Fluid velocity and mass ratio identification of piezoelectric nanotube conveying fluid using inverse analysis

In this paper, an inverse problem is developed to identify the fluid velocity and mass ratio of a piezoelectric nanotube conveying fluid flow. The natural frequencies of a piezoelectric nanotube are measured through a model-based approach and used to predict those unknown parameters. The numerical Levenberg–Marquardt and artificial neural network methods are employed as inverse tools for this purpose. The Eringen’s nonlocal elasticity theory with a combination of the Euler–Bernoulli beam theory is used to derive the governing equation of motion. The well-known Galerkin method is applied to extract the required natural frequencies. The presented inverse approaches are utilized for both noise-free and noisy data. The results show the high capability of the neural network approach in the identification of both fluid velocity and mass ratio of a piezoelectric nanotube, especially for noisy data.