[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126051-en":3,"doc-seo-126051-105":31,"detail-sidebar-cat-0-en-105":93},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126051,962084928904,"Asher","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Predictive Analytics for the Development of Green Lubricants Using Machine Learning - June 2024","This master’s thesis develops predictive analytics to support the development of green lubricants using machine learning. The work covers tribological target variables such as coefficient of friction and specific wear rate, builds and cleans a dataset, and applies feature engineering including feature selection and extraction. Multiple learning approaches are evaluated, from linear regression and decision trees to ensemble methods and neural networks, with model validation and performance metrics. Results are analyzed further through bootstrapping, special cases, and interpretation techniques including SHAP, followed by a discussion of challenges, imbalance, and overfitting.","Master’s thesis  \nNT NU  \nNorwegian University of Science and Technology Faculty of Engineering  \nDepartment of ICT and Natural Sciences  \nNicolai A. Olsen  \nPredictive Analytics for the Development of Green Lubricants Using Machine Learning  \nMaster’s thesis in Ingeniørvitenskap og IKT Supervisor: Nuria Espallargas  \nJune 2024  \nNicolai A. Olsen  \nPredictive Analytics for the Development of Green Lubricants Using Machine Learning  \nMaster’s thesis in Ingeniørvitenskap og IKT Supervisor: Nuria Espallargas  \nJune 2024  \nNorwegian University of Science and Technology Faculty of Engineering  \nDepartment of ICT and Natural Sciences  \nTable of Contents  \nList of Figures v  \nList of Tables vii  \n1 Introduction 1  \n1.1 Background ........................................ 1  \n1.2 The Shift Towards Environmentally Friendly Lubricants ............... 1  \n1.3 Problem Statement .................................... 2  \n2 Structure of the Thesis 3  \n2.1 Introduction ........................................ 3  \n2.2 Theoretical Foundations ................................. 3  \n2.3 Tribological Analysis and Predictive Modeling of Lubricants ............. 3  \n2.4 Methodology ....................................... 3  \n2.5 Utilization of Theoretical Framework .......................... 4  \n2.6 Results ........................................... 4  \n2.7 Discussion ......................................... 4  \n2.8 Conclusions ........................................ 4  \n2.9 Bibliography and Appendix ............................... 4  \n3 Theoretical Foundations 5  \n3.1 Machine Learning ..................................... 5  \n3.1.1 Understanding the Domain ........................... 5  \n3.1.2 Data Exploration ................................. 5  \n3.2 Feature Engineering ................................... 6  \n3.2.1 Feature Selection ................................. 6  \n3.2.2 Feature Extraction ................................ 7  \n3.3 Correlation does not equal Causation .......................... 8  \n3.4 Clustering ......................................... 8  \n3.4.1 Nearest Neighbor Algorithm ........................... 8  \n3.4.2 Bootstrapping with Nearest Neighbor Algorithm ............... 9  \n3.5 Different Machine Learning Models ........................... 9  \n3.5.1 Decision Trees .................................. 9  \n3.5.2 Random Forest .................................. 9  \n3.5.3 Boosting ...................................... 10  \n3.5.4 Gradient Boosting ................................ 10  \n3.5.5 Support Vector Machines ............................ 10  \n3.5.6 Feedforward neural networks .......................... 11  \n3.6 Model Validation in Machine Learning ......................... 12  \n3.7 Summary ......................................... 14  \n4 Tribological Analysis and Predictive Modeling of Lubricants 16  \n4.1 Coefficient of Friction .................................. 16  \n4.2 Specific Wear Rate .................................... 17  \n4.3 Previous Data Collection ................................ 17  \n4.3.1 Simplified Molecular-Input Line-Entry System ................ 18  \n4.4 Previous Studies on Machine Learning in Tribology .................. 19  \n5 Methodology 20  \n5.1 Introduction ........................................ 20  \n5.2 Building the dataset ................................... 20  \n5.3 Data Exploration ..................................... 21  \n5.4 Data cleaning ....................................... 21  \n5.4.1 Splitting the data ................................ 22  \n5.4.2 Feature Reduction ................................ 22  \n5.4.3 Data Imbalance .................................. 24  \n5.5 Graphical Representation of Methodology ....................... 25  \n5.6 Machine Learning Models ................................ 27  \n6 Utilization of Theoretical Framework 29  \n6.1 Supervised Learning Approach ............................. 29  \n6.2 Domain Expertise in Feature Engineering ....................... 29  \n6.3 Data Cle","cbCaijmTRZ6WkOyh","https://ap.wps.com/l/cbCaijmTRZ6WkOyh","pdf",9756272,6,1,86,"English","en",105,"# 1 Introduction\n## 1.1 Background\n## 1.2 The Shift Towards Environmentally Friendly Lubricants\n## 1.3 Problem Statement\n# 2 Structure of the Thesis\n## 2.2 Theoretical Foundations\n## 2.3 Tribological Analysis and Predictive Modeling of Lubricants\n## 2.4 Methodology\n## 2.6 Results\n## 2.8 Conclusions\n## 2.9 Bibliography and Appendix\n# 3 Theoretical Foundations\n## 3.1 Machine Learning\n## 3.2 Feature Engineering\n## 3.4 Clustering\n## 3.5 Different Machine Learning Models\n## 3.6 Model Validation in Machine Learning\n# 4 Tribological Analysis and Predictive Modeling of Lubricants\n## 4.1 Coefficient of Friction\n## 4.2 Specific Wear Rate\n## 4.3 Previous Data Collection\n## 4.4 Previous Studies on Machine Learning in Tribology\n# 5 Methodology\n## 5.2 Building the dataset\n## 5.4 Data cleaning\n## 5.5 Graphical Representation of Methodology\n## 5.6 Machine Learning Models\n# 6 Utilization of Theoretical Framework\n## 6.1 Supervised Learning Approach\n## 6.2 Domain Expertise in Feature Engineering\n## 6.4 Model Performance Metrics\n# 7 Results\n## 7.1 Initial Data Exploration\n## 7.2 Selected Molecular Descriptors\n## 7.4 Model Performance\n## 7.5 Specific Wear Rate\n## 7.6 Concluding remarks from the results\n# 8 Discussion\n## 8.1 Analysis\n## 8.2 Model Interpretation\n## 8.3 Model Interpretation using SHAP\n## 8.4 Support Vector Regression: Unexpected Challenges\n## 8.5 Regression Imbalance\n## 8.8 Overfitting","[{\"question\":\"Which tribological properties are predicted in the thesis?\",\"answer\":\"The thesis focuses on predicting the coefficient of friction and the specific wear rate using machine learning models.\"},{\"question\":\"How is feature engineering handled before training models?\",\"answer\":\"Feature engineering includes feature selection and feature extraction, supported by exploratory analysis to understand the domain and dataset characteristics.\"},{\"question\":\"What model interpretation methods are used to explain predictions?\",\"answer\":\"Model interpretation includes traditional approaches and interpretation using SHAP to assess feature contributions. The discussion also covers unexpected challenges and limitations for specific models.\"}]","Predictive Analytics for the Development of Green Lubricants Using Machine Learning - June 2024 | PDF",1785902791,217,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"predictive-analytics-for-the-development-of-green-lubricants-using-machine-learning-june-2024","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/predictive-analytics-for-the-development-of-green-lubricants-using-machine-learning-june-2024/126051/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Which tribological properties are predicted in the thesis?","Question",{"text":77,"@type":78},"The thesis focuses on predicting the coefficient of friction and the specific wear rate using machine learning models.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How is feature engineering handled before training models?",{"text":82,"@type":78},"Feature engineering includes feature selection and feature extraction, supported by exploratory analysis to understand the domain and dataset characteristics.",{"name":84,"@type":75,"acceptedAnswer":85},"What model interpretation methods are used to explain predictions?",{"text":86,"@type":78},"Model interpretation includes traditional approaches and interpretation using SHAP to assess feature contributions. The discussion also covers unexpected challenges and limitations for specific models.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]