Dynamics of nonlinear cantilever piezoelectric-mechanical system: An intelligent computational approach

In this study, a novel application of intelligent computing by the exploitation of a supervised neural networks (SNNs) optimized with the Levenberg-Marquardt method (LMM) is presented to study the dynamics of nonlinear cantilever piezoelectric-mechanical system (NCPMS) represented with a second-order system of ordinary differential equation. The dataset for NCPMS is created using Adams numerical solver for input and target parameters for continuous mapping of SNN model of the system. The training, testing, and validation processes are exploited for SNNs models learned by LMM to determine the solution of NCPMS for different scenarios based on variation of amplitude and phase of cantilever frequency for small and large-time domains while keeping the tip mass, beam length, mass density, capacitance and load resistance constant. The performance of SNN to solve NCPMS is substantiated on measurement of achieved accuracy through mean squared error, error histogram illustrations and regression analyzes.(c) 2022 International Association for Mathematics and Computers in Simulation (IMACS). Published by Elsevier B.V. All rights reserved.