Physics-informed Neural Networks for Acoustic Diagnostics and Prognostics of Complex System
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Acoustic diagnostics have emerged as a low-cost and non-invasive alternative to vibration-based condition monitoring for rotating machinery such as pumps and bearings. However, acoustic signals are highly sensitive to environmental noise, operating variability, and sensor placement, limiting the robustness and generalization of existing data-driven approaches. In addition, most acoustic diagnostic systems remain purely data-driven and rarely incorporate physical knowledge such as characteristic fault frequencies, resonances, and degradation dynamics.
This PhD research proposes a Physics-Informed framework for unsupervised acoustic fault diagnosis and prognosis of pumps and bearings. The framework integrates detection, diagnosis, and prognosis for continuous health monitoring and remaining useful life estimation. Physics-informed constraints are incorporated into the learning process to improve robustness, interpretability, and transferability across varying industrial operating conditions.
How to Cite
##plugins.themes.bootstrap3.article.details##
acoustics, pyhisics-informed, continual learning
Gu, X., Li, R., Kang, M., Lu, F., Tang, D., & Peng, J. (2021, October). Unsupervised adversarial domain adaptation abnormal sound detection for machine condition monitoring under domain shift conditions. In 2021 IEEE 20th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) (pp. 139–146). doi: 10.1109/ICCICC53683.2021.9811305
Jiang, M., Luo, M., Zhang, C., Shu, M., & Sun, G. (2024, November). Rolling bearing fault diagnosis based on acoustic-vibration data fusion and mode decomposition combined with the crested porcupine optimization algorithm. Heliyon, 10(22), e40351. doi: 10.1016/j.heliyon.2024.e40351
Keshun, Y., Puzhou, W., Peng, H., & Yingkui, G. (2025). A sound-vibration physical-information fusion constraint-guided deep learning method for rolling bearing fault diagnosis. , 253, 110556. doi: 10.1016/j.ress.2024.110556
Tang, L., Tian, H., Huang, H., Shi, S., & Ji, Q. (2023). A survey of mechanical fault diagnosis based on audio signal analysis. , 220, 113294. doi: 10.1016/j.measurement.2023.113294
Wu, X., &Peng, D. (2024). Acoustic monitoring of rolling element bearings using simulation-based partial domain adaptation.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.