Open AccessPrediction of Core Shear Strength in Sandwich Composites using Deep Learning and Support Vector Regression
Author(s) -
P J Antony,
M R Prajna,
N A Jnanesh
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.a1971.078219
Subject(s) - composite material , materials science , core (optical fiber) , shear (geology) , flexural strength , universal testing machine , shear strength (soil) , test set , fiber , direct shear test , structural engineering , artificial intelligence , computer science , engineering , ultimate tensile strength , environmental science , soil science , soil water
In the present study, machine learning approaches have been developed to predict the 180 days aged core shear strength of sandwich composites. The characteristics of the sandwich composites depends on the number of factors namely fibre type i.e., Chopped strand Mat, Stitched, Chopped strand Mat and Woven Roving, core density, bond between the core and the face sheets and the ability to bear the load in flexural mode. In the current approach deep learning and SVR models were worked out by taking on six different parameters namely foam density, aging temperature and variety of fiber types as input variables. For each set of these input variables, the 180 days aged shear strength of sandwich composites with a test frequency of 30 days was determined. The paper aims at predicting the core shear strength value of stitch bond sandwich composites using other three aforementioned fibers. To create the model and confirm the accuracy of the algorithm training and test data are considered. The results obtained revealed that the deep learning model develo ped provides better predictive ability than the model of SVR.