Gaussian-Based Machine Learning Algorithm for the Design and Characterization of a Porous Meta-Material for Acoustic Applications

Abstract

The scope of this work is to consolidate research dealing with the vibroacoustics of periodic media. This investigation aims at developing and validating tools for the design and characterization of global vibroacoustic treatments based on foam cores with embedded periodic patterns, which allow passive control of acoustic paths in layered concepts. Firstly, a numerical test campaign is carried out by considering some perfectly rigid inclusions in a 3D-modeled porous structure; this causes the excitation of additional acoustic modes due to the periodic nature of the meta-core itself. Then, through the use of the Delany–Bazley–Miki equivalent fluid model, some design guidelines are provided in order to predict several possible sets of characteristic parameters (that is unit cell dimension and foam airflow resistivity) that, constrained by the imposition of the total thickness of the acoustic package, may satisfy the target functions (namely, the frequency at which the first Transmission Loss (TL) peak appears, together with its amplitude). Furthermore, when the Johnson–Champoux–Allard model is considered, a characterization task is performed, since the meta-material description is used in order to determine its response in terms of resonance frequency and the TL increase at such a frequency. Results are obtained through the implementation of machine learning algorithms, which may constitute a good basis in order to perform preliminary design considerations that could be interesting for further generalizations.

A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic

“…Zhang et al [166] used RBFbased surrogate to replace the modal and vibroacoustic coupling simulation of the volute case of a centrifugal fan in the optimization of the thickness parameters of the geometry to decrease the radiated sound power and the total mass. Transmission Loss (TL) optimization using Gaussian Process surrogates was performed for intake systems [167] and for meta-material properties [168]. [169] carried out Bandgap optimization of meta-materials supported by RBF surrogate.…”

Density Functional Theory-Assisted Active Learning-Driven Organic Ligand Design for CsPbBr3 Nanocrystals

“…In recent years, machine learning tools have been utilized in materials science to mine regulations in known data and make predictions. In the case of dealing with massive search space and undergoing relatively high data acquisition costs, active learning has been recognized as a promising strategy to accelerate the optimization process in machine-learning model training, drug design, functional material discovery, etc. − High efficiency was demonstrated by the active learning method in the example of the discovery of new composition of BaTiO family within only five iterations. Wen et al accelerated the high-entropy alloys (HEAs) composition design active-learning process by introducing descriptors exploiting knowledge associated with HEAs and proposed HEAs with hardness 10% higher than the best value in the initial data set.…”

Identification of Key Factors Influencing Sound Insulation Performance of High-Speed Train Composite Floor Based on Machine Learning

“…Zhou et al [15] proposed a fault isolation method based on the k-nearest neighbor rules to identify the fault causes of industrial processes with nonlinear, multimode, and non-Gaussian distributed data, which could isolate multiple sensor faults under relatively loose conditions. Casaburo et al [16] applied a Gaussian machine-learning algorithm to the structural design and characterization of porous acoustic metamaterials and achieved good results. Eddin et al [17] used an artificial neural network method to evaluate the influence of materials, thickness, density, size, and quality of light wood flooring on sound insulation, and the prediction error of 250~1000 Hz was no more than 2 dB.…”