Antonio Zippo | Searcharxiv

arXiv2026

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

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.

math.OC↗

arXiv2024

Dynamic Modelling of a Controlled Orthotropic Plate: Analytic and Data-Driven Approaches in the Frequency Domain

This paper is devoted to the mathematical modelling of a vibrating orthotropic plate equipped with a laminated piezosensor, under the influence of a lumped force actuation. We employ the Kirchhoff plate theory to derive the corresponding partial differential equation, assuming free boundary conditions. Analytical solutions for this boundary value problem are explored in the form of series expansions, using products of Krylov functions. Utilizing Galerkin's method, this mathematical model is transformed into an infinite-dimensional control system characterized by modal coordinates. The transfer function of such a system is explicitly evaluated in the single-input single-output case. The computation of coefficients for finite-dimensional approximate systems is formalized in an algorithm with an arbitrary number of degrees of freedom. Our numerical study confirms that the modeled input-output behavior shows acceptable agreement over the given frequency range.

math.OC↗