What question did this study set out to answer?

To establish a quantitative relationship between the microstructure and acoustic performance of polyurethane foam.

May 6, 2026The Journal of the Acoustical Society of America0 citationsOpen Access

Deep Learning Framework Links Microstructural Properties to Acoustic Performance of Foam

Deep learning-based approach for linking microstructural and macroscopic acoustic properties of sound-absorbing polyurethane foam

View Full Paper

Ask AI

Bookmark

Authors

Acoustic modeling framework predicts sound absorption in flexible polyurethane foam, suggesting advances in construction materials.

To establish a quantitative relationship between the microstructure and acoustic performance of polyurethane foam.
Developed a deep learning-based acoustic modeling framework.
Utilized a U-Net model for semantic segmentation of SEM images.
Analyzed 210 samples of flexible polyurethane foam, including thermally aged materials.
Created an artificial neural network model to relate microstructural parameters to acoustic performance.
Validated the framework through comparisons with experiments and alternative methods.
Established a quantitative link between microstructural morphology and acoustic performance.
Identified key microstructural parameters, such as cell size and pore size, affecting sound absorption.
Proposed a data-driven approach to optimize the design of sound-absorbing materials for construction applications.

Jung et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

May 6, 2026The Journal of the Acoustical Society of America0 citationsOpen Access

Deep learning-based approach for linking microstructural and macroscopic acoustic properties of sound-absorbing polyurethane foam

View Full Paper

Ask AI

Bookmark

Authors

Acoustic modeling framework predicts sound absorption in flexible polyurethane foam, suggesting advances in construction materials.

To establish a quantitative relationship between the microstructure and acoustic performance of polyurethane foam.
Developed a deep learning-based acoustic modeling framework.
Utilized a U-Net model for semantic segmentation of SEM images.
Analyzed 210 samples of flexible polyurethane foam, including thermally aged materials.
Created an artificial neural network model to relate microstructural parameters to acoustic performance.
Validated the framework through comparisons with experiments and alternative methods.
Established a quantitative link between microstructural morphology and acoustic performance.
Identified key microstructural parameters, such as cell size and pore size, affecting sound absorption.
Proposed a data-driven approach to optimize the design of sound-absorbing materials for construction applications.

Jung et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark