ANN based optimization of nano-beam oscillations with intermolecular forces and geometric nonlinearity

Abstract

In this study, we investigate the effect of Van der Waals and Casimir forces on the mathematical model of nano-electromechanical systems (NEMS) such as nano-beam actuators that contain cantilever and double cantilever beams. The singular nonlinear boundary value problem governing the beam-type actuators, including geometric nonlinearity is solved by using an intelligent strength of feedforward artificial neural networks (ANNs) and hybridization of optimization algorithms such as arithmetic optimization algorithm (AOA) and active set algorithm (ASA). The proposed ANN-AOA-AS algorithm is employed to quantify the effect of changes in applied voltage, dispersion forces, geometric nonlinearity parameters, and initial axial strain on the deflection of the beam. Furthermore, to validate the results obtained by the proposed algorithm, statistical analyses are conducted to compare the approximate solutions with state-of-the-art methodologies available in the latest literature. In addition, performance indicators are defined such as mean square error (MSE), Nash–Sutcliffe efficiency (NSE), mean absolute deviations (MAD), root mean square error (RMSE), and Error in Nash–Sutcliffe efficiency (ENSE) to study the accuracy and efficiency of the solutions. The results show that these indicators’ mean percentage values lie around $10^{-4}$ to $10^{-6}$ which reflects the perfect modeling of the approximate solutions.