A machine learning accelerated inverse design of underwater acoustic polyurethane coatings

Abstract

Here we propose a detailed protocol to enable an accelerated inverse design of acoustic coatings for underwater sound attenuation application by coupling Machine Learning and an optimization algorithm with Finite Element Models (FEM). The FEMs were developed to obtain the realistic performance of the polyurethane (PU) acoustic coatings with embedded cylindrical voids. The frequency dependent viscoelasticity of PU matrix is considered in FEM models to substantiate the impact on absorption peak associated with the embedded cylinders at low frequencies. This has been often ignored in previous studies of underwater acoustic coatings, where usually a constant frequency-independent complex modulus was used for the polymer matrix. The key highlight of the proposed optimization framework for the inverse design lies in its potential to tackle the computational hurdles of the FEM when calculating the true objective function. This is done by replacing the FEM with an efficiently computable surrogate model developed through a Deep Neural Network. This enhances the speed of predicting the absorption coefficient by a factor of $$4.5 \times 10^3$$ 4.5 × 10 3 compared to FEM model and is capable of rapidly providing a well-performing, sub-optimal solution in an efficient way. A significant, broadband, low-frequency attenuation is achieved by optimally configuring the layers of cylindrical voids. This is accomplished by accommodating attenuation mechanisms, including Fabry–P$$\acute{e}$$ e ´ rot resonance and Bragg scattering of the layers of voids. Furthermore, the proposed protocol enables the inverse and targeted design of underwater acoustic coatings through accelerating the exploration of the vast design space compared to time-consuming and resource-intensive conventional trial-and-error forward approaches.

A machine learning enabled hybrid optimization framework for efficient coarse-graining of a model polymer

“…Therefore, we avoid the need for a large number of simulations, where data are generally not reused. Thus, DNNs are used as surrogate models, which addresses the re-usability issue of the data 59 . Our focus is on the working mechanism of the framework by demonstrating the ability of the CG model to make accurate predictions, and the validation of the trained model.…”

AI-Based Metamaterial Design

“…Some groups have combined ML algorithms with NNs to have an accelerated design timeline. Accelerated inverse design of acoustic coating was proposed by Weeratunge et al for underwater acoustic absorbers . Polyurethane (PU) acoustic coating (Figure A) with embedded cylindrical voids was designed by considering the frequency-dependent viscoelasticity of PU.…”

“…Accelerated inverse design of acoustic coating was proposed by Weeratunge et al for underwater acoustic absorbers. 80 Polyurethane (PU) acoustic coating ( Figure 2 A) with embedded cylindrical voids was designed by considering the frequency-dependent viscoelasticity of PU. The viscoelasticity was used instead of a constant frequency-independent complex modulus in the matrix which does not reflect real-life acoustics.…”

“… Acoustic absorbers and AI-based design (A) Underwater acoustic absorbers with polyurethane (PU) acoustic coatings. Adapted from ref ( 80 ) in accordance with its CC BY 4.0 license. (B) DL-based acoustic metamaterial design for attenuating structure-borne noise in auditory frequency bands.…”

Application of Digital Methods in Polymer Science and Engineering

“…An inverse design strategy to identify optimum geometric parameters (size and location of voids) of polyurethane coatings is also possible. [ 194 ] For this purpose, synthetic data were generated via FEM simulations and, subsequently, used the data to train a deep learning model. The direct ML model used geometric parameters and sound frequency as features to predict the underwater acoustic response of the elastomer ( R 2 = 0.99 for the test set).…”