Machine learning model for detecting hydrogen leakage from hydrogen pipeline using physical modeling

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Sep 4, 2023
Yuki Suzuki Jo Nakayama Tomoya Suzuki Tomoya Soma Yu-ichiro Izato Atusmi Miyake

Abstract

Hydrogen pipelines (HPL) are one of the hydrogen transportation systems for realizing a hydrogen society. Hydrogen leakage from HPL is a challenge because hydrogen has a wide flammable range and low minimum ignition energy. Thus, hydrogen leakage from the HPL must be rapidly detected, and appropriate actions should be taken. Leakage detection is important for safe operation of HPL. The basic leakage detection method for HPL involves monitoring the pressure and flow rate values of the sensors. However, in some cases, it is difficult to distinguish between non-leakage and leakage conditions using this method. In this study, we focus on a leakage detection method using machine learning (ML) based on the relationship between pressure and flow rate data. There are two challenges in applying the ML- based leak detection method to an HPL. First, there are insufficient operational data for ML during the process- design stage. Secondly, it is difficult to obtain the pressure and flow rate behaviors during hydrogen leakage because leakage does not occur frequently. Consequently, this study employed an unsupervised ML method based on data simulated using a physical model of the HPL. First, a physical model of the HPL (HPL model) was constructed, and an ML model for leak detection was constructed based on the data simulated by the HPL model. The leak detection capability of the ML model was verified by comparing the anomaly scores of the non-leakage and leakage conditions. From the results, the ML model can distinguish between non-leakage and leakage behaviors and identify leakage points under certain conditions. This method can contribute to the optimization of the sensors required for leak detection during the process design stage.

Abstract 275 | PDF Downloads 216

##plugins.themes.bootstrap3.article.details##

Keywords

hydrogen pipeline, leak detection, machine learning

References
ESI ITI GmbH, https://www.simulationx.com/.

Faye, O., Szpunar, J., & Eduok, U. (2022). A critical review on the current technologies for the generation, storage, and transportation of hydrogen. International Journal of Hydrogen Energy, Vol. 47, pp. 13771-13802. doi: 10.1016/j.ijhydene.2022.02.112

Hanae, D. (2011). Models, methods and approaches for the planning and design of the future hydrogen supply chain. International Journal of Hydrogen Energy, Vol. 37, pp. 5318-5327. doi: 10.1016/j.ijhydene.2011.08.041 Idachaba, F., & Tomomewo, O. (2023). Framework for generating pipeline leak datasets using PIPESIM. Journal of Pipeline Science and Engineering, pp. 1-30. doi: 10.1016/j.jpse.2023.100113

Imamura, T., Hamada, S., Mogi, T., Wada, Y., Horiguchi, S., Miyake, A., & Ogawa, T. (2008). Experimental investigation on the thermal properties of hydrogen jet flame and hot currents in the downstream region. International Journal of Hydrogen Energy, Vol. 33, pp. 3426-3435. doi: 10.1016/j.ijhydene.2008.03.063

Kawatsu, K. (2018). System-level modeling and simulation- based approach to risk assessment for space systems. An nual Reliability and Maintainability Symposium (pp. 1- 8), January 22-25. Reno, NV, USA. doi:10.1109/RAM. 2018.8463034

Nakayama, J., Suzuki, T., Owada, S., Izato, Y., Noguchi, K., & Miyake, A. (2022). Qualitative risk analysis of the overhead hydrogen piping at the conceptual process design stage. International Journal of Hydrogen Energy, Vol. 47, pp. 11725-11738. doi: 10.1016/j.ijhydene.2022.01.199 NEC, https://www.nec.com/en/global/solutions/ai/analyze/in variant.html

Mingbin, Z., Teng, H., Chenhui, L., Mingjia, C., Shui, J., Da vid, C., & Xuefang, L. (2021). Leak localization using d istributed sensors and machine learning for hydrogen rel eases from a fuel cell vehicle in a parking garage. Intern ational Journal of Hydrogen Energy, Vol. 46, pp. 1420- 1433. doi: 10.1016/j.ijhydene.2020.09.218

Omata, N., Satoh, D., Tsutsusmi, S., Kawatsu, K., & Abe, M. (2022). Model-based supervised sensor placement optimization to detect propellant leak in a liquid rocket engine. Acta Astronautica, Vol. 195, pp. 234-242. Doi: 10.1016/j.actaastro.2022.02.009

Rong-Heng, L., Ying-Ying, Z., & Bu-Dan, W. (2020). Towa rd a hydrogen society: Hydrogen and smart grid integrat ion. International Journal of Hydrogen Energy, Vol. 45, pp. 20164-20175. doi: 10.1016/j.ijhydene.2020.01.047

Soma, T., Ishii, K., Fukuta, Y., & Shiga, M. (2018). Applying of system analysis technology (SIAT) to J-PARC accelerator system. Proceedings of the 15th Annual Meeting of Particle Society of Japan (pp. 114-118), August 7-10. Nagaoka, Japan

Suzuki, T., Kawatsu, K., Shiota, K., Izato, Y., Komori, M., Sato, K., Takai, Y., Ninomiya, T., & Miyake, A. (2021). Quantitative risk assessment of a hydrogen refueling station using a dynamic physical model based on multi- physics system-level modeling. International Journal of Hydrogen Energy, Vol. 46, pp. 38923-38933. doi: 10.1016/j.ijhydene.2021.09.125 The Modelica Association. Modelica Language, https://mod elica.org/

Zhonglin, Z., Li, M., Shan, L., Jing, L., Hao, Z., & Tong, L. (2022). A semi-supervised leakage detection method dri ven by multivariate time series for natural gas gathering pipeline. Process Safety and Environmental Protection, Vol. 164, pp. 468-478. doi: 10.1016/j.psep.2022.06.036
Section
Special Session Papers