跳至主導覽 跳至搜尋 跳過主要內容

A Novel End-to-End Ensemble UNet Network Based on Edge Computing for Tool Wear Detection

  • Jianwen Chen
  • , Meng Shiun Tsai
  • , Wan Ju Lin
  • , Che Lun Hung*
  • *此作品的通信作者
  • National Tsing Hua University
  • National Taiwan University
  • National Kaohsiung University of Science and Technology
  • National Yang Ming Chiao Tung University

研究成果: 圖書/報告稿件的類型 › 會議稿件 › 同儕審查

4 引文 斯高帕斯(Scopus)

摘要

Automated tool wear condition monitoring is essential for ensuring product quality. However, achieving both high detection precision and utilizing edge computing are critical for advancing intelligent manufacturing. Consequently, this article develops a tool wear detection system utilizing edge computing techniques. Firstly, a novel end-to-end ensemble UNet-based model is proposed. Through end-to-end feature fusion training, it effectively addresses the robustness and accuracy issues inherent in single models. Secondly, multiple neural computing sticks are involved to reduce the need for cloud transmission and preserve data privacy, thereby enabling scalability and flexibility in deployment. Experiments demonstrate that mean intersection over union (mIoU) and mean dice coefficient (mDice) in tool wear detection can be improved by over 3% and 2%, respectively. Furthermore, the execution time can be accelerated by a factor of 4.

原文英語
主出版品物標題CACML 2024 - 2024 3rd Asia Conference on Algorithms, Computing and Machine Learning
發行者Association for Computing Machinery
頁面403-408
頁數6
ISBN(電子)9798400716416
DOIs
出版品狀態已出版 - 22 03 2024
對外發佈是
事件3rd Asia Conference on Algorithms, Computing and Machine Learning, CACML 2024 - Shanghai, 中國
持續時間: 22 03 2024 → 24 03 2024

出版品系列

名字ACM International Conference Proceeding Series

Conference

Conference3rd Asia Conference on Algorithms, Computing and Machine Learning, CACML 2024
國家/地區中國
城市Shanghai
期間22/03/24 → 24/03/24

文獻附註

Publisher Copyright:
© 2024 ACM.

UN SDG

此研究成果有助於以下永續發展目標

  1. SDG9 工業、創新基礎建設
    SDG9 工業、創新基礎建設

指紋

深入研究「A Novel End-to-End Ensemble UNet Network Based on Edge Computing for Tool Wear Detection」主題。共同形成了獨特的指紋。

引用此