
An Unconventional Approach for Analyzing the Mechanical Properties of Natural Fiber Composite Using Convolutional Neural Network
Author(s) -
G. Ramkumar,
Satyajeet Sahoo,
G Anitha,
S. Ramesh,
P. Nirmala,
M. Tamilselvi,
Ram Subbiah,
S. Rajkumar
Publication year - 2021
Publication title -
advances in materials science and engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.356
H-Index - 42
eISSN - 1687-8442
pISSN - 1687-8434
DOI - 10.1155/2021/5450935
Subject(s) - materials science , composite material , finite element method , ultimate tensile strength , convolutional neural network , bending , composite number , fiber , artificial neural network , computation , modulus , natural fiber , rigidity (electromagnetism) , structural engineering , computer science , artificial intelligence , algorithm , engineering
Over the past few years, natural fiber composites have been a strategy of rapid growth. The computational methods have become a significant tool for many researchers to design and analyze the mechanical properties of these composites. The mechanical properties such as rigidity, effects, bending, and tensile testing are carried out on natural fiber composites. The natural fiber composites were modeled by using some of the computation techniques. The developed convolutional neural network (CNN) is used to accurately predict the mechanical properties of these composites. The ground-truth information is used for the training process attained from the finite element analyses below the plane stress statement. After completion of the training process, the developed design is authorized using the invisible data through the training. The optimum microstructural model is identified by a developed model embedded with a genetic algorithm (GA) optimizer. The optimizer converges to conformations with highly enhanced properties. The GA optimizer is used to improve the mechanical properties to have the soft elements in the area adjacent to the tip of the crack.