Search

[Display omitted] • A CNN-GA hybrid optimization framework for accelerating the inverse design of lightweight sound-absorbing metaporous. • CNN model with high accuracy and generalization ability is developed and validated. • Customizing various metaporous of 30mm thickness with several simple inclusions on demand. • Desired high sound absorption is achieved in a diffuse sound field. A key challenge in sound-absorbing structure design is the effectively inverse generation of structure capable of achieving high absorption at desired frequencies. As the two of the most commonly used methods in inverse design, trial-and-error and traditional topology optimization suffer extensive computational costs. In this work, we develop a CNN-GA hybrid optimization framework that combines the advantages of the traditional heuristic algorithm with emerging machine learning technology to accelerate the inverse design of a random sound-absorbing structure called metaporous with only 30mm thickness based on the sound absorption in diffuse field. The finite element method (FEM) simulation is applied to calculate the sound absorption coefficients of randomly generated metaporous structures. The numerous data obtained from the FEM simulation are input to the convolutional neural network (CNN) model for training the network. The well-trained CNN model, of which generalization ability is validated by a testing set, is coupled with a genetic algorithm (GA) for accelerating the iterative evaluation of the objective function in inverse design. The proposed inverse design framework leverages the accelerated GA to generate near-optimal metaporous structures of various tailored absorption peaks typically in roughly 5 s to 30 s on average. The numerical results show that the proposed CNN-GA hybrid optimization framework works several orders of magnitude faster than the conventional single algorithms in inverse design of metaporous, on the condition that accuracy is ensured. In addition, an impedance tube measurement is performed to validate the proposed method. This work brings forward a new inverse design method for metaporous materials and brings out the immense potential of combining the meta-heuristic algorithm and machine learning. [ABSTRACT FROM AUTHOR]

This work designs a tunable acoustic composite metasurface, with porous material and a modified microperforated panel (MPP) system. The broadband sound absorption performance of the composite metasurface is evaluated by the analytical theory, numerical simulation, and experiment in the frequency range between 200 Hz and 3500 Hz. The designed composite metasurface has a significant advantage in sound absorption performance compared with a uniform porous material, especially in the low-frequency range. The excellent sound absorption performance is achieved not only by the wavefront controlling with the phase gradient adjustment but also by the resonance dissipation of the modified MPP system. The high-order reflected waves have been converted into surface waves by the wave controlling ability of the designed metasurface for excellent sound absorption at the high frequency of interest. The modified MPP system is formed by a microperforated panel and a coiling-up space cavity to achieve excellent sound absorption in the low-frequency range. By adjusting the length of the coiling silt in the modified microperforated panel system, the absorption peak can move to the frequency of interest. The compact composite metasurface with 3 cm height has remarkably improved the sound absorption of porous material alone from low to high frequency, which could easily replace porous material for better sound absorption in industry. [ABSTRACT FROM AUTHOR]

[Display omitted] • A theoretical model is developed for predicting the acoustic performance of a novel designed sound absorber of nanofibrous membrane composite porous material. • Theoretical and experimental studies have revealed the nanofibrous membrane can effectively enhance the acoustic performance of substrate porous materials without weight sacrifices. • The maximum up to 50% sound absorption promotion at the high-frequency range for substrate porous material with 25 μm thickness of nanofibrous membrane covering. • Thickness range of nanofibrous membrane between 25 and 100 μm results in good acoustic performance improvements for melamine foams and fiberglass materials. This study mainly focuses on the structural design, acoustic performance prediction, and experimental validation of a novel composite sound absorber that is similar to the feather surface structure of barn owls. The composite sound absorber is composed of an ultra-light nanofibrous membrane backed with a substrate porous materials layer (NMSPM). A theoretical NMSPM model is proposed for predicting the sound absorption coefficient (SAC) of NMSPM. The experimental results demonstrate that the nanofibrous membrane can effectively improve the acoustic performance of substrate porous materials (SPM) based on specific material parameters conditions, which also compare well with the numerical results of the theoretical NMSPM model. The applicability of the theoretical NMSPM model for different sorts of SPMs is explained based on both the experimental and numerical results. A suitable thickness range of nanofibrous membrane for effectively improving the SAC of SPM is given through a series of numerical analyses. This study may provide new thinking for a novel composite sound absorber design without weight sacrifices. [ABSTRACT FROM AUTHOR]