<p style="text-align: justify">Engineering structures with piezoelectric actuators and sensors proved great improvement in vibration and noise reduction. In the open literature, the effect of the piezoelectric patch dimension on the dynamic responses is usually ignored due to the complicity of the dynamic model. In this paper, an artificial neural network (ANN) model was employed to explore the piezoelectric patch size and thickness’s effect on the first order natural frequency and displacement amplitude of a plate. First, the Hamiltonian principle is used to derive the constitutive equations of the movement of the rectangular piezoelectric thin plate with bonded piezoelectric sheets on the surface and the related natural and geometric boundary conditions. A common method for solving PDE (representing the dynamics of the plate) is to use the representation of the PDE obtained by a simplification process from a finite set of ordinary differential equations. In comparison, the finite element method (FEM) defines a function on the element domain of simple geometric shapes without considering the complex boundary conditions of the entire domain. Then use COMSOL to model and simulate the piezoelectric thin plate system. With the finite element method (FEM), a rectangular plate actuated by a piezoelectric patch was analyzed with various patch sizes. The FEM data was later used to build an ANN model. The dynamic response of the plate was predicted by the ANN model and validated with FEM in terms of first order natural frequency and displacement amplitude. After that, the effectiveness of the model obtained was studied by comparing the first-order natural frequency and displacement amplitude of the plate predicted by the artificial neural network model with the values obtained using the finite element method. After verifying the model, the relationship between the output parameters and the key parameters such as the side length, thickness, area, and volume of the piezoelectric patch is discussed by changing the parameters of the input layer. Results from case studies showed that with the input of patch length, width and thickness, the artificial neural network model can accurately predict both natural frequency and displacement amplitude. When the input of the artificial neural network model was simplified to patch size and thickness or the volume of the patch, the accuracy became worse and worse. The influence of the patch size and thickness on the first order natural frequency was coupled and the maximal and minimal values were predicted based on the artificial neural network model.</p>

Size Effect of a Piezoelectric Patch on a Rectangular Plate With the Neural Network Model

Paper Proceedings: https://asmedigitalcollection.asme.org/IMECE/IMECE2021/volume/85543

ASME 2021 International Mechanical Engineering Congress and Exposition (IMECE2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.