應用AI影像技術於刀具紋路之分類

Application of AI Image Technology on Classification of Surface Texture from Cutting Operations

蔡孟勳 ； 莊健平 ； 麥朝創

《機械工業雜誌》 444期 (2020/03) Pp. 13-16

摘要

工具機加工時，工件表面產生的紋路一般而言可區分為過切、振紋、斜陡坡紋、刀圈紋、拉絲等。在解析紋路時，通常需要有經驗的師傅來加以判讀，而且工件在不同光線、不同角度下所判讀的結果也不盡相同，本文結合AI（Faster RCNN）與影像技術來自動分類加工紋路，使用者只要將加工好的標準模具放置於我們所設計的拍攝模組中即能自動標示紋路的類型，未來將結合專家與IoT系統，達到自動判讀紋路成因的目標。

關鍵字

人工智慧 ； 刀具紋路分類

並列摘要

For CNC machining, surface texture of a workpiece can be generally divided into overcutting, chattering, oblique slope vibration marks, cutting ring, wiring, etc. Analyzing and interpretation of the surface texture usually require an experienced engineer, and the interpretation result for workpiece under different lighting conditions and different angles will also be different. This article described how to combine AI (Faster RCNN) and image technology to classify the surface texture type automatically. Users only need to put the processed standard mould part in the designed camera module then the texture type will be automatically marked. In the future, experts will be combined with Internet of things (IoT) systems to achieve the goal of automatic determination of the cause of surface texture.

並列關鍵字

Artificial intelligent ； Classification of tool cutting mark

參考文獻

Ren, Shaoqing(2015).Faster r-cnn: Towards real-time object detection with region proposal networks.Advances in neural information processing systems.(Advances in neural information processing systems).

He, Kaiming(2016).Deep residual learning for image recognition.Proceedings of the IEEE conference on computer vision and pattern recognition.(Proceedings of the IEEE conference on computer vision and pattern recognition).

Lien, Po Chun,Zhao, Qiangfu(2018).Product Surface Defect Detection Based on Deep Learning.2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech).(2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech)).

Lv, Yongfa,Ma, Ling,Jiang, Huiqin(2019).A Mobile Phone Screen Cover Glass Defect Detection MODEL Based on Small Samples Learning.2019 IEEE 4th International Conference on Signal and Image Processing(ICSIP).(2019 IEEE 4th International Conference on Signal and Image Processing(ICSIP)).