International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 09 Issue: 07 | July 2022
p-ISSN: 2395-0072
www.irjet.net
METHOD FOR OPTIMIZATION OF COMPOSITE SANDWICH STRUCTURE USING ARTIFICIAL NEURAL NETWORK. Rahul Sanjay Autade Student, dept. of Mechanical Engineering, Pimpri Chinchwad College Of Engineering, Maharashtra, India. ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - laminates are utilized in a variety of fields,
be determined in order to determine the weakest link in a sandwich structure. By reinforcing the weakest link, the overall panel strength can be increased. For the prediction of failure mode, researchers drew failure maps[6] based on large sample testing; however, these failure maps vary for different materials, and determining their boundaries requires a large number of sample tests.
including naval, aeronautics, automobiles, etc. The objective of the panel's design is to maximize flexural strength, energy absorption, and flexural rigidity while minimizing weight. However, finding the optimum configuration of layer thickness and core thickness requires extensive destructive testing. Using a neural network, this study established the relationship between the configuration of laminates, such as layer thickness, core thickness, weight with the flexural strength, and the flexural rigidity of laminates. For this study, training data is collected via finite element analysis (FEA) of three-point bending tests of laminates with varying core and layer thicknesses and then utilized to train a neural network. This FEA study of a three-point bending test is conducted using the academic software ANSYS. An artificial neural network is used to perform regression. After hyperparameter optimization, 256 points of ANSYS data are used to train an artificial neural network model with an accuracy of 95.29 percent for deflection prediction and 95.05 percent for force prediction. This will decrease the amount of computation required to determine the optimal configuration after the neural network is trained.
In addition, these maps do not account for the panel weight parameter. The 3-point bending test of CFRP with an aluminium core is studied using the pre-post module and the inbuilt material library in the ANSYS student edition. Maximum failure stress can be determined using Maximum principal stress, maximum principal strain, tsai wu [7], tsai hill [8], and Hoffman theory [9]. Failure load and failure modes can be determined using inverse reserve factor (IRF) [10] in ANSYS. The dimensions of the monocoque construction of the test rig are fixed in formula student[11]. This type of intricate structure necessitates a great deal of computer power, and the outcomes vary depending on the production procedure. To circumvent this, an artificial neural network (ANN) is implemented to forecast sandwich structure attributes.
Key Words: composites sandwich, carbon fibre, artificial neural network, multi-objective optimization, design optimization.
ANN is preferred to linear regression for prediction due to its superior performance[12], [13]. ANN is motivated by biological neural network[14]. Applications of ANN linear regression includes diesel pollution prediction[15], GDP growth prediction[16], stock market prediction[17], and computer vision[18]. Afterward, acquired data from ANSYS is utilised to train a model of an artificial neural network. With feed-forward architecture, a small number of hidden layers is sufficient to create multivariate polynomial regression for the model. Finally, the prediction with 95.45% accuracy is achieved.
1.INTRODUCTION Sandwich structures consist of a thin, high-strength outer layer and a low-strength inner core similar to the I-beam structure. It provides greater bending strength and stiffness with less weight. Sandwich structures are utilized in a variety of applications, including aircraft wings[1] , electric vehicles [2], monocoque structures, rooftops[3], and bridges[4] . For fibre reinforced composite sandwich panel manufacturing carbon fibre, glass fibre, Kevlar fibre, and natural fibres are used with PVC foam, balsa wood, and aluminium honeycomb core. In this analysis, carbon fibre and aluminium honeycomb structures are studied.
2.PROBLEM DEFINITION 2.1 Material characteristics of the sandwich panel
Face wrinkling, core shear, and face yielding, Intra-cell buckling, as well as the face indentation[5], are the primary failure modes of a sandwich panel in three-point bending. A three-point bending test is used to analyse sandwich panel for the above criteria. Failure mode must
© 2022, IRJET
|
Impact Factor value: 7.529
With a fibre-to-resin ratio of 60:40, carbon fibre is chosen as the reinforcing fibre and epoxy resin as the matrix[10]. The composite properties Pc are generated from the individual fibre and matrix properties Pf and Pm, respectively.
|
ISO 9001:2008 Certified Journal
|
Page 1728