Reverse design of broadband sound absorption structure based on deep learning method
Abstract This research presents a method based on deep learning for the reverse design of sound-absorbing structures. Traditional methods require time-consuming individual numerical simulations followed by cumbersome calculations, whereas the deep learning design method significantly simplifies the...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-86077-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594759493877760 |
|---|---|
| author | Yihong Zhou Lifeng Ma Xi Kang Zhiyuan Zhu |
| author_facet | Yihong Zhou Lifeng Ma Xi Kang Zhiyuan Zhu |
| author_sort | Yihong Zhou |
| collection | DOAJ |
| description | Abstract This research presents a method based on deep learning for the reverse design of sound-absorbing structures. Traditional methods require time-consuming individual numerical simulations followed by cumbersome calculations, whereas the deep learning design method significantly simplifies the design process, achieving efficient and rapid design objectives. By utilizing deep neural networks, a mapping relationship between structural parameters and the sound absorption coefficient curve is established. The forward network predicts the sound absorption coefficient curve, while the reverse network enables the on-demand design of structural parameters for broadband high sound absorption. During the design process, a mean squared error (MSE) below 0.0001 is achieved. The accuracy of the proposed design method is validated through examples. The results demonstrate that the trained deep learning neural network could effectively replace the complex physical mechanisms between structural parameters and sound absorption coefficient curves. This deep learning design method could also be extended to other types of metamaterial reverse designs, significantly enhancing the efficiency of complex metamaterial designs. Lightweight design is crucial for energy saving and emission reduction. With the total mass and average sound absorption coefficient of sound-absorbing materials as targets, the NSGA-II algorithm has been used for multi-objective optimization design. The optimized average sound absorption coefficient increased by 4.84%, and the total material mass was reduced by 18.98%. |
| format | Article |
| id | doaj-art-541e83bba4dc4e2d9df565a32e447982 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-541e83bba4dc4e2d9df565a32e4479822025-01-19T12:23:11ZengNature PortfolioScientific Reports2045-23222025-01-0115111510.1038/s41598-025-86077-wReverse design of broadband sound absorption structure based on deep learning methodYihong Zhou0Lifeng Ma1Xi Kang2Zhiyuan Zhu3School of Mechanical and Automotive Engineering, Shanghai University of Engineering ScienceSchool of Mechanical and Automotive Engineering, Shanghai University of Engineering ScienceSchool of Mechanical and Automotive Engineering, Shanghai University of Engineering ScienceSchool of Mechanical and Automotive Engineering, Shanghai University of Engineering ScienceAbstract This research presents a method based on deep learning for the reverse design of sound-absorbing structures. Traditional methods require time-consuming individual numerical simulations followed by cumbersome calculations, whereas the deep learning design method significantly simplifies the design process, achieving efficient and rapid design objectives. By utilizing deep neural networks, a mapping relationship between structural parameters and the sound absorption coefficient curve is established. The forward network predicts the sound absorption coefficient curve, while the reverse network enables the on-demand design of structural parameters for broadband high sound absorption. During the design process, a mean squared error (MSE) below 0.0001 is achieved. The accuracy of the proposed design method is validated through examples. The results demonstrate that the trained deep learning neural network could effectively replace the complex physical mechanisms between structural parameters and sound absorption coefficient curves. This deep learning design method could also be extended to other types of metamaterial reverse designs, significantly enhancing the efficiency of complex metamaterial designs. Lightweight design is crucial for energy saving and emission reduction. With the total mass and average sound absorption coefficient of sound-absorbing materials as targets, the NSGA-II algorithm has been used for multi-objective optimization design. The optimized average sound absorption coefficient increased by 4.84%, and the total material mass was reduced by 18.98%.https://doi.org/10.1038/s41598-025-86077-wSound-absorbing materialsDeep learningNeural networksReverse designLightweight designTarget optimization |
| spellingShingle | Yihong Zhou Lifeng Ma Xi Kang Zhiyuan Zhu Reverse design of broadband sound absorption structure based on deep learning method Scientific Reports Sound-absorbing materials Deep learning Neural networks Reverse design Lightweight design Target optimization |
| title | Reverse design of broadband sound absorption structure based on deep learning method |
| title_full | Reverse design of broadband sound absorption structure based on deep learning method |
| title_fullStr | Reverse design of broadband sound absorption structure based on deep learning method |
| title_full_unstemmed | Reverse design of broadband sound absorption structure based on deep learning method |
| title_short | Reverse design of broadband sound absorption structure based on deep learning method |
| title_sort | reverse design of broadband sound absorption structure based on deep learning method |
| topic | Sound-absorbing materials Deep learning Neural networks Reverse design Lightweight design Target optimization |
| url | https://doi.org/10.1038/s41598-025-86077-w |
| work_keys_str_mv | AT yihongzhou reversedesignofbroadbandsoundabsorptionstructurebasedondeeplearningmethod AT lifengma reversedesignofbroadbandsoundabsorptionstructurebasedondeeplearningmethod AT xikang reversedesignofbroadbandsoundabsorptionstructurebasedondeeplearningmethod AT zhiyuanzhu reversedesignofbroadbandsoundabsorptionstructurebasedondeeplearningmethod |