Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Data-Driven Modeling of a Controlled Orthotropic Plate Using Machine Learning

Yongho Kim, Alexander Zuyev, Francesco Pellicano, Antonio Zippo

Abstract

We study the problem of learning the input-output map of a controlled vibrating plate with a composite structure from experimental measurements. Analytical modeling of this control system faces challenges due to the essential orthotropy and unknown damping characteristics of the material. Surrogate models based on linear regression, multilayer perceptrons, and gated recurrent units are constructed from the available sampled data. Through comparative analysis, we show that the multilayer perceptron model provides an acceptable approximation of this dynamical system, capturing the potentially nonlinear phenomena in its input-output behavior.

Data-Driven Modeling of a Controlled Orthotropic Plate Using Machine Learning

Abstract

We study the problem of learning the input-output map of a controlled vibrating plate with a composite structure from experimental measurements. Analytical modeling of this control system faces challenges due to the essential orthotropy and unknown damping characteristics of the material. Surrogate models based on linear regression, multilayer perceptrons, and gated recurrent units are constructed from the available sampled data. Through comparative analysis, we show that the multilayer perceptron model provides an acceptable approximation of this dynamical system, capturing the potentially nonlinear phenomena in its input-output behavior.
Paper Structure (6 sections, 17 equations, 4 figures, 1 table)

This paper contains 6 sections, 17 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Experimental Setup
  3. Governing Equations of the Orthotropic Plate
  4. Surrogate Modeling
  5. Numerical Experiments
  6. Conclusion

Figures (4)

  • Figure 1: Controlled orthotropic plate at the Enzo Ferrari Department of Engineering, University of Modena and Reggio Emilia.
  • Figure 2: Time series dataset with input $u(t)$ and output $y(t)$, sampled over time $t$. Only the data within the yellow-shaded region ($t\in[0.64\,s,16.31\,s]$) are used for training, validation, and testing models.
  • Figure 3: $R^2$ scores of pretrained MLPs \ref{['MLP']}: Solid lines represent the mean score $\mu$, and the shaded regions indicate the statistical uncertainty measured using the standard deviation $\sigma$, i.e., the interval $(\mu-\sigma,\mu+\sigma)$.
  • Figure 4: Scatter plots of predicted versus reference outputs for the LR \ref{['LR']}, MLP \ref{['MLP']}, and GRU \ref{['GRU_input']}--\ref{['GRU_output']} models.