[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121856-en":3,"doc-seo-121856-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},121856,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","A Novel Deep Reinforcement Learning (DRL) Algorithm to Apply Artificial Intelligence-Based Maintenance in Electrolysers","Hydrogen can be generated with electrolysers, but safe and cost-effective operation depends on defining appropriate maintenance strategies. Predictive maintenance often relies on potentially faulty sensor data, which may create false information and trigger mistimed actions. This work applies artificial intelligence to predict target sensor readings using data from another instrument in the process. A novel Deep Reinforcement Learning (DRL) method selects the best feature(s) from measured electrolyser data and uses them in an LSTM network for forecasting. Results show near-perfect correlation (0.99) and low RMSE (0.1351).","algorithms  \nArticle  \nA Novel Deep Reinforcement Learning (DRL) Algorithm to Apply Artificial Intelligence-Based Maintenance in Electrolysers  \nAbiodun Abiola *, Francisca Segura Manzano * and Jos² Manuel Andójar   \nCitation: Abiola, A.; Manzano, F.S.; Andújar, J.M. A Novel Deep Reinforcement Learning (DRL)  \nAlgorithm to Apply Artificial Intelligence-Based Maintenance in Electrolysers. Algorithms 2023, 16, 541 . [https://doi.org/10.3390/a16120541](https://doi.org/10.3390/a16120541)  \nAcademic Editors: Van-Hai Bui, Sina Zarrabian and Paul Kump  \nReceived: 30 September 2023  \nRevised: 17 November 2023  \nAccepted: 21 November 2023  \nPublished: 27 November 2023  \nCopyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \nReseaarch Centre on Technology, Energy and Sustainability (CITES), University of Huelva, Campus El Carmen, 21071 Huelva, Spain; andujar@diesia.uhu.es  \n* Correspondence: [abiodunolatokunbo.abiola@alumni.urv.cat](abiodunolatokunbo.abiola@alumni.urv.cat) (A.A.); francisca.segura@diesia.uhu.es (F.S.M.)  \nAbstract: Hydrogen provides a clean source of energy that can be produced with the aid of electrolysers. For electrolysers to operate cost-effectively and safely, it is necessary to define an appropriate maintenance strategy. Predictive maintenance is one of such strategies but often relies on data from sensors which can also become faulty, resulting in false information. Consequently, maintenance will not be performed at the right time and failure will occur. To address this problem, the artificial intelligence concept is applied to make predictions on sensor readings based on data obtained from another instrument within the process. In this study, a novel algorithm is developed using Deep Reinforcement Learning (DRL) to select the best feature(s) among measured data of the electrolyser, which can best predict the target sensor data for predictive maintenance. The features are used as input into a type of deep neural network called long short-term memory (LSTM) to make predictions. The DLR developed has been compared with those found in literatures within the scope of this study. The results have been excellent and, in fact, have produced the best scores. Specifically, its correlation coefficient with the target variable was practically total (0.99) . Likewise, the root-mean-square error (RMSE) between the experimental sensor data and the predicted variable was only 0.1351 .  \nKeywords: hydrogen technology; PEM electrolyser; predictive maintenance; artificial intelligence; reinforcement learning; neural network; long short-term memory (LSTM)  \n1. Introduction  \nThe hydrogen technology deployment is heavily dependent on cost-effectiveness. Regarding hydrogen-based microgrids, their economic impact is conditioned by costs of different nature (investment costs, operation and maintenance costs, and replacement costs) [1] . Among them, operation and maintenance are the ones that are repeated along the lifespan and affect the replacement costs. If equipment is not properly maintained, it arrives early at the end of its lifespan, and the equipment will need to be replaced much earlier.  \nIn the case of electrolysers, they can only function effectively to produce hydrogen at the desired parameters if their components do not fail during the period of operation. Failures can be avoided if they are detected early during operation and resolved. The process of taking actions to monitor, detect, and resolve failures of a system is known as maintenance practice, as defined according to EN13306 [2] . Adequate maintenance of electrolysers will guarantee optimum operation at the designed level of efficiency, long-term cost-effectiveness, and saf","cbCaicmcXGqtmQJP","https://ap.wps.com/l/cbCaicmcXGqtmQJP","pdf",9253153,1,27,"English","en",105,"# Introduction\n## Maintenance strategies for electrolysers\n# Problem setting: predictive maintenance and sensor faults\n# Proposed approach: DRL feature selection and LSTM prediction\n# Method comparison and evaluation results","[{\"question\":\"Why is maintenance important for electrolysers in hydrogen systems?\",\"answer\":\"Electrolysers must operate safely and efficiently at designed parameters. Proper maintenance prevents early end-of-life and reduces the need for premature replacement.\"},{\"question\":\"What problem does the proposed approach address in predictive maintenance?\",\"answer\":\"Sensor readings used for predictive maintenance can be faulty, leading to false information. This can cause maintenance actions to be performed at the wrong time and failures to occur.\"},{\"question\":\"How does the novel DRL algorithm make predictions for maintenance?\",\"answer\":\"The method selects the best feature(s) from measured electrolyser data and feeds them into an LSTM deep neural network to predict target sensor data, supporting predictive maintenance.\"}]","A Novel Deep Reinforcement Learning (DRL) Algorithm to Apply Artificial Intelligence-Based Maintenance in Electrolysers | PDF",1785807262,68,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"a-novel-deep-reinforcement-learning-drl-algorithm-to-apply-artificial-intelligence-based-maintenance-in-electrolysers","",{"@graph":36,"@context":86},[37,54,69],{"@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-novel-deep-reinforcement-learning-drl-algorithm-to-apply-artificial-intelligence-based-maintenance-in-electrolysers/121856/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is maintenance important for electrolysers in hydrogen systems?","Question",{"text":76,"@type":77},"Electrolysers must operate safely and efficiently at designed parameters. Proper maintenance prevents early end-of-life and reduces the need for premature replacement.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What problem does the proposed approach address in predictive maintenance?",{"text":81,"@type":77},"Sensor readings used for predictive maintenance can be faulty, leading to false information. This can cause maintenance actions to be performed at the wrong time and failures to occur.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the novel DRL algorithm make predictions for maintenance?",{"text":85,"@type":77},"The method selects the best feature(s) from measured electrolyser data and feeds them into an LSTM deep neural network to predict target sensor data, supporting predictive maintenance.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]