A physics-constrained deep learning based approach for acoustic inverse scattering problems. (1st February 2022)

• Record Type: Journal Article
• Authors: Wu, Rih-Teng; Jokar, Mehdi; Jahanshahi, Mohammad R.; Semperlotti, Fabio
• Is Part Of: Mechanical systems and signal processing. Volume 164(2022)
• Publication Date: 2022-02-01
• Subjects: Material design -- Inverse problems -- Acoustic wave scattering -- Machine learning -- Deep auto-encoder; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2021.108190
• Languages: English
• ISSNs: 0888-3270

Abstract

Abstract: The control of acoustic and elastic waves via engineered materials has several important real-world applications such as non-destructive evaluation of structural components, synthesis of biomedical devices, high-resolution imaging, and remote sensing. Being formulated as inverse problems, all these applications share as a common denominator the need for efficient solution methodologies. Available techniques, mostly based on conventional optimization approaches, have shown some significant limitations in terms of the ability to explore a vast design space and to limit the computation burden. In this study, a novel deep auto-encoder (DAE) based approach is proposed in order to solve a benchmark inverse problem consisting in designing assemblies of acoustic scattering elements capable of molding an incoming plane wave into a target (user-defined) downstream pressure distribution. The proposed approach is validated numerically through three design scenarios, involving either a single or multiple scatterer configuration, and target pressure fields defined at different frequencies. The proposed network consists of a geometry estimator and a DAE that imposes constraints due to the physics of the problem on the geometry estimator during the learning process which leads to more robust design. By joint optimization, the estimation of scatterer geometry is strengthened with the latent representations of the target pressure field learned by the DAE. For a trained network, the design inference is quasi-instantaneous given a target 2D pressure field. The generalization capability of the proposed network is further explored by using a dataset generated based on scatterers having new shapes. Highlights: A physics-constrained deep learning-based method for wave scattering is presented. The geometry of scattering elements is designed given a 2D downstream pressure field. The proposed network uses a deep auto-encoder to impose constraints during training. A benchmark of multi-objective inverse wave scattering application is presented. A mathematical interpretation of the trained kernels is investigated in detail.