An adaptive neuro fuzzy inference system model for studying free in plane and out of plane vibration behavior of curved beams. (January 2023)

• Record Type: Journal Article
• Authors: Mohanty, Nupur; Mishra, Uttam Kumar; Sahu, Shishir Kumar
• Is Part Of: Structures. Volume 47(2023)
• Page Start: 1836
• Page End: 1845
• Publication Date: 2023-01
• Subjects: Adaptive neuro-fuzzy inference system -- Out of plane vibration -- In-plane vibration -- Curved beam -- Natural frequency -- Sensitivity analysis; Structural engineering -- Periodicals; 624.1
• DOI: 10.1016/j.istruc.2022.12.021
• Languages: English
• ISSNs: 2352-0124

Abstract

Abstract: The current study examines the free vibration behavior of curved beams in detail. Basic, lightweight curved beams are used in many different engineering projects. Therefore, it is very important to study their dynamic behavior extensively. Hence, in this study, numerical analysis on free in-plane and out-of-plane vibration of curved beams is carried out using finite element modeling software ANSYS, and experimental analysis was conducted using Fast Fourier Transform (FFT) spectrum analyzer for validation of numerical results. Adaptive neuro-fuzzy inference system (ANFIS) models are developed using 384 numbers of datasets that are procured from numerical investigations. The input parameters considered are cross-sectional area, radius of curvature, curvature angle, support conditions, and mode of vibration. An empirical equation is derived for estimating natural frequencies. Different statistical indices, such as the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE), is used to evaluate the performance of the input parameters. Sensitivity analysis is used to spot the input parameters that have the greatest influence on the natural frequency of curved beams and rank them in importance.