fracture behaviour of particle composites made of polymers under impact loading is predicted in this research using a hybrid machine learning approach dubbed Hybrid Articial Neural Networks and Random Forest (HANN-RF), with a focus on mode-I fracture. The goal of the study is to create a model for prediction that accurately links input variables to histories of crack initiation, fracture toughness, and the intensity of the stress factor (SIF). A full dataset is created, with inputs for the composites' compositional properties and impact loading scenarios. The HANN-RF model combines a Random Forest (RF) method and anANN (Artificial Neural Network) in order to improve robustness and accuracy in forecasting. Metrics like MAE, MAPE for short, and accuracy are used in model evaluation. The outcomes show that the HANN-RF technique successfully predicts and forecasts mode-I fracture behaviour, offering insightful information for evaluating the effect on resilience and longevity of particle polymer composites in a variety of applications. © 2023 Published by Faculty of Engineering 1. INTRODUCTION A family of materials known as "particulate polymer composites" consists of an epoxy matrix with discrete particles (Kushvaha and Sharma 2021) . These composites have distinct mechanical characteristics, making them appealing for various uses in industries like airplanes, cars, and construction. For the design of particulate polymer composites to be optimized and for their structural integrity to be guaranteed under varied loading circumstances, it is essential to understand the fracture behavior of these materials. When a crack spreads perpendicular to the applied tensile tension, it is referred to as a mode-I fracture, also known as an opening or tensile mode of fracture (Karthik et al., 2023) . It is crucial to examine their mode-I fracture behavior to determine how resistant particulate polymer composites are to crack initiation, propagation, and ultimate failure. Important metrics, including the fracture toughness, crack propagation rate, and energy absorption capacity, characterize these composites' mode-I fracture behavior. The type, size, and volume percent of the reinforcement particles and the make-up of the polymer matrix influence the way fracturing in particle polymer composites behave (Ganguly 2022) . The interactions between the particles and the matrix and the interactions between individual particles significantly affect the mechanisms leading to fracture and the material's overall fracture toughness. Various experimental and computational methodologies are used to estimate how particle polymer composites may shatter in mode-I (Kushvaha et al. , 2020) . The crack initiation, propagation, and particle-matrix interactions can be understood using experimental methods like tensile testing, fracture toughness testing, and microscope analysis. The understanding of fracture mechanisms at various length scales and the forecasting of the fracture response of the composite material are each assisted by computational modeling methodologies like finite element analysis and molecular dynamics simulations. In recent years, significant progress has been made in creating advanced particulate polymer composites with improved fracture resistance (Mousavi et al. , 2022) . Researchers want to increase the composite's fracture toughness and damage tolerance by customizing its composition, morphology, and interface characteristics. Enhancing the composite

FAQs

What loading condition and fracture mode does the study focus on?

The study predicts fracture behaviour of particulate polymer composites under impact loading, focusing on mode-I fracture (opening/tensile mode).

What machine learning model is proposed in the paper?

It proposes the HANN-RF approach, combining Random Forest with an Artificial Neural Network to improve robustness and forecasting accuracy.

Which outcomes does the model aim to predict?

The model links input variables to histories of crack initiation, fracture toughness, and the intensity of the stress intensity factor (SIF) for mode-I behaviour.

Aug 5, 2026

Upload by Anda