Eventos Anais de eventos
COBEM 2019
25th International Congress of Mechanical Engineering
Neural Network and Shunt Control for Beam Structure: Multimodal Approach
Submission Author:
Venicio Silva Araujo , MT , Brazil
Co-Authors:
Venicio Silva Araujo, Guilherme Silva Prado, Heinsten Frederich Leal dos Santos
Presenter: Venicio Silva Araujo
doi://10.26678/ABCM.COBEM2019.COB2019-1658
Abstract
Piezoelectric materials have been extensively studied in recent years for the development of electromechanical harvesting and damping devices. Usually linked to a structure, these kinds of materials convert kinetic energy into electric energy, and your electronic parameters interact directly to the vibrations of the system they are coupled on. Therefore, this work aims at the usage of artificial neural network techniques in the implement of a multimodal shunt control in a structural set of a cantilever beam coupled to a piezoelectric layer in the piezo-beam configuration. For the architecture of the neural network was used a software with finite element model implemented, and efficiency analysis was done by comparing the algorithm’s response and the peaks of the beam for the first two natural vibration modes to piezoeletrics of 10mm, 25mm and 50mm of length. The results shows that the neural network provides an average gain superior than 23dB for both modes, in an average time of 170 seconds, defining a range of damping for the piezo layer of 5 to 45mm from the crimp, and respectively showing the 10mm piezoeletric as the best in damping per area.
Keywords
Vibrations Controls, Neural Network, Smart Structures, Shunt Control, cantilever-beam
