Polynomial Neural Network Based Stochastic Natural Frequency Analysis of Functionally Graded Plates
The present article deals with the stochastic approach for natural frequency (NF) analysis of functionally graded (FG) plates by employing polynomial neural network (PNN) surrogate model combined with finite element (FE) method. The surrogate model for NF
- PDF / 444,565 Bytes
- 8 Pages / 439.37 x 666.142 pts Page_size
- 67 Downloads / 210 Views
Abstract The present article deals with the stochastic approach for natural frequency (NF) analysis of functionally graded (FG) plates by employing polynomial neural network (PNN) surrogate model combined with finite element (FE) method. The surrogate model for NF analysis of FG plates is validated with the original FE method. Both individual and mixed variation of material properties are taken into account. The present PNN model significantly rises the computational efficiency, and the computational cost decreased in comparison to Monte Carlo Simulation (MCS).
1 Introduction In the recent era, plenty of applications of advanced materials such as functionally graded material (FGM) structures are gaining popularity in the field of aerospace, automobile, medical optoelectronics, and many other engineering applications due to high stiffness [1]. FGM is a major type of composite material in which microstructure is varying continuously throughout the section [2]. In FGM, there is no internal boundary so stress concentration is negligible [3, 4]. FGM is the new composite materials composed of two different materials to obtain the functional requirements. The FGM is inhomogeneous composite materials with property gradient depending upon the chemical composition, atomic order, and microstructure. There are two materials namely metal and ceramic, which are smoothly and continuously distributed throughout the volume of the plate. The mechanical properties of FGM are better than the laminated composite materials due to absence of interlaminate joint, internal stresses, delamination, improper bonding. The FGM have good thermal resistance properties provided by ceramic material, while high mechanical strength is given by metal constitute. Some researchers worked on NF analysis of different materials
P. K. Karsh (B) · A. Kumar · S. Dey National Institute of Technology, Silchar, India e-mail: [email protected] Parul Institute of Engineering & Technology, Parul University, Vadodara, India © Springer Nature Singapore Pte Ltd. 2021 S. Dutta et al. (eds.), Advances in Structural Vibration, Lecture Notes in Mechanical Engineering, https://doi.org/10.1007/978-981-15-5862-7_31
379
380
P. K. Karsh et al.
using different models. Escobedo-Trujillo et al. [5], presented a hybrid model integrates to increase the coefficient of performance forecasting for solar refrigeration system. Zjavka [6] have used polynomial neural networks for forecasting wind speed in order to improve forecasting. Han et al. [7] developed a PNN model for sequential processes of silicon solar cell fabrication. Fazel Zarandi et al. [8] proposed a fuzzy PNN to forecasting the strength of concrete. Zhang et al. [9] used single-output Chebyshev PNN for pattern classification. Haiyan et al. [10] introduced orthogonal polynomial neural networks for modeling of polymer molecular weight distribution. Roha et al. [11] introduces a new method for designing of fuzzy radial basis function approach. Dorn et al. [12] used the PNN for the forecasting of approximate threed
Data Loading...
