Development of an App for analyzing and monitoring non-linear fluid-induced vibration of nanotube using analytical and machine learning approaches

This paper investigates the dynamic response and Single-walled carbon nanotube’s vibrational properties under varying conditions. This study uses a blend of theoretical modeling and empirical analysis to investigate the effects of different parameters on the behavior. The Galerkin method was used to derive and simplify the nonlinear Partial Differential Equation that represented the motion of the Single-walled carbon nanotube into an Ordinary Differential Equation. The Differential Transform Method is then used to solve the resulting Ordinary Differential Equation. The application of Cosine After-Treatment and Sine After-Treatment techniques guarantees the validity of the solution over longer time domains. The impacts of nonlocal elasticity, nonlinear foundation parameters, and mode number on the system’s response are thoroughly examined. Furthermore, this study integrates machine learning to enhance the analysis and visualization of the nanotube's deflection and vibration effects. Simulated data are used to train various machine learning models using Extreme Gradient Boosting (XGBoost). The study also includes the development of a mobile application to provide an interactive platform for visualizing the nanotube's dynamic response, making the findings accessible to a broader audience. The results are relevant to nano-electromechanical systems, nanofluidic transport, nanosensors, energy harvesting devices, and medicinal systems where vibrational stability and dependability are essential. This subsequently advances the knowledge of Single-walled carbon nanotube’s behavior and lay the groundwork for further studies in this field.