[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-504316-105":59,"doc-detail-504316-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","multi-objective-optimization-of-an-integrated-bio-hydrogen-liquefaction-system-using-surrogate-assisted-nsga-ii-and-multiagent-reinforcement-learning","Multi-Objective Optimization of an Integrated Bio-Hydrogen Liquefaction System Using Surrogate-Assisted NSGA-II and MultiAgent Reinforcement Learning","","Hydrogen liquefaction is an energy-intensive step in the hydrogen supply chain, requiring coordinated multi-objective integration and optimization. The paper develops a thermoeconomic framework for an integrated bio-hydrogen liquefaction system combining a two-loop Rankine cycle with an absorption chiller to recover waste heat for on-site power and pre-cooling. An ANN surrogate model trained on Aspen HYSYS simulations predicts specific energy consumption, exergy efficiency, and levelized cost of hydrogen with strong test performance. Optimization is performed using NSGA-II and PPO-based multi-agent reinforcement learning, where MARL yields broader Pareto trade-off exploration and reduces SEC, increases exergy efficiency, and lowers LCOH versus baseline conditions.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/multi-objective-optimization-of-an-integrated-bio-hydrogen-liquefaction-system-using-surrogate-assisted-nsga-ii-and-multiagent-reinforcement-learning/504316/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/multi-objective-optimization-of-an-integrated-bio-hydrogen-liquefaction-system-using-surrogate-assisted-nsga-ii-and-multiagent-reinforcement-learning/504316.png","ImageObject",300,407,{"name":92,"@type":93},"4398046744996","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-22","2026-10-03",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What integrated system configuration is optimized in the study?","Question",{"text":112,"@type":113},"The study optimizes an integrated bio-hydrogen liquefaction system that combines a two-loop Rankine cycle and an absorption chiller for waste-heat recovery for on-site power generation and pre-cooling.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How is the optimization model built and what does the surrogate predict?",{"text":117,"@type":113},"An ANN-based surrogate model is trained using Aspen HYSYS simulations to predict specific energy consumption (SEC), exergy efficiency, and levelized cost of hydrogen (LCOH).",{"name":119,"@type":110,"acceptedAnswer":120},"How do NSGA-II and PPO-based multi-agent reinforcement learning differ in optimization results?",{"text":121,"@type":113},"Both are used for multi-objective optimization, but MARL demonstrates a broader capability for exploring Pareto solution trade-offs. The selected optimal conditions report SEC, exergy efficiency, and LCOH improvements relative to initial conditions.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},504316,1791259249,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":66,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":133,"file_id":134,"file_url":135,"file_type":136,"file_size":137,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":138,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144},4398046744996,"Process Integration and Optimization for Sustainability [https://doi.org/10.1007/s41660-026-00863-1](https://doi.org/10.1007/s41660-026-00863-1)  \nORIGINAL RESEARCH PAPER  \nMulti-Objective Optimization of an Integrated Bio-Hydrogen Liquefaction System Using Surrogate-Assisted NSGA-II and MultiAgent Reinforcement Learning  \nMochamad Yusuf Efendi1 · Erdiyanto Munandar1 · Misri Gozan2 · Lubi Rahadiyan3 · Muhammad Aziz4 · Nasruddin Nasruddin1  \nReceived: 28 April 2026 / Revised: 6 July 2026 / Accepted: 13 August 2026  \n© The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2026  \nAbstract  \nHydrogen liquefaction is a highly energy-intensive step in the supply chain that requires effective multi-objective integration and optimization processes. This study presents a thermoeconomic framework for an integrated bio-hydrogen liquefaction system that combines a two-loop Rankine cycle and an absorption chiller to recover waste heat for on-site power generation and pre-cooling. An artificial neural network (ANN)-based surrogate model was developed from Aspen HYSYS simulations to predict specific energy consumption (SEC), exergy efficiency, and levelized cost of hydrogen (LCOH) . The developed surrogate model reaches the coefficient of determination (R2) values up to 0.968 for thermodynamic metricsand a robust global average test R2 of 0.89. The model is then optimized using two multi-objective approaches, namely the non-dominated sorting genetic algorithm II (NSGA-II) and proximal policy optimization (PPO)-based multi-agent reinforcement learning (MARL) . MARL demonstrates a broader capability for exploring Pareto solutions trade-offs. The selected optimal conditions resulted in an SEC of 4.44 kWh/kg-LH₂, an exergy efficiency of 71.98%, and an LCOH of 2.88 USD/kg-LH₂ . Compared to the initial conditions, the SEC decreased by 39.1%, the exergy efficiency increased by 2.66%, and the LCOH decreased by 3.5%. These results demonstrate the potential of MARL as a complementary approach for optimizing integrated hydrogen liquefaction systems.  \n Nasruddin Nasruddin[nasruddin@eng.ui.ac.id](nasruddin@eng.ui.ac.id)  \n1 Department of Mechanical Engineering, Faculty of Engineering, Universitas Indonesia, Kampus Baru UI, Depok, West Java 16424, Indonesia  \n2 Department of Chemical Engineering, Faculty of Engineering, Universitas Indonesia, Kampus Baru UI, Depok, West Java 16424, Indonesia  \n3 Pertamina New and Renewable Energy, Graha Pertamina, Gambir, Jakarta 10110, Indonesia  \n4 Institute of Industrial Science, The University of Tokyo, Tokyo 153-8505, Japan  \nGraphical Abstract  \nKeywords ANN surrogate modeling · Dual-loop Rankine cycle · Hydrogen liquefaction · Multi-agent reinforcement learning · Multi-objective optimization · NSGA-II  \nIntroduction  \nThe global energy landscape is undergoing rapid change as decarbonization targets intensify and the demand for lowcarbon energy carriers grows (Paramati et al. 2022) . The World Meteorological Organization reported that 2024 was the warmest year on record, with a global mean near-surface temperature approximately 1.55 ± 0.13 °C above the 1850– 1900 baseline, highlighting the need to reduce greenhouse gas emissions (WMO, 2024). Afundamental transformation of the global energy infrastructure is necessary to achieve net-zero carbon emissions by the year 2050, encompassing deep decarbonization of electricity production, widespread deployment of sustainable energy technologies, advanced waste heat recovery techniques, and the application of pollutant capture technologies, along with the increased use of hydrogen (H₂) as a clean energy vehicle (Fam and Fam 2024) .  \nAmong these strategies, hydrogen stands out due to its high gravimetric energy density (141.88 MJ/kg), which is 3–7 times greater than that of conventional fossil fuels (~ 44 MJ/kg) (Qureshi et al. 2022) . The global hydrogen market is projected to expand significantly, potentially reaching 621 million tons by 2050 (Zhang","cbCaipaaCylZbeI9","https://ap.wps.com/l/cbCaipaaCylZbeI9","pdf",4203351,25,"English","# Abstract\n# Introduction\n## Energy transition and hydrogen demand\n## Hydrogen production pathways and storage challenges\n## Liquefaction energy requirements and efficiency gaps\n## Proposed integration strategies and optimization approaches","[{\"question\":\"What integrated system configuration is optimized in the study?\",\"answer\":\"The study optimizes an integrated bio-hydrogen liquefaction system that combines a two-loop Rankine cycle and an absorption chiller for waste-heat recovery for on-site power generation and pre-cooling.\"},{\"question\":\"How is the optimization model built and what does the surrogate predict?\",\"answer\":\"An ANN-based surrogate model is trained using Aspen HYSYS simulations to predict specific energy consumption (SEC), exergy efficiency, and levelized cost of hydrogen (LCOH).\"},{\"question\":\"How do NSGA-II and PPO-based multi-agent reinforcement learning differ in optimization results?\",\"answer\":\"Both are used for multi-objective optimization, but MARL demonstrates a broader capability for exploring Pareto solution trade-offs. The selected optimal conditions report SEC, exergy efficiency, and LCOH improvements relative to initial conditions.\"}]","Multi-Objective Optimization of an Integrated Bio-Hydrogen Liquefaction System Using Surrogate-Assisted NSGA-II and MultiAgent Reinforcement Learning | PDF",1791065972,63]