[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125093-en":3,"doc-seo-125093-105":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":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},125093,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine Learning for Predicting Polarization Curves and Their Features","Important electrochemical parameters are often extracted from empirical measurements because analytical models, such as variants of the Butler-Volmer equation, do not capture key polarization-curve features accurately. Measuring polarization curves, however, requires time-consuming instrumentation. This thesis applies machine learning to predict polarization curves and specific features across different pH environments for an aluminium alloy AA6060 with 0.0043 wt% nickel, including corrosion potential, cathodic Tafel slope, corrosion current density, and critical pitting potential.","Master’s thesis  \nNT NU  \nNorwegian University of Science and Technology Faculty of Natural Sciences  \nDepartment of Mater ials Science and Engineering  \nMats Stensrud Skui  \nMachine Learning for Predicting Polarization Curves and Their Features  \nMaster’s thesis in Chemical Engineering and Biotechnology Supervisor: Andreas Erbe  \nCo-supervisor: Iman Taji June 2023  \nMats Stensrud Skui  \nMachine Learning for Predicting Polarization Curves and Their Features  \nMaster’s thesis in Chemical Engineering and Biotechnology Supervisor: Andreas Erbe  \nCo-supervisor: Iman Taji June 2023  \nNorwegian University of Science and Technology Faculty of Natural Sciences  \nDepartment of Materials Science and Engineering  \nPreface  \nThis work was conducted as part of the author’s master’s thesis at the Department of Materials Science and Engineering, Norwegian University of Science and Technology (NTNU) in Trondheim, during the spring of 2023 . I would like to thank my supervisor Andreas Erbe, co-supervisor Iman Taji, and laboratory assistants Anita Storsve and Marthe Folstad for their valuable assistance throughout this project. Additional thanks goes to Norsk Hydro ASA for providing samples for testing.  \nFinally, I would like to thank my good friends and fellow students, especially the ”Mattek gang”, for making these years so great.  \nAbstract  \nTypically, important electrochemical parameters are derived from empirical data. This is largely due to the fact that analytical models, such as various forms of the Butler-Volmer equation, often fall short in accurately capturing the important features. Unfortunately, obtaining these polarization curves requires utilization of time consuming instruments. Therefore, employing machine learning could prove advantageous. In this work, machine learning was applied in the attempt of predicting important polarization curves and some of their important features in various pH environments on an aluminium alloy AA6060 + 0.0043 wt% nickel. The polarization curve features under investigation were (i) the corrosion potential, (ii) the cathodic Tafel slope, (iii) the corrosion current density and (iv) the critical pitting potential.  \nDetermining the most suitable machine learning algorithm for a specific task can be challenging. Therefore, in this study, five distinct algorithms were employed. These included four decision tree algorithms, namely Random Forest, Categorical Boosting, eXtreme Gradient Boosting, and Light Gradient Boosting Machine, along with an Artificial Neural Network. The results delivered by these algorithms were comparable, though the Random Forest algorithm demonstrated a slight edge in terms of both accuracy and training speed. Random Forest’s marginally enhanced predictive abilities were explained by the small input feature dimension of solely pH and electrochemical potential. This lead to large amounts of unknown behaviour in the training data set as variables such as surface cracks and segregation were not accounted for. As a result, the error observed on unseen data was considerably larger, reaching many multiples of the error observed on the training data. The large variation in data lead to a smaller effect of the applied hyperparameter tuning of certain models. Thus, viability of using an Artificial Neural Network for the given machine learning task came under scrutiny, given its need for extensive hyperparameter tuning, which, despite the effort, only yielded average results compared to the other algorithms.  \nFinally, the algorithms demonstrated intriguing results, achieving a mean absolute percentage error of roughly 7% for the logarithmic current density (the target output) over the applied potential range. Furthermore, the algorithms showed strong predictive abilities for the features under investigation, with average errors of 5%, 13% and 19% for the corrosion potential, cathodic Tafel slope and corrosion current density, respectively. Additionally, the algorithms located the pitt","cbCaiuvjN1k4VJtb","https://ap.wps.com/l/cbCaiuvjN1k4VJtb","pdf",11361162,1,115,"English","en",105,"# Abstract\n## Purpose and motivation\n## Target features and algorithms\n## Results and model performance\n## Key findings and implications","[{\"question\":\"Why does the thesis use machine learning instead of analytical electrochemical models?\",\"answer\":\"Analytical models like the Butler-Volmer equation often fail to accurately capture important polarization-curve features. Machine learning is explored to improve prediction while avoiding time-consuming instrumentation.\"},{\"question\":\"Which polarization-curve features are predicted in this work?\",\"answer\":\"The study predicts corrosion potential, cathodic Tafel slope, corrosion current density, and critical pitting potential across different pH environments.\"},{\"question\":\"Which algorithms were compared, and what was the overall outcome?\",\"answer\":\"Five algorithms were used: Random Forest, Categorical Boosting, eXtreme Gradient Boosting, Light Gradient Boosting Machine, and an Artificial Neural Network. Results were comparable, with Random Forest showing a slight advantage in accuracy and training speed.\"}]","Machine Learning for Predicting Polarization Curves and Their Features | PDF",1785896601,290,{"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},"machine-learning-for-predicting-polarization-curves-and-their-features","",{"@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/machine-learning-for-predicting-polarization-curves-and-their-features/125093/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why does the thesis use machine learning instead of analytical electrochemical models?","Question",{"text":75,"@type":76},"Analytical models like the Butler-Volmer equation often fail to accurately capture important polarization-curve features. Machine learning is explored to improve prediction while avoiding time-consuming instrumentation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which polarization-curve features are predicted in this work?",{"text":80,"@type":76},"The study predicts corrosion potential, cathodic Tafel slope, corrosion current density, and critical pitting potential across different pH environments.",{"name":82,"@type":73,"acceptedAnswer":83},"Which algorithms were compared, and what was the overall outcome?",{"text":84,"@type":76},"Five algorithms were used: Random Forest, Categorical Boosting, eXtreme Gradient Boosting, Light Gradient Boosting Machine, and an Artificial Neural Network. Results were comparable, with Random Forest showing a slight advantage in accuracy and training speed.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]