Research on the Leakage Monitoring and Recognition Method of High-Pressure Hydrogen Valves

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription Access

Abstract

High-pressure hydrogen valves are subjected to the instantaneous impact of hydrogen flow and repeated start-stop action during service, and there is a potential risk of leakage. This paper investigates monitoring and identification of hydrogen valves leakage to ensure their operational reliability. Firstly, an acoustic signal monitoring system was built based on a high-pressure hydrogen gas-tightness test platform, and the time-domain feature of valves under different leakage conditions was analyzed. Secondly, the frequency-domain feature is extracted using a combination of Variational Modal Decomposition and Wavelet Packet Decomposition. Ultimately, the Backward Propagation Network (BP) and Convolutional Neural Network (CNN) are used to recognize patterns of acoustic signals, with the time-domain and frequency-domain parameters as feature inputs independently. The results show that the accuracy of BP and CNN networks based on frequency domain features has significantly improved, 93.33 and 91.67 %, respectively. This paper obtained the feature extraction and pattern recognition method for hydrogen valves, which provides a reference for accurate and efficient recognition of the leakage condition of high-pressure hydrogen valves in the service process.

Full Text

Restricted Access

About the authors

Yi Qin

SINOPEC Research Institute of Safety Engineering

Email: kangzt_upc@163.com
China, 339, Songling Road, Laoshan District, Qingdao, Shandong, 266000

Zhe Yang

SINOPEC Research Institute of Safety Engineering

Email: kangzt_upc@163.com
China, 339, Songling Road, Laoshan District, Qingdao, Shandong, 266000

Zetian Kang

SINOPEC Research Institute of Safety Engineering

Author for correspondence.
Email: kangzt_upc@163.com
China, 339, Songling Road, Laoshan District, Qingdao, Shandong, 266000

Qian Wu

SINOPEC Research Institute of Safety Engineering

Email: kangzt_upc@163.com
China, 339, Songling Road, Laoshan District, Qingdao, Shandong, 266000

Yuchen Wang

SINOPEC Research Institute of Safety Engineering

Email: kangzt_upc@163.com
China, 339, Songling Road, Laoshan District, Qingdao, Shandong, 266000

Anfeng Yu

SINOPEC Research Institute of Safety Engineering

Email: kangzt_upc@163.com
China, 339, Songling Road, Laoshan District, Qingdao, Shandong, 266000

Huan Liu

SINOPEC Research Institute of Safety Engineering

Email: kangzt_upc@163.com
China, 339, Songling Road, Laoshan District, Qingdao, Shandong, 266000

Yun Luo

SINOPEC Research Institute of Safety Engineering

Email: kangzt_upc@163.com
China, 339, Songling Road, Laoshan District, Qingdao, Shandong, 266000

References

  1. Filippov S.P., Yaroslavtsev A.B. Hydrogen energy: Development prospects and materials // Russian Chemical Reviews. 2021. V. 90 (6). P. 627. https://doi.org/10.1070/RCR5014
  2. Vechkinzova E., Steblyakova L.P., Roslyakova N. et al. Prospects for the development of hydrogen energy: Overview of global trends and the Russian market state // Energies. 2022. V. 15 (22). P. 8503. https://doi.org/10.3390/en15228503
  3. Ferlazzo A., Espro C., Iannazzo D. et al. A novel yttria-doped ZrO2 based conductometric sensor for hydrogen leak monitoring // International Journal of Hydrogen Energy. 2022. V. 47 (16). P. 9819—28. https://doi.org/10.1016/j.ijhydene.2022.01.036
  4. Falsafi F., Hashemi B., Mirzaei A. et al. Sm-doped cobalt ferrite nanoparticles: A novel sensing material for conductometric hydrogen leak sensor // Ceramics International. 2017. V. 43 (1, Part B). P. 1029—37. https://doi.org/10.1016/j.ceramint.2016.10.035
  5. Chen Y., Yang Y., Liang C. et al. Palladium-based optical fiber Bragg grating hydrogen sensors: A comprehensive review // Optics & Laser Technology. 2024. V. 175. P. 110850. https://doi.org/10.1016/j.optlastec.2024.110850
  6. Sazhin S., Soborover E., Tokarev S. Sensor methods of ammonia inspection // Russian journal of nondestructive testing. 2003. V. 39 (10). P. 791—806. https://doi.org/10.1023/B:RUNT.0000020251.56686.a5
  7. Ye Z., Ruan H., Hu X. et al. TBAOH intercalated WO3 for high-performance optical fiber hydrogen sensor // International Journal of Hydrogen Energy. 2022. V. 47 (65). P. 28204—11. https://doi.org/10.1016/j.ijhydene.2022.06.133
  8. Zhao L., Cao Z., Deng J. A review of leak detection methods based on pressure waves in gas pipelines // Measurement. 2024. V. 236. P. 115062. https://doi.org/10.1016/j.measurement.2024.115062
  9. Banjara N.K., Sasmal S., Voggu S. Machine learning supported acoustic emission technique for leakage detection in pipelines // International Journal of Pressure Vessels and Piping. 2020. V. 188. P. 104243. https://doi.org/10.1016/j.ijpvp.2020.104243
  10. Shi M., Liang Y., Qin L. et al. Prediction method of ball valve internal leakage rate based on acoustic emission technology // Flow Measurement and Instrumentation. 2021. V. 81. P. 102036. https://doi.org/10.1016/j.flowmeasinst.2021.102036
  11. Mostafapour A., Davoudi S. Analysis of leakage in high pressure pipe using acoustic emission method // Applied Acoustics. 2013. V. 74 (3). P. 335—42. https://doi.org/10.1016/j.apacoust.2012.07.012
  12. Ye G.-Y., Xu K.-J., Wu W.-K. Multivariable modeling of valve inner leakage acoustic emission signal based on Gaussian process // Mechanical Systems and Signal Processing. 2020. V. 140. P. 106675. https://doi.org/10.1016/j.ymssp.2020.106675
  13. Asatryan R., Asatryan S., Sukoyan L. et al. A spectroradiometer for remote ecological testing of gas main pipelines // Russian Journal of Nondestructive Testing. 2010. V. 46 (8). P. 598—602. https://doi.org/10.1134/S1061830910080085
  14. Tian C.H., Yan J.C., Huang J. et al. Negative pressure wave based pipeline leak detection: Challenges and algorithms / proceedings of the Proceedings of 2012 IEEE international conference on service operations and logistics, and informatics. F, 2012 [C]. IEEE.
  15. Li J., Weng H., Yang Q. et al. Data-driven diagnosis method of high-pressure hydrogen leakage based on actual driving conditions and probabilistic neutral network // International Journal of Hydrogen Energy. 2024. V. 71. P. 411—21. https://doi.org/10.1016/j.ijhydene.2024.04.204
  16. Prateepasen A., Kaewwaewnoi W., Kaewtrakulpong P. Smart portable noninvasive instrument for detection of internal air leakage of a valve using acoustic emission signals // Measurement. 2011. V. 44 (2). P. 378—84. https://doi.org/10.1016/j.measurement.2010.10.009
  17. Banjara N.K., Sasmal S., Kapuria S. Fatigue and leakage-type damage detection in metallic plates and pipelines using piezoelectric patch acoustic sensors // International Journal of Pressure Vessels and Piping. 2024. V. 209. P. 105162. https://doi.org/10.1016/j.ijpvp.2024.105162
  18. Li Z., Zhang H., Tan D. et al. A novel acoustic emission detection module for leakage recognition in a gas pipeline valve // Process Safety and Environmental Protection. 2017. V. 105. P. 32—40. https://doi.org/10.1016/j.psep.2016.10.005
  19. Zhang Y., Yang G., Zhang D. et al. Investigation on recognition method of acoustic emission signal of the compressor valve based on the deep learning method // Energy Reports. 2021. V. 7. P. 62—71. https://doi.org/10.1016/j.egyr.2021.10.053
  20. Xu C., Du S., Gong P. et al. An improved method for pipeline leakage localization with a single sensor based on modal acoustic emission and empirical mode decomposition with Hilbert transform // IEEE Sensors Journal. 2020. V. 20 (10). P. 5480—91. https://doi.org/10.1109/JSEN.2020.2971854
  21. Martyugov A., Ershov E., Varfolomeev I. et al. Method of processing acoustic information for purposes of monitoring state of valves of gas cleaning equipment // Russian Journal of Nondestructive Testing. 2021. V. 57. P. 838—45. https://doi.org/10.1134/S1061830921100041
  22. Qiu F., Shen Z., Bai Y. et al. Hydrogen defect acoustic emission recognition by deep learning neural network // International Journal of Hydrogen Energy. 2024. V. 54. P. 878—93. https://doi.org/10.1016/j.ijhydene.2023.09.176
  23. Khlybov A., Uglov A., Ryabov D. Developing a Method for Assessing the Degree of Hydrogenation of VT1-0 Titanium Alloy by the Acoustic Method // Russian Journal of Nondestructive Testing. 2024. V. 60 (8). P. 843—58. https://doi.org/10.1134/S1061830924601739
  24. Peng J., Cairui L., Luying Z. et al. Study on Material Damage Characterization of High-Pressure Hydrogen Storage Vessels Based on DIC and Acoustic Emission Entropy // Russian Journal of Nondestructive Testing. 2022. V. 58 (6). P. 433—43. https://doi.org/10.1134/S1061830922060055
  25. Wang D., Liao B., Hao C. et al. Acoustic emission characteristics of used 70 MPa type IV hydrogen storage tanks during hydrostatic burst tests // International Journal of Hydrogen Energy. 2021. V. 46 (23). P. 12605—14. https://doi.org/10.1016/j.ijhydene.2020.12.177
  26. Li Y., Xu F. Structural damage monitoring for metallic panels based on acoustic emission and adaptive improvement variational mode decomposition–wavelet packet transform // Structural Health Monitoring. 2022. V. 21 (2). P. 710—30.
  27. Mostafapour A., Davoodi S. Continuous leakage location in noisy environment using modal and wavelet analysis with one AE sensor // Ultrasonics. 2015. V. 62. P. 305—11. https://doi.org/10.1016/j.ultras.2015.06.004.
  28. Du J., Wang H., Chen C. et al. Damage classification and evolution in composite under low-velocity impact using acoustic emission, machine learning and wavelet packet decomposition // Engineering Fracture Mechanics. 2024. P. 110238. https://doi.org/10.1016/j.engfracmech.2024.110238
  29. Pan Y., Zhang L., Wu X. et al. Structural health monitoring and assessment using wavelet packet energy spectrum // Safety Science. 2019. V. 120. P. 652—65. https://doi.org/10.1016/j.ssci.2019.08.015
  30. Gutkin R., Green C., Vangrattanachai S. et al. On acoustic emission for failure investigation in CFRP: Pattern recognition and peak frequency analyses // Mechanical systems and signal processing. 2011. V. 25 (4). P. 1393—407. https://doi.org/10.1016/j.ymssp.2010.11.014
  31. Zhou L., Wang P., Zhang C. et al. Multi-mode fusion BP neural network model with vibration and acoustic emission signals for process pipeline crack location // Ocean Engineering. 2022. V. 264. P. 112384. https://doi.org/10.1016/j.oceaneng.2022.112384
  32. Zhou J., Lin H., Li S. et al. Leakage diagnosis and localization of the gas extraction pipeline based on SA-PSO BP neural network // Reliability Engineering & System Safety. 2023. V. 232. P. 109051. https://doi.org/10.1016/j.ress.2022.109051
  33. Zhao H., Li Z., Zhu S. et al. Valve internal leakage rate quantification based on factor analysis and wavelet-BP neural network using acoustic emission // Applied Sciences. 2020. V. 10 (16). P. 5544. https://doi.org/10.3390/app10165544
  34. Krysko N., Skrynnikov S., Shchipakov N. et al. Classification and Sizing of Surface Defects in Pipelines Based on the Results of Combined Diagnostics by Ultrasonic, Eddy Current, and Visual Inspection Methods of Nondestructive Testing // Russian Journal of Nondestructive Testing. 2023. V. 59 (12). P. 1315—23. https://doi.org/10.1134/S1061830923601022
  35. Ai L., Bayat M., Ziehl P. Localizing damage on stainless steel structures using acoustic emission signals and weighted ensemble regression-based convolutional neural network // Measurement. 2023. V. 211. P. 112659. https://doi.org/10.1016/j.measurement.2023.112659

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. Scheme of leakage monitoring and recognition.

Download (438KB)
Indexing metadata
3. Fig. 2. Experimental setup: acoustic signal monitoring system (a); acoustic signal monitoring scheme (b).

Download (581KB)
Indexing metadata
4. Fig. 3. Correlation between signal parameters obtained by acoustic monitoring and hydrogen valve leakage pressure (feature parameters for acoustic leak detection): magnitude (a); RMS value (b); average signal level (c); energy (d); rise time (e); accumulated counts (f).

Download (582KB)
Indexing metadata
5. Fig. 4. Variational modal decomposition of the leakage signal at a pressure of 20 MPa.

Download (903KB)
Indexing metadata
6. Fig. 5. Wavelet packet energy distribution for different leakage conditions.

Download (171KB)
Indexing metadata
7. Fig. 6. Basic structure of BP.

Download (211KB)
Indexing metadata
8. Fig. 7. BP recognition results: input signal in time domain (a); input signal in frequency domain (b).

Download (211KB)
Indexing metadata
9. Fig. 8. BP losses for different number of periods.

Download (161KB)
Indexing metadata
10. Fig. 9. Basic structure of CNN.

Download (215KB)
Indexing metadata
11. Fig. 10. CNN recognition results: input signal in time domain (a); input signal in frequency domain (b).

Download (215KB)
Indexing metadata
12. Fig. 11. CNN losses for different number of periods.

Download (153KB)
Indexing metadata

Copyright (c) 2025 Russian Academy of Sciences