Repository logo
  • English
  • 中文
Log In
Have you forgotten your password?
  1. Home
  2. College of Engineering / 工學院
  3. Mechanical Engineering / 機械工程學系
  4. AI賦能工具機數位雙生平台
 
  • Details

AI賦能工具機數位雙生平台

Other Title
AI-Power Machine Tool Digital Twin Platform
Journal
機械工業雜誌
Journal Issue
516
Start Page
53
End Page
61
ISSN
0255-0075
Date Issued
2026-03
Author(s)
李建毅
楊善荏
莊佳瑾
廖孟秋
黃鵬緒
蔡孟勳  
簡嘉宏
DOI
10.30256/JIM.202603_(516).0009
URI
https://scholars.lib.ntu.edu.tw/handle/123456789/739196
Abstract
近年來國際工具機製造商如DMG-MORI、MAZAK皆陸續導入邊緣人工智慧(Edge AI),強化設備的健康狀態監控、異常診斷與製程優化等提升智慧設備。然而,控制器受限於格式封閉且運算效能與外接硬體成本考量,使得AI技術難以在工廠大規模落地,為解決此瓶頸,工研院機械所偕同國立臺灣大學機械系蔡孟勳教授團隊以及新代科技三方合作,建置示範線樣板,以AI Embedded CNC(Computer Numerical Control)控制器技術,將AI模型直接部署至控制器內,與原有的控制器核心協同運作,並建置工具機邊緣驗證平台,導入國內控制器實測資料驗證AI模型的可行性,降低AI Apps上機測試成本,以先驗證再導入的標準化路徑,提供AI模型自工具機數位雙生平台整合的虛擬建模技術,再以AI Embedded CNC控制器技術的控制器端部署到最後於臺中工研院智慧製造驗證場域實機驗證的完整技術路徑,為AI賦能工具機的實用化與產業化奠定基礎。
In recent years, international machine tool manufacturers such as DMG-MORI and MAZAK have progressively adopted Edge AI to enhance equipment health monitoring, anomaly diagnosis, and process optimization, thereby advancing smart equipment capabilities. However, controllers face limitations due to closed formats, computational performance constraints, and external hardware costs, hindering large-scale AI implementation in factories. To overcome this bottleneck, the Industrial Technology Research Institute's Smart Machinery Center collaborated with Professor Meng-Hsun Tsai's team from the Department of Mechanical Engineering at National Taiwan University and S.T. Technology to establish a demonstration line prototype. This initiative employs AI Embedded CNC (Computer Numerical Control) controller technology. This approach deploys AI models directly within the controllers, enabling them to operate synergistically with the existing controller core. Additionally, an edge verification platform for machine tools has been established. This platform utilizes real-world data from domestic controllers to validate the feasibility of AI models, thereby reducing the cost of AI application testing on actual machines. Following a standardized path of "verify first, then deploy," the platform provides virtual modeling technology integrated from the machine tool digital twin platform. and finally deploying the AI Embedded CNC controller technology at the controller end for real-machine validation at the ITRI Smart Manufacturing Verification Site in Taichung. This comprehensive technical pathway lays the foundation for the practical application and industrialization of AI-enabled machine tools.
Subjects
AI驅動模擬
設備賦能
驗證先行
AI嵌入式CNC控制器
AI-Driven simulation
Equipment enablement
Validate before deploy
AI Embedded CNC controller
Type
journal article

臺大位居世界頂尖大學之列,為永久珍藏及向國際展現本校豐碩的研究成果及學術能量,圖書館整合機構典藏(NTUR)與學術庫(AH)不同功能平台,成為臺大學術典藏NTU scholars。期能整合研究能量、促進交流合作、保存學術產出、推廣研究成果。

To permanently archive and promote researcher profiles and scholarly works, Library integrates the services of “NTU Repository” with “Academic Hub” to form NTU Scholars.

總館學科館員 (Main Library)
醫學圖書館學科館員 (Medical Library)
社會科學院辜振甫紀念圖書館學科館員 (Social Sciences Library)

開放取用是從使用者角度提升資訊取用性的社會運動,應用在學術研究上是透過將研究著作公開供使用者自由取閱,以促進學術傳播及因應期刊訂購費用逐年攀升。同時可加速研究發展、提升研究影響力,NTU Scholars即為本校的開放取用典藏(OA Archive)平台。(點選深入了解OA)

  • 請確認所上傳的全文是原創的內容,若該文件包含部分內容的版權非匯入者所有,或由第三方贊助與合作完成,請確認該版權所有者及第三方同意提供此授權。
    Please represent that the submission is your original work, and that you have the right to grant the rights to upload.
  • 若欲上傳已出版的全文電子檔,可使用Open policy finder網站查詢,以確認出版單位之版權政策。
    Please use Open policy finder to find a summary of permissions that are normally given as part of each publisher's copyright transfer agreement.
  • 網站簡介 (Quickstart Guide)
  • 使用手冊 (Instruction Manual)
  • 線上預約服務 (Booking Service)
  • 方案一:臺灣大學計算機中心帳號登入
    (With C&INC Email Account)
  • 方案二:ORCID帳號登入 (With ORCID)
  • 方案一:定期更新ORCID者,以ID匯入 (Search for identifier (ORCID))
  • 方案二:自行建檔 (Default mode Submission)
  • 方案三:學科館員協助匯入 (Email worklist to subject librarians)

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science