Loading...
Send to Friend
 Bookmark
 Review List
  1. Machine learning, analytical, and numerical techniques for vibration analysis of submerged Porous functional gradient piezoelectric microbeams with movable supports (Property)
  2. Simple search
  3. Search result
Machine learning, analytical, and numerical techniques for vibration analysis of submerged Porous functional gradient piezoelectric microbeams with movable supports
211 viewed

Machine learning, analytical, and numerical techniques for vibration analysis of submerged Porous functional gradient piezoelectric microbeams with movable supports

Ebrahimi-Mamaghani, A

Machine learning, analytical, and numerical techniques for vibration analysis of submerged Porous functional gradient piezoelectric microbeams with movable supports

Ebrahimi-Mamaghani, A ; Sharif University of Technology | 2024

211 Viewed
  1. Type of Document: Article
  2. DOI: 10.1142/S0219455426500549
  3. Publisher: World Scientific , 2024
  4. Abstract:
  5. This research numerically and analytically examines the dynamics of underwater movable porous functional gradient (FG) microsize beams integrated with a piezoelectric layer. Also, the efficiency and accuracy of support vector machine (SVM) techniques in the vibration prediction of the microbeam are assessed. The dynamical simulation is conducted by considering the assumptions of Rayleigh beam theory, different porosity distribution models, nonlinear and linear stress-temperature relationships, and modified couple stress theory (MCST). The eigenvalues of the system, critical temperature increment, and critical speed of the microbeam are computed. Comparative studies are carried out, frequency analyses are performed, and stability diagrams are drawn. The impacts of microbeam geometry, fluid mass ratio, piezoelectric voltage, and axial force on stability behavior in variable complex environmental conditions are parametrically inspected. The outcomes revealed that the smaller the contribution of voids on the outer surface of the microbeam, the better the microbeam stability. It is understood that among the utilized regression-based SVMs, the quadratic polynomial and medium Gaussian kernel models have the highest performance and speed, respectively. These research outcomes will be advantageous for designing the next generation of targeted drug delivery devices. © 2026 World Scientific Publishing Company
  6. Keywords:
  7. Hydro-hygro-magneto-electro-thermo-elastic response ; Machine learning ; Movable submerged microstructures ; Porous FG materials ; Vibration and stability ; Polynomial regression ; Support vector machines ; Vibration analysis
  8. Source: International Journal of Structural Stability and Dynamics ; 2024 ; 02194554 (ISSN)
  9. URL: https://www.worldscientific.com/doi/10.1142/S0219455426500549