[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127297-en":3,"doc-seo-127297-105":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},127297,2336475104957,"Seraphina","https://ap-avatar.wpscdn.com/avatar/22000c4c6bd8a5076e1?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786593998035447633",8,"Research & Report","Detecting and Explaining Performance Differences and Cycle Time Variability in Industrial Robots Using Multivariate Machine Learning Models","Modern material handling depends on automation, making it essential to explain why robots differ in speed and efficiency. This thesis analyzes performance differences and cycle time variability in customized gantry robots built by Cimcorp Oy, using real-world data from eight robots collected over extended operation. The dataset is grouped by working conditions and studied in two operating states with anonymized internal cycle signals. Supervised XGBoost regression predicts cycle times, while SHAP, Sobol sensitivity analysis, and PCA support interpretability, pattern discovery, and robot-level ranking for improved monitoring and decision-making.","BHAGYA LAKMINI KARUNARATHNE RANBANDI  \nDEWAGE  \nDetecting and Explaining Performance Differences and Cycle Time Variability in Industrial Robots Using Multivariate Machine Learning Models  \nDEGREE PROGRAMME IN DATA ENGINEERING  \nABSTRACT  \nRanbandi Dewage Bhagya Lakmini Karunarathne: Detecting and Explaining Performance Differences and Cycle Time Variability in Industrial Robots Using Multivariate Machine Learning Models  \nBachelor’s thesis Data Engineering July 2025  \nNumber of pages: 112  \nModern material handling relies heavily on automation, so it is important to understand why some robots complete tasks faster and more efficiently than others. This thesis looks at performance differences and cycle time variation in customized gantry robots built by Cimcorp Oy. The analysis uses machine learning models and real-world data collected from eight robots over a long period of operation.  \nThe full dataset was divided into eight groups based on different working conditions, and two operating states were chosen for detailed study. Each dataset included numeric signal data from individual robot cycles. Time-based features were removed to focus on internal signals, and all signal names were anonymised to protect the client’s confidentiality.  \nA supervised XGBoost regression model was used to predict cycle times in both selected conditions. The model gave high predictive accuracy , with R² values of 0.92 and 0.77. To understand which signals had the biggest impact on cycle time, SHAP (SHapley Additive exPlanations) and Sobol sensitivity analysis were used. PCA (Principal Component Analysis) was also used to find patterns in robot behaviour and show how different robots performed under the same conditions.  \nThese results show that machine learning, combined with explainable AI methods, can help predict and understand differences in robot performance. The model's reliability was further confirmed by testing on new unseen data, and an additional efficiency ranking method was developed using predicted versus actual cycle times to highlight robot level performance differences. This approach supports improved monitoring, decision making, and operational efficiency in industrial automation systems.  \nKeywords: Industrial automation, gantry robots, Cimcorp Oy, robot performance, cycle time prediction, machine learning, XGBoost, SHAP, Sobol sensitivity analysis, PCA, explainable AI  \nPREFACE  \nWorking on this thesis has been one of the most meaningful and challenging experiences of my studies in Data Engineering at Satakunta University of Applied Sciences (SAMK) . It brought together everything I have learned over the past few years and gave me the opportunity to apply that knowledge to areal-world industrial problem.  \nThe topic, which focuses on analysing performance differences and cycle time variability in customized gantry robots, was developed in close collaboration with Cimcorp Oy. From the very beginning, their team was actively involved in the process. We held weekly meetings where I received feedback, suggestions, and motivation that consistently pushed the work forward. That continuous support helped me maintain focus and aim for a higher quality of work than I could have achieved on my own.  \nThis project gave me a realistic view of how data is used in the industrial world not just to build models, but to solve practical problems, improve systems, and support decision-making. It also helped me grow personally. I learned how to manage long-term work, communicate technical findings clearly, and stay motivated through complex challenges.  \nI am deeply grateful to Cimcorp Oy for their trust, collaboration, and support throughout the project. I also want to thank my thesis supervisor at SAMK for providing clear guidance and encouragement whenever needed, and my data analytics teacher, whose advice helped sharpen the analytical side of the work.  \nLooking back, this project has been a key step in shaping my identity as a data enginee","cbCaifEnIO6RY6cb","https://ap.wps.com/l/cbCaifEnIO6RY6cb","pdf",5155679,1,112,"English","en",105,"# 1 Introduction\n## 1.1 Background and Motivation\n## 1.2 Company Overview: Cimcorp Oy\n## 1.3 Research Objectives and Questions\n## 1.4 Scope and Limitations\n## 1.5 Thesis Structure\n# 2 Literature Review\n## 2.1 Industrial Automation and Material Handling\n## 2.2 Gantry Robots and Performance Metrics\n## 2.3 Machine Learning in Industrial Robotics\n## 2.4 Explainable AI: SHAP, Sobol, and PCA\n## 2.5 Related Work and Research Gaps\n# 3 Data and Preprocessing\n## 3.1 Description of Operational Data\n## 3.2 Data Collection Period and Robot Context\n## 3.3 Data Grouping and Operational States\n## 3.4 Data Cleaning and Feature Engineering\n## 3.5 Anonymization and Confidentiality Considerations\n## 3.6 Conceptual Framework\n# 4 Machine Learning","[{\"question\":\"What problem does the thesis address in industrial robotics?\",\"answer\":\"It studies why some customized gantry robots complete tasks faster and more efficiently than others, focusing on performance differences and cycle time variability.\"},{\"question\":\"How is the dataset prepared for the analysis?\",\"answer\":\"The data from eight robots is divided into groups by working conditions, two operating states are selected for detailed study, time-based features are removed, and signal names are anonymised to protect confidentiality.\"},{\"question\":\"Which methods are used to predict cycle times and explain the results?\",\"answer\":\"An XGBoost regression model predicts cycle times, while SHAP and Sobol sensitivity analysis identify influential signals; PCA is used to find behavioral patterns across robots under the same conditions.\"}]","Detecting and Explaining Performance Differences and Cycle Time Variability in Industrial Robots Using Multivariate Machine Learning Models | PDF",1785938161,282,{"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},"detecting-and-explaining-performance-differences-and-cycle-time-variability-in-industrial-robots-using-multivariate-machine-learning-models","",{"@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/detecting-and-explaining-performance-differences-and-cycle-time-variability-in-industrial-robots-using-multivariate-machine-learning-models/127297/",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","2026-08-22","2026-08-05",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},"What problem does the thesis address in industrial robotics?","Question",{"text":76,"@type":77},"It studies why some customized gantry robots complete tasks faster and more efficiently than others, focusing on performance differences and cycle time variability.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is the dataset prepared for the analysis?",{"text":81,"@type":77},"The data from eight robots is divided into groups by working conditions, two operating states are selected for detailed study, time-based features are removed, and signal names are anonymised to protect confidentiality.",{"name":83,"@type":74,"acceptedAnswer":84},"Which methods are used to predict cycle times and explain the results?",{"text":85,"@type":77},"An XGBoost regression model predicts cycle times, while SHAP and Sobol sensitivity analysis identify influential signals; PCA is used to find behavioral patterns across robots under the same conditions.","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"]