[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118630-en":3,"doc-seo-118630-105":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},118630,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Efficient Milling Quality Prediction with Explainable Machine Learning","An explainable machine learning approach is presented for predicting surface roughness in milling. Using a dataset collected from milling aluminum alloy 2017A, the study builds random forest regression models and applies feature importance techniques to interpret model behavior. The work delivers accurate predictions for multiple roughness targets and pinpoints redundant sensors, notably those measuring normal cutting force. Experiments show that removing certain sensors can reduce sensing and implementation cost without degrading predictive accuracy, improving machining cost-effectiveness through interpretable ML.","arXiv :2409 . 10203v1 [ cs .LG] 16 Sep 2024  \nEfficient Milling Quality Prediction with Explainable Machine Learning ⋆  \nDennis Gross ∗ Helge Spieker ∗ Arnaud Gotlieb ∗  \nRicardo Knoblauch ∗∗ Mohamed Elmansori ∗∗  \n∗ Simula Research Laboratory, Oslo, Norway  \n(e-mail: [dennis@simula.no](dennis@simula.no)).∗∗ Ecole Nationale Sup´erieure d’Arts et M´etiers, Aix-en-Provence,  \nFrance.  \nAbstract: This paper presents an explainable machine learning (ML) approach for predicting surface roughness in milling. Utilizing a dataset from milling aluminum alloy 2017A, the study employs random forest regression models and feature importance techniques. The key contributions include developing ML models that accurately predict various roughness values and identifying redundant sensors, particularly those for measuring normal cutting force. Our experiments show that removing certain sensors can reduce costs without sacrificing predictive accuracy, highlighting the potential of explainable machine learning to improve cost-effectiveness in machining.  \nKeywords: Machine Learning, Milling, Sustainable Production, Explainable ML  \n1. INTRODUCTION  \nMachine Learning (ML) significantly impacts the manufacturing industry (Jyeniskhan et al., 2023; Jiang, 2023) . Applying ML to manufacturing offers improved efficiency (Panzer and Bender, 2022), predictive maintenance (Wang et al., 2023), and better control over manufacturing quality (Kim et al., 2023) .  \nIn general, ML uses algorithms to interpret data and make predictions. It involves creating models that learn from a training data set and can be used to make predictions over unseen data. Before deployment, the trained ML model is tested on a test data set (Jiang, 2023) .  \nHowever, integrating trained ML models into industrial applications comes with challenges (Sampedro et al., 2022; Khuat et al., 2023) . One of these challenges is the ”blackbox” nature of many ML models, making it difficult for human experts to trust the prediction results of trained ML models (Kwon et al., 2023) . This is essential because, in manufacturing, the addition of sensors to a machine tool for generating data for the ML model can be costly, difficult to be implemented (necessity of trained staff), may interfere in the working area inside the machine, and even might modify machine’s behaviour (e.g. reducing machine rigidity with installation of a dynamometer) . (Dornfeld and Lee, 2008; Hawkridge et al., 2021) . The inclusion of a specific sensor value in the data collection phase for a prototype system does not necessarily imply its significance for the ML model’s predictive capabilities; hence, it might be reasonable to consider omitting this sensor feature in the real system if subsequent analysis shows it does not contribute meaningfully to the model’s perfor-  \n⋆ This work is funded by the European Union under grant agreement number 101091783 (MARS Project) and as part of the Horizon Europe HORIZON-CL4-2022-TWIN-TRANSITION-01-03 .  \nmance. Explainable ML encompasses methods that render the outputs of ML models comprehensible to humans, allowing for the analysis of how various features contribute to the model’s predictions (Rasheed et al., 2022; Tiddi and Schlobach, 2022; Theissler et al., 2022) .  \nIn this paper, we showcase with explainable ML methods that it is possible to train explainable ML models and to identify and remove already mounted non-significant sensors for high-quality roughness predicting ML models in the context of a milling system. The dataset for this paper was generated at MSMP - ENSAM, encompassing a series of surface milling operations on aluminium alloy 2017A. These operations employed a 20 mm diameter milling cutter, specifically the R217.69-1020.RE- 12-2AN model equipped with two XOEX120408FR-E06 H15 carbide inserts from SECO. The process utilized a synthetic emulsion comprising water and 5% Ecocool CS+ cutting fluid.  \nThe rest of the paper is organized as follows: Section 2 covers existi","cbCaikQV5gcV6Afz","https://ap.wps.com/l/cbCaikQV5gcV6Afz","pdf",792670,1,6,"English","en",105,"# Introduction\n## Explainable ML motivation in milling\n# Related Work","[{\"question\":\"What problem does the paper address?\",\"answer\":\"The paper addresses predicting milling surface roughness using explainable machine learning while making model decisions understandable to human experts.\"},{\"question\":\"Which dataset and materials are used for model training?\",\"answer\":\"The dataset is generated from milling aluminum alloy 2017A using a 20 mm diameter milling cutter with specified carbide inserts and a synthetic emulsion cutting fluid.\"},{\"question\":\"How does explainability help reduce costs?\",\"answer\":\"Feature importance analysis identifies redundant sensors, and experiments show that removing selected sensors—such as those for normal cutting force—can lower costs without sacrificing predictive accuracy.\"}]","Efficient Milling Quality Prediction with Explainable Machine Learning | PDF",1785684596,15,{"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},"efficient-milling-quality-prediction-with-explainable-machine-learning","",{"@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/efficient-milling-quality-prediction-with-explainable-machine-learning/118630/",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","2026-08-02",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 paper address?","Question",{"text":76,"@type":77},"The paper addresses predicting milling surface roughness using explainable machine learning while making model decisions understandable to human experts.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which dataset and materials are used for model training?",{"text":81,"@type":77},"The dataset is generated from milling aluminum alloy 2017A using a 20 mm diameter milling cutter with specified carbide inserts and a synthetic emulsion cutting fluid.",{"name":83,"@type":74,"acceptedAnswer":84},"How does explainability help reduce costs?",{"text":85,"@type":77},"Feature importance analysis identifies redundant sensors, and experiments show that removing selected sensors—such as those for normal cutting force—can lower costs without sacrificing predictive accuracy.","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},[94,98,102,106,111,115,120,123,128,131,135],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"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":107,"slug":138},19,"General","general"]