Back to Search
Start Over
Nonlinear size-dependent aerodynamics of axially reinforced doubly curved micropanel with GPLs: Application of innovative artificial neural network model.
- Source :
-
Mechanics of Advanced Materials & Structures . Sep2023, p1-25. 25p. 12 Illustrations, 4 Charts. - Publication Year :
- 2023
-
Abstract
- Abstract Recent years have seen significant research on oscillations in aircraft structures. A self-excited oscillation known as flutter is known to wear down aircraft equipment. So, in this work, the graphene nanoplatelets reinforced composite (GPLRC) micropanel’s nonlinear aerodynamics are modeled in this paper, and the nonlinear aerodynamics properties are validated using an artificial neural network technique. The axial direction and the material characteristics of the current system are graded. The relationship between the input layers of composite weight fraction, mode number, and slenderness ratio and the output layer of nonlinear vibrations derived from mathematical simulation has been estimated using an artificial neural network model. As a training algorithm, Levenberg–Marquardt back-propagation is employed. This study is new in that it attempts for the first time to estimate the nonlinear vibration properties of micropanels built of axially graded GPLRC material using the aforementioned input layer. Without the need to solve any differential equations or go through time-consuming experimental procedures, the suggested artificial neural network model can forecast linear or nonlinear natural frequencies. The findings demonstrate that axially graded GPLRC micropanel linear/nonlinear vibration problems can be effectively addressed using artificial intelligence techniques. Future vibration analyses of the microstructures for engineering reasons can use the provided mode. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 15376494
- Database :
- Academic Search Index
- Journal :
- Mechanics of Advanced Materials & Structures
- Publication Type :
- Academic Journal
- Accession number :
- 172273894
- Full Text :
- https://doi.org/10.1080/15376494.2023.2254760