[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121662-en":3,"doc-seo-121662-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121662,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","A Machine Learning Pressure Emulator for Hydrogen Embrittlement - Abstract and Introduction Overview","A physics-informed machine learning approach predicts gas pressure on the inner wall of pipelines carrying hydrogen-natural-gas blends to mitigate hydrogen embrittlement risks. High-fidelity PDE simulators are accurate yet time- and computation-intensive, motivating an ML surrogate trained on simulation data. The study targets pipeline surveillance by forecasting inner-wall pressure and uses comparisons to show physics-based modeling outperforms purely data-driven methods while enforcing physical constraints of the gas-flow system.","A Machine Learning Pressure Emulator for Hydrogen Embrittlement  \nMinh Triet Chau 1 Joo Lucas de Sousa Almeida 2 Elie Alhajjar 3 Alberto Costa Nogueira Junior 2  \narXiv :2306 . 13116v1 [ cs .LG] 22 Jun 2023  \nAbstract  \nA 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 physicsinformed 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.  \nUsing 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.  \n1. Introduction  \nClimate change requires clean and effective energy storage to replace gasoline, coal, or natural gas (NG) . Batteries area clean carrier but do not have sufficient energy density for sectors such as cement, steel, and long-haul transport (Emma et al., 2021) . For those industries, one option that has received considerable attention is low-carbon hydrogen (McQueen et al., 2020), which can store a large amount of energy and does not release greenhouse pollutants in combustion. However, the inefficiency of green H2 manufacturing process is one of the biggest obstacles to its dissemination (Joshi et al., 2022) . While finding an environmentally friendly and affordable way to produce H2 is along-term task, it should not deny us hydrogen's immediate benefit.  \nOne viable strategy is blending H2 with NG (HCNG) to  \n1Independent researcher 2IBM Research Brazil 3RAND Corporation, USA. Correspondence to: Minh Triet Chau \u003C[s6michau@uni-bonn.de](s6michau@uni-bonn.de) > .  \nAccepted after peer-review at the 1st workshop on Synergy of Scientific and Machine Learning Modeling, SynS & ML ICML, Honolulu, Hawaii, USA. July, 2023 . Copyright 2023 by the author(s) .  \nreduce emissions when burning (Melaina et al., 2013) . By increasing the volume of H2 from 0% to 15%, up to 50% reduction in CO2 emission was observed (Pandey et al., 2022) . Blends with less than 20% H2 by volume can be transmitted by repurposing existing natural gas pipelines, which are 67% cheaper than building new ones (Peter et al., 2020) . However, a major drawback with repurposed pipelines is during daily consumption, gas pressure may reach excessive values that lead to hydrogen diffusion through the most current pipeline wall materials (EU Agency for the Cooperation of Energy Regulators, 2021) . Specifically, due to friction incurred on the inner wall caused by the gas flow, atomic H can permeate into its metal lattice, reducing the stress required for cracks to form. This phenomenon, known as hydrogen embrittlement (HE), causes pipelines to be prone to leaking H2 , which can lead to catastrophic events due to H2 ignition in the presence of air, as well as some other complications like decreasing the upper stratospheric ozone mixing ratios (Nicola et al., 2022) . Such a risk is currently prohibiting HCNG from becoming more popular. In Germany, where it is most widely adopted, HCNG only accounts for 10% of demand per capita (Dolci et al., 2019) .  \nPreventing HE requires monitoring, operational pressure management, and pipeline maintenance (Ronevich & San Marchi, 2019) . To the best of our knowledge, few works frame pipeline monitoring works from a data driven perspective (Spandonidis et al., 2022) while the rest rely on signals from sensors and hardware (Du et al., 2016 ; Zhu et al., 2017 ; Aba et al., 2021) . To apply ML to this problem, there are two steps involved. The first is addressing the prediction task of the gas flow pressure. The next step is to use the predicted press","cbCaiah4LYp6mtjM","https://ap.wps.com/l/cbCaiah4LYp6mtjM","pdf",347516,1,6,"English","en",105,"# Introduction\n## Hydrogen blending and embrittlement risk\n## Monitoring and modeling pipeline pressure\n# Problem\n## Physics viewpoint: turbulent flow and Reynolds number\n## Pressure field prediction setup","[{\"question\":\"Why is hydrogen embrittlement a concern in hydrogen-natural gas pipeline blends?\",\"answer\":\"Hydrogen can permeate into metal lattice under operational pressure and frictional effects, reducing the stress needed for cracks and leading to leaks and potentially catastrophic ignition events.\"},{\"question\":\"What is the main contribution of the proposed work?\",\"answer\":\"The work proposes a physics-informed machine learning model to predict future gas pressure values on the pipeline inner wall using simulation data, supporting pipeline surveillance.\"},{\"question\":\"How does the physics-informed model compare to purely data-driven methods?\",\"answer\":\"Results indicate the physics-based approach outperforms the purely data-driven approach and satisfies physical constraints governing the gas-flow system.\"}]","A Machine Learning Pressure Emulator for Hydrogen Embrittlement - Abstract and Introduction Overview | PDF",1785806049,15,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-machine-learning-pressure-emulator-for-hydrogen-embrittlement-abstract-and-introduction-overview","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-machine-learning-pressure-emulator-for-hydrogen-embrittlement-abstract-and-introduction-overview/121662/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is hydrogen embrittlement a concern in hydrogen-natural gas pipeline blends?","Question",{"text":75,"@type":76},"Hydrogen can permeate into metal lattice under operational pressure and frictional effects, reducing the stress needed for cracks and leading to leaks and potentially catastrophic ignition events.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the main contribution of the proposed work?",{"text":80,"@type":76},"The work proposes a physics-informed machine learning model to predict future gas pressure values on the pipeline inner wall using simulation data, supporting pipeline surveillance.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the physics-informed model compare to purely data-driven methods?",{"text":84,"@type":76},"Results indicate the physics-based approach outperforms the purely data-driven approach and satisfies physical constraints governing the gas-flow system.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]