Systematizing Data Preparation in Smart Manufacturing via Axiomatic Design: A Toolkit Integrating GUI and Agentic AI

Systematizing Data Preparation in Smart Manufacturing via Axiomatic Design: A Toolkit Integrating GUI and Agentic AI | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Systematizing Data Preparation in Smart Manufacturing via Axiomatic Design: A Toolkit Integrating GUI and Agentic AI Angkush Kumar Ghosh, Saman Fattahi, Yu Kogawara, Bahman Azarhoushang, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8872511/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Data serves as the primary driving force behind smart manufacturing, yet the transition from raw data to analysis-ready data remains a critical operational bottleneck. Often dismissed as janitorial work, data preparation consumes a disproportionate amount of analytical effort due to a reliance on fragmented, ad-hoc, and project-specific solutions. To overcome these barriers, this study proposes a systematic, requirements-driven approach grounded in the principles of axiomatic design. By cross-examining diverse manufacturing experiments, recurring operational needs were identified and mapped to a set of modular functional requirements. This theoretical foundation was materialized into a dual-approach toolkit that integrates two complementary interaction models: an interactive graphical user interface and an agentic artificial intelligence system. While the former ensures reproducibility and ground truth validation through granular manual control, the latter leverages a large language model to orchestrate complex tool sequences via natural language. The applicability of this unified architecture is validated through a comprehensive micro-drilling case study, demonstrating the seamless execution of several data preparation tasks. The findings of this study highlight the synergistic relationship between user experience and agent experience. By offering a robust, human-in-the-loop pathway, the developed system transforms data preparation from a peripheral burden into a rigorous scientific discipline. Consequently, this approach democratizes access to advanced data workflows for diverse manufacturing environments. Thus, this study contributes to the advancement of fundamental data practices within the smart manufacturing domain. Mechanical Engineering Industrial Engineering Systems Engineering Data Preparation Systems GUI Agentic AI OpenAI UX/AX Smart Manufacturing Full Text Additional Declarations The authors declare no competing interests. Supplementary Files S1.docx Visual screenprints and operational flowcharts for the launcher and tools underlying the developed GUI-based toolkit S2.docx Visual screenprints of the GUI- and Agentic AI-based toolkit, demonstrating the application scenario Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8872511","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":590968125,"identity":"2f34580b-7348-4ee0-8cca-1ac5bfcf31fc","order_by":0,"name":"Angkush Kumar Ghosh","email":"","orcid":"https://orcid.org/0000-0002-9644-177X","institution":"Division of Mechanical and Electrical Engineering, Kitami Institute of Technology, Japan","correspondingAuthor":false,"prefix":"","firstName":"Angkush","middleName":"Kumar","lastName":"Ghosh","suffix":""},{"id":590985233,"identity":"4fad1947-40fe-48b1-bca1-453fea4d66b4","order_by":1,"name":"Saman Fattahi","email":"","orcid":"https://orcid.org/0000-0002-3355-1576","institution":"KSF Institute for Advanced Manufacturing, Furtwangen University, Germany","correspondingAuthor":false,"prefix":"","firstName":"Saman","middleName":"","lastName":"Fattahi","suffix":""},{"id":590985234,"identity":"954cd9c4-e5d6-48de-a066-c6897a14bc74","order_by":2,"name":"Yu Kogawara","email":"","orcid":"","institution":"Machine Intelligence and Biomechanics Course, Kitami Institute of Technology, Japan","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Kogawara","suffix":""},{"id":590985235,"identity":"38d5bd95-f799-4dd2-86d6-481b74c35414","order_by":3,"name":"Bahman Azarhoushang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYHACxsdAgh9ZxICQFmZjICHZwMBMvBY2adK08PcfflZd8IdBwuD2+WMSP3fUypkzMG98gE+LxIFjZrdntgG1nEtmk+w9c9zYsoGtGL81BxvMbvM2/K8zOMPMdoO37VjihgM8ZhL4dMgfZv9WzANyGFDLzb9tx+qBWsx/4NNicIzHjJmHDaLlNm9bTYIB0Ba87jI8w1MszQv0i+QZZvPfsm0HDDccZivG6zC588c3fgY5jO8M42PDt2118gbHmzd+wGsNGjjMgBQ/xIE6EtWPglEwCkbBSAAAgVBGc2Sxbf8AAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-4393-4500","institution":"Department of Microsystems Engineering (IMTEK), University of Freiburg, Freiburg, Germany","correspondingAuthor":true,"prefix":"","firstName":"Bahman","middleName":"","lastName":"Azarhoushang","suffix":""},{"id":590985236,"identity":"c1a57b51-899a-42f6-b00a-824753cfd305","order_by":4,"name":"Takuya Okamoto","email":"","orcid":"","institution":"Department of Creative Engineering, National Institute of Technology (KOSEN), Kushiro College, Japan","correspondingAuthor":false,"prefix":"","firstName":"Takuya","middleName":"","lastName":"Okamoto","suffix":""},{"id":590985237,"identity":"bf8b0680-4a67-4542-8924-e385362dcdba","order_by":5,"name":"Sharifu Ura","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDElEQVRIie3RsWqDQBjA8e840EWdE4T6Cjq3sQ/S5QtCNoduhQZ6QbhsmQ0NzVs4C0Ky5A1uSd4gUCiBQunn1SGQXEK3Uu7voOj9uE8FsNn+Yi4XHJ4AHBc4IN1wgAn9pDudxhmRDa3kLUFNJuIqYbK9oENvc2GxLm7Y5P3xrYoCIvHukD4EwKdbGKfAX89LIkU4r1QiiSBilks92CoDtqhNRIR+pVhLakSey2hHxKmBlWjc5dNfqPuOvHS7fF0kMvSFGnaDNT+ESTPpE7n1ViqTnBUxjtaalMNZ5pneJVgXjfLGarCcFk3/cPecL4W73e8/0pvE8MWOOv4bNJKXlNfESVHv18Rms9n+Z98cbVkqi6/OkAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-4584-5288","institution":"Division of Mechanical and Electrical Engineering, Kitami Institute of Technology, Japan","correspondingAuthor":true,"prefix":"","firstName":"Sharifu","middleName":"","lastName":"Ura","suffix":""}],"badges":[],"createdAt":"2026-02-13 13:39:57","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8872511/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8872511/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102963067,"identity":"cebd19bf-94e6-4f53-966a-f8d18c76f56a","added_by":"auto","created_at":"2026-02-19 04:13:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2871741,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptv2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8872511/v1_covered_0043d3fd-b39e-41e6-ba9b-5ce4c6b3eb89.pdf"},{"id":102820108,"identity":"0cc25983-c7e9-45f1-ace0-65d131b290c8","added_by":"auto","created_at":"2026-02-17 07:13:46","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":5948729,"visible":true,"origin":"","legend":"\u003cp\u003eVisual screenprints and operational flowcharts for the launcher and tools underlying the developed GUI-based toolkit\u003c/p\u003e","description":"","filename":"S1.docx","url":"https://assets-eu.researchsquare.com/files/rs-8872511/v1/3bf3e31ae81573d5867bb7c0.docx"},{"id":102820109,"identity":"96560de6-835a-4819-aac8-f047253a543f","added_by":"auto","created_at":"2026-02-17 07:13:46","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":9376304,"visible":true,"origin":"","legend":"\u003cp\u003eVisual screenprints of the GUI- and Agentic AI-based toolkit, demonstrating the application scenario\u003c/p\u003e","description":"","filename":"S2.docx","url":"https://assets-eu.researchsquare.com/files/rs-8872511/v1/910f95266996cad2133ea876.docx"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eSystematizing Data Preparation in Smart Manufacturing via Axiomatic Design: A Toolkit Integrating GUI and Agentic AI\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Kitami Institute of Technology","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Data Preparation Systems, GUI, Agentic AI, OpenAI, UX/AX, Smart Manufacturing","lastPublishedDoi":"10.21203/rs.3.rs-8872511/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8872511/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eData serves as the primary driving force behind smart manufacturing, yet the transition from raw data to analysis-ready data remains a critical operational bottleneck. Often dismissed as janitorial work, data preparation consumes a disproportionate amount of analytical effort due to a reliance on fragmented, ad-hoc, and project-specific solutions. To overcome these barriers, this study proposes a systematic, requirements-driven approach grounded in the principles of axiomatic design. By cross-examining diverse manufacturing experiments, recurring operational needs were identified and mapped to a set of modular functional requirements. This theoretical foundation was materialized into a dual-approach toolkit that integrates two complementary interaction models: an interactive graphical user interface and an agentic artificial intelligence system. While the former ensures reproducibility and ground truth validation through granular manual control, the latter leverages a large language model to orchestrate complex tool sequences via natural language. The applicability of this unified architecture is validated through a comprehensive micro-drilling case study, demonstrating the seamless execution of several data preparation tasks. The findings of this study highlight the synergistic relationship between user experience and agent experience. By offering a robust, human-in-the-loop pathway, the developed system transforms data preparation from a peripheral burden into a rigorous scientific discipline. Consequently, this approach democratizes access to advanced data workflows for diverse manufacturing environments. Thus, this study contributes to the advancement of fundamental data practices within the smart manufacturing domain.\u003c/p\u003e","manuscriptTitle":"Systematizing Data Preparation in Smart Manufacturing via Axiomatic Design: A Toolkit Integrating GUI and Agentic AI","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-17 07:13:41","doi":"10.21203/rs.3.rs-8872511/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a417803d-9153-4f71-8b44-30b676d7a78e","owner":[],"postedDate":"February 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":62892228,"name":"Mechanical Engineering"},{"id":62892229,"name":"Industrial Engineering"},{"id":62892230,"name":"Systems Engineering"}],"tags":[],"updatedAt":"2026-02-17T07:13:41+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-17 07:13:41","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8872511","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8872511","identity":"rs-8872511","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}