Papers
Topics
Authors
Recent
Detailed Answer
Quick Answer
Concise responses based on abstracts only
Detailed Answer
Well-researched responses based on abstracts and relevant paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses
Gemini 2.5 Flash
Gemini 2.5 Flash 47 tok/s
Gemini 2.5 Pro 37 tok/s Pro
GPT-5 Medium 15 tok/s Pro
GPT-5 High 11 tok/s Pro
GPT-4o 101 tok/s Pro
Kimi K2 195 tok/s Pro
GPT OSS 120B 465 tok/s Pro
Claude Sonnet 4 37 tok/s Pro
2000 character limit reached

A Machine Learning Pressure Emulator for Hydrogen Embrittlement (2306.13116v1)

Published 22 Jun 2023 in cs.LG and cs.AI

Abstract: A recent alternative for hydrogen transportation as a mixture with natural gas is blending it into natural gas pipelines. However, hydrogen embrittlement of material is a major concern for scientists and gas installation designers to avoid process failures. In this paper, we propose a physics-informed machine learning model to predict the gas pressure on the pipes' inner wall. Despite its high-fidelity results, the current PDE-based simulators are time- and computationally-demanding. Using simulation data, we train an ML model to predict the pressure on the pipelines' inner walls, which is a first step for pipeline system surveillance. We found that the physics-based method outperformed the purely data-driven method and satisfy the physical constraints of the gas flow system.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (29)
  1. Petroleum pipeline monitoring using an internet of things (IoT) platform. SN Applied Sciences, 3(2):180, February 2021. ISSN 2523-3963, 2523-3971. doi: 10.1007/s42452-021-04225-z. URL http://link.springer.com/10.1007/s42452-021-04225-z.
  2. Incentives and legal barriers for power-to-hydrogen pathways: An international snapshot. International Journal of Hydrogen Energy, 44(23):11394–11401, 2019. ISSN 0360-3199. doi: https://doi.org/10.1016/j.ijhydene.2019.03.045. URL https://www.sciencedirect.com/science/article/pii/S0360319919309693.
  3. Damage detection of pipeline multiple cracks using piezoceramic transducers. Journal of Vibroengineering, 18(5):2828–2838, August 2016. ISSN 1392-8716, 2538-8460. doi: 10.21595/jve.2016.17040. URL https://www.extrica.com/article/17040.
  4. Enabling the european hydrogen economy. Technical report, May 2021.
  5. EU Agency for the Cooperation of Energy Regulators. Transporting Pure Hydrogen by Repurposing Existing Gas Infrastructure: Overview of existing studies and reflections on the conditions for repurposing, July 2021. URL https://web.archive.org/web/20220805232342/https://acer.europa.eu/Official_documents/Acts_of_the_Agency/Publication/Transporting%20Pure%20Hydrogen%20by%20Repurposing%20Existing%20Gas%20Infrastructure_Overview%20of%20studies.pdf. publisher: European Union Agency for the Cooperation of Energy Regulators.
  6. Fick, A. Ueber diffusion. Annalen der Physik und Chemie, 170(1):59–86, 1855. doi: 10.1002/andp.18551700105. URL https://doi.org/10.1002/andp.18551700105.
  7. Learning physics-based models from data: perspectives from inverse problems and model reduction. Acta Numerica, 30:445–554, 2021. doi: 10.1017/S0962492921000064.
  8. Hydrogen embrittlement of steel pipelines during transients. Procedia Structural Integrity, 13:210–217, 2018. ISSN 2452-3216. doi: https://doi.org/10.1016/j.prostr.2018.12.035. URL https://www.sciencedirect.com/science/article/pii/S2452321618302683. ECF22 - Loading and Environmental effects on Structural Integrity.
  9. Darts: User-friendly modern machine learning for time series. Journal of Machine Learning Research, 23(124):1–6, 2022. URL http://jmlr.org/papers/v23/21-1177.html.
  10. Hydrogen 101: Frequently asked questions about hydrogen for decarbonization. July 2022. doi: 10.2172/1879231. URL https://www.osti.gov/biblio/1879231.
  11. Fourier neural operator for parametric partial differential equations, 2020. URL https://arxiv.org/abs/2010.08895.
  12. Temporal fusion transformers for interpretable multi-horizon time series forecasting. 2021.
  13. Data-driven reduced-order models via regularized operator inference for a single-injector combustion process. CoRR, abs/2008.02862, 2020. URL https://arxiv.org/abs/2008.02862.
  14. Department of energy hydrogen program plan. 11 2020. doi: 10.2172/1721803. URL https://www.osti.gov/biblio/1721803.
  15. Blending hydrogen into natural gas pipeline networks. a review of key issues. 3 2013. doi: 10.2172/1219920. URL https://www.osti.gov/biblio/1219920.
  16. Menter, F. R. Zonal two equation k-w turbulence models for aerodynamic flows. 1993.
  17. Pipeline Design and Construction. American Society of Mechanical Engineers, Fairfield, CA, July 2003.
  18. Climax: A foundation model for weather and climate, 2023. URL https://arxiv.org/abs/2301.10343.
  19. Atmospheric implications of increased hydrogen use, 2022.
  20. Performance and emission study of low HCNG fuel blend in SI engine with fixed ignition timing. Cogent Engineering, 9(1):2010925, December 2022. ISSN 2331-1916. doi: 10.1080/23311916.2021.2010925. URL https://www.tandfonline.com/doi/full/10.1080/23311916.2021.2010925.
  21. Hydrogen infrastructure – the pillar of energy transition, 2020.
  22. Hydrogen effects on pipeline steels and blending into natural gas. 10 2019. URL https://www.osti.gov/biblio/1646101.
  23. Boundary-layer theory. Springer, Berlin, Germany, 9 edition, October 2016.
  24. Preserving lagrangian structure in data-driven reduced-order modeling of large-scale dynamical systems, 2022. URL https://arxiv.org/abs/2203.06361.
  25. Evaluation of deep learning approaches for oil and gas pipeline leak detection using wireless sensor networks. Engineering Applications of Artificial Intelligence, 113:104890, 2022. ISSN 0952-1976. doi: https://doi.org/10.1016/j.engappai.2022.104890. URL https://www.sciencedirect.com/science/article/pii/S0952197622001294.
  26. A hybrid hourly natural gas demand forecasting method based on the integration of wavelet transform and enhanced deep-RNN model. Energy, 178:585–597, July 2019. doi: 10.1016/j.energy.2019.04.167. URL https://doi.org/10.1016/j.energy.2019.04.167.
  27. Learning physics-based reduced-order models for a single-injector combustion process. AIAA Journal, 58(6):2658–2672, jun 2020. doi: 10.2514/1.j058943. URL https://doi.org/10.2514%2F1.j058943.
  28. Are transformers effective for time series forecasting? 2023.
  29. Gas pipeline leakage detection based on PZT sensors. Smart Materials and Structures, 26(2):025022, February 2017. ISSN 0964-1726, 1361-665X. doi: 10.1088/1361-665X/26/2/025022. URL https://iopscience.iop.org/article/10.1088/1361-665X/26/2/025022.
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Follow-Up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now