2022
DOI: 10.1109/lra.2021.3130368
|View full text |Cite
|
Sign up to set email alerts
|

AcousNet: A Deep Learning Based Approach to Dynamic 3D Holographic Acoustic Field Generation From Phased Transducer Array

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
7
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 20 publications
(7 citation statements)
references
References 24 publications
0
7
0
Order By: Relevance
“…To realize more flexible modulation of the acoustic virtual walls and rolling in three-dimensional (3D) space, a transducer array [66][67][68] can be designed to establish 3D virtual walls and incorporated with a rotational magnetic field having variable rotational axes. However, when it comes to instrumentation and attaining a higher resolution of 3D manipulation, several practical limitations are expected.…”
Section: Discussionmentioning
confidence: 99%
“…To realize more flexible modulation of the acoustic virtual walls and rolling in three-dimensional (3D) space, a transducer array [66][67][68] can be designed to establish 3D virtual walls and incorporated with a rotational magnetic field having variable rotational axes. However, when it comes to instrumentation and attaining a higher resolution of 3D manipulation, several practical limitations are expected.…”
Section: Discussionmentioning
confidence: 99%
“…Neural networks have powerful fitting abilities to accomplish complex linear or nonlinear mappings, and Chengxi Zhong et al [ 82 ] used a deep learning-based method, AcousNet, in 2021 to solve the inverse mapping problem from sound field distribution to phase distribution by training to allow the VGG-based neural network model to learn a large number of inverse mapping relations to directly predict the phase distribution of the PTA, which was experimentally demonstrated to be well reconstructed and usable for practical applications, with significantly shorter computation time and faster reconstruction compared to traditional optimization algorithms (IBP) and competitive prediction accuracy and real-time performance in PTA-based holographic sound field generation. It is expected that this acoustic holographic optimization method will improve the performance of many applications by reconstructing high-quality holographic acoustic fields in real time.…”
Section: Application Of Ultrasonic Particle Manipulationmentioning
confidence: 99%
“…A limitation of most static metasurface-based holograms [29,38,39] is that only a single and static acoustic field can be generated at a target plane for a given hologram, limiting the range of activities that can be performed, whereas applications in tissue engineering and 3D printing benefit from the incorporation of designed heterogeneity. [40,41] Flexible and reconfigurable acoustic fields can be generated using phased array transducers (PATs), [17,[42][43][44][45][46] in which many ultrasonic devices are individually actuated with varying phase/amplitude. However, the aperture size and drive circuitry of PATs add cost and complexity as the element number increases, [47,48] limiting the spatial resolution at which PATs can create sophisticated wavefront manipulation.…”
Section: Introductionmentioning
confidence: 99%
“…Flexible and reconfigurable acoustic fields can be generated using phased array transducers (PATs), [ 17 , 42 , 43 , 44 , 45 , 46 ] in which many ultrasonic devices are individually actuated with varying phase/amplitude. However, the aperture size and drive circuitry of PATs add cost and complexity as the element number increases, [ 47 , 48 ] limiting the spatial resolution at which PATs can create sophisticated wavefront manipulation.…”
Section: Introductionmentioning
confidence: 99%