Abstract
Accurate monitoring of boiling heat transfer is critical for safeguarding high-power systems operating in environments where conventional optical diagnostics are hindered by radiation fields or restricted visual accessibility. This study presents a non-intrusive framework that integrates hydroacoustic sensing with deep learning to infer near-wall boiling characteristics and enable predictive thermal assessment without visual access. In a prototypical subcooled flow-boiling facility representative of the Isotope Production Facility (IPF) at Los Alamos, hydrophones capture boiling-induced acoustic emissions that are transformed into background-removed Short-Time Fourier Transform (STFT) spectrograms. A convolutional neural network (CNN) then regresses heat flux, wall superheat, and key bubble parameters directly from these spectrograms. The CNN achieved predictive accuracy under nominal conditions and demonstrated robustness and generalization under acoustic noise for Signal-to-Noise Ratios (SNRs) down to approximately 0 dB. When integrated into an ANSYS CFX wall-boiling model, the acoustically inferred parameters reproduced boiling curve and critical heat flux (CHF) values consistent with image-based benchmarks. Furthermore, the model retained reliable performance under moderate variations in bulk temperature, flow rate, and hydrophone placement, confirming its generalizability across practical boundary conditions. These results demonstrate the feasibility of hydroacoustic-based deep learning as a viable path toward real-time, radiation-tolerant boiling diagnostics and predictive thermal safety assessment in inaccessible systems such as the IPF.
Data availability
The data supporting the findings of this study are provided as Supplementary Information with this manuscript, including the raw data underlying the figures and example datasets sufficient to run the accompanying analysis and machine-learning code. The full dataset generated and analyzed during the current study is available from the first author, Dr. Huang ([phhuang@lanl.gov](mailto: phhuang@lanl.gov)), or the corresponding author, Dr. O’Brien ([emobrien@lanl.gov](mailto: emobrien@lanl.gov)) upon reasonable request and will be deposited in the Los Alamos National Laboratory Research Library and assigned a persistent DOI upon acceptance.
References
O’Brien, E. M. et al. Novel design and diagnostics improvements for increased production capacity and improved reliability at the Los Alamos Isotope Production Facility. Nucl. Instrum. Methods Phys. Res. A 956, 163316 (2020).
Seong, J. H. et al. Development of experimental and computational frameworks to predict subcooled flow boiling in the LANL Isotope Production Facility. Int. J. Heat Mass Transfer 203, 123836 (2023).
Rapisarda, D. et al. Boiling bubbles monitoring for the protection of the LIPAc beam-dump. Fusion Eng. Des. 96, 917–921 (2015).
Nishihara, H. Resonant acoustic noise spectra of nucleate coolant boiling. J. Nucl. Sci. Technol. 11(1), 1–7 (1974).
Huang, P.H., Seong, J.H., Castro Aguilar, J.M., O’Brien, E.M., & Vermeulen, C. Acoustic Analysis to Identify Boiling Characteristics in the LANL Isotope Production Facility Cooling System. In 21st International Topical Meeting on Nuclear Reactor Thermal Hydraulics (NURETH-21) (2025).
Sinha, K. N. R. et al. In-situ acoustic detection of critical heat flux for controlling thermal runaway in boiling systems. Int. J. Heat Mass Transfer 138, 135–143 (2019).
Almadih, M. H. et al. Acoustic analysis of the effects of vapor-liquid interfacial morphology on pool-boiling heat transfer. Nucl. Technol. 208(8), 1290–1300 (2022).
Negi, A., Rishi, A. M. & Kandlikar, S. G. Effect of heat flux on bubble coalescence phenomena and sound signatures during pool boiling. J. Heat Transfer 143(5), 051601 (2021).
Zhang, K., Yang, J., Huai, X. & Cheng, K. Highly stable subcooled flow boiling enabled by an opposed wall jet design. Int. J. Heat Mass Transfer 216, 124562 (2023).
Baek, S. H. et al. Acoustic emission monitoring of water boiling on fuel cladding surface at 1 bar and 130 bar. Measurement 109, 18–26 (2017).
Kichigin, A. M. & Kesova, L. A. Relationship between the nature of acoustic oscillations and the mode of surface boiling of water in annular channels. J. Appl. Mech. Tech. Phys. 8, 54–56 (1967).
Schwartz, F. L., & Siler, L. G. Correlation of sound generation and heat transfer in boiling. (1965).
Minnaert, M. On musical air-bubbles and the sounds of running water. Lond. Edinb. Dublin Philos. Mag. J. Sci. 16, 235–248 (1933).
Dorofeev, B. M. & Volkova, V. I. The effect of evaporation and condensation in vapor bubbles on the hydrodynamic sound generation in a subcooled boiling liquid. Acoust. Phys. 52, 173–179 (2006).
Bessho, Y. & Nishihara, H. Boiling acoustic emission and bubble dynamics in nucleate boiling. J. Nucl. Sci. Technol. 13, 520–522 (1976).
Tang, J. et al. Experimental study of sound emission in subcooled pool boiling on a small heating surface. Chem. Eng. Sci. 188, 179–191 (2018).
Ravichandran, M. & Bucci, M. Online, quasi-real-time analysis of high-resolution, infrared, boiling heat transfer investigations using artificial neural networks. Appl. Therm. Eng. 163, 114357 (2019).
Nirapure, P., Singh, A., Rangarajan, S., & Sammakia, B. Image driven deep learning based compact model to predict critical heat flux in direct immersion cooling via pool boiling. In 2024 23rd IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm) IEEE. 1–11. (2024)
Ueki, Y. & Ara, K. Proof of concept of acoustic detection of boiling inception and state transition using deep neural network. Int. Commun. Heat Mass Transf. 129, 105675 (2021).
Barathula, S., Chaitanya, S. K. & Srinivasan, K. Evaluation of machine learning models in the classification of pool boiling regimes up to critical heat flux based on boiling acoustics. Int. J. Heat Mass Transf. 201, 123623 (2023).
Sinha, K. N. R., Kumar, V., Kumar, N., Thakur, A. & Raj, R. Deep learning the sound of boiling for advance prediction of boiling crisis. Cell Rep. Phys. Sci. https://doi.org/10.1016/j.xcrp.2021.100382 (2021).
Sinha, K. N. R., Kumar, V., Kumar, N., Thakur, A. & Raj, R. Dataset for boiling acoustic emissions: A tool for data driven boiling regime prediction. Data Brief 52, 109793 (2024).
Zhang, K., Yang, J., Huang, C. & Huai, X. Nonintrusive identification of boiling regimes enabled by deep learning based on flow boiling acoustics. Int. J. Heat Mass Transf. 236, 126290 (2025).
Dunlap, C., Pandey, H., Weems, E. & Hu, H. Nonintrusive heat flux quantification using acoustic emissions during pool boiling. Appl. Therm. Eng. 228, 120558 (2023).
Lim, D., Liu, Y. & Bang, I. C. Predicting boiling heat flux, heat transfer coefficient, and regimes non-intrusively using external acoustics and deep learning. Sci. Rep. 15(1), 22690 (2025).
Huang, P.H., Seong, J.H., Castro Aguilar, J.M., O’Brien, E.M., Vermeulen, C. Visual-Acoustic Boiling Data Driven Machine Learning for Isotope Production. In ANS Winter Meeting. (2025).
Ansys® CFX Fluids, Release 21.2. https://www.ansys.com/academic/ terms- and- conditions#Tables 1- 1.
SPECIAL METALS, INCONEL® Alloy 625, UNS N06625/W.Nr. 2.4856. www.specialmetals.com. (Accessed 3 January 2023).
Seong, J. H., Ravichandran, M., Su, G., Phillips, B. & Bucci, M. Automated bubble analysis of high-speed subcooled flow boiling images using U-net transfer learning and global optical flow. Int. J. Multiph. Flow 159, 104336 (2023).
Richenderfer, A. et al. Investigation of subcooled flow boiling and CHF using high-resolution diagnostics. Exp. Therm. Fluid Sci. 99, 35–58 (2018).
Seong, J. H., Ravichandran, M., Su, G., Phillips, B. & Bucci, M. Automated bubble analysis of high-speed subcooled flow boiling images using U-net transfer learning and global optical flow. Int. J. Multiph. Flow 159, 104336 (2023).
A. GULLI, PAL, S. “Deep learning with Keras,” Packt Publishing Ltd. (2017).
Kenning, D. B. R. Fully-developed nucleate boiling: Overlap of areas of influence and interference between bubble sites. Int. J. Heat Mass Transfer 24(6), 1025–1032 (1981).
Acknowledgements
This work was supported by the U.S. Department of Energy (DOE) Isotope Program, managed by the Office of Science for Isotope R&D and Production. Los Alamos National Laboratory is operated by Triad National Security, LLC, for the National Nuclear Security Administration of the U.S. Department of Energy under Contract No. 89233218CNA000001.
Funding
This work was supported by the U.S. Department of Energy (DOE) Isotope Program.
Author information
Authors and Affiliations
Contributions
P.H.: Writing—review & editing, Writing—original draft, Conceptualization, Methodology, Validation, Formal analysis, Investigation, Visualization, Data curation. J.S.: Writing—review &editing, Resources, Methodology, Investigation. J.M.C.A.: Methodology, Investigation. C.V.: Conceptualization, Methodology, Writing—review & editing, Supervision, Resources, Project administration, Funding acquisition. E.M.O.: Conceptualization, Methodology, Writing—review & editing, Supervision, Resources, Project administration, Funding acquisition.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Huang, PH., Seong, J.H., Castro-Aguilar, J.M. et al. A non-intrusive framework using acoustic signals and deep learning for boiling diagnostics in visual-limited environments. Sci Rep (2026). https://doi.org/10.1038/s41598-026-41757-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-41757-z
