Topic of Research Seminar: Prediction of Low Velocity Impact Performance of Carbon/Flax Bio-Hybrid Composite using Experimental and Neural Network Approaches

Abstract: In this study, the impact behavior of carbon/flax bio-hybrid composite laminates at low velocities was examined in relation to stacking configurations and fiber hybridization. The methodology was developed based on experimental testing and then utilizing an artificial neural network-based machine learning regression model. Vacuum bagging was used to create five distinct stacking configurations of carbon/flax material, which were then exposed to low-velocity impact with energies that varied from 15J to 90J. Data in the form of peak impact force was recorded for each stacking configuration. It was found that the performance was improved in a symmetric design where the flax layers were evenly distributed across the thickness. Furthermore, two machine learning approaches—deep neural network (DNN) with Adam optimizer and DNN with stochastic gradient descent (SGD)—were applied. The performance metrics employed to assess the performance were the coefficient of determination (R2), mean square error (MSE), and mean absolute error (MAE). DNN-SGD, which has three hidden layers and 80 neurons in each, was the model that performed the best at predicting the peak impact force. The highest correlation and the smallest MSE and MAE values were attained using the DNN-SGD model. The developed methodology and the model serve as powerful tools to predict the mechanical properties of bio-hybrid composite laminates, utilizing minimal resources and saving time as well.

Subject field of Topic: Application of Machine Learning in Mechanics of Composite Materials

Name of Speaker: Manzar Masud

Professional Rank of Speaker: PhD Scholar

University Email of Speaker: [email protected]

Affiliation of Speaker: Computational Mechanics Group, School of Mechanical and Manufacturing Engineering, NUST

Date and Venue: 10th Oct 2024, from 1600-1700 hrs, at School of Mechanical and Manufacturing Engineering (SMME), NUST Islamabad