端銑刀磨耗監測與壽命預測技術之研發

在加工廠的自動化過程裡，刀具的更換目前還是依賴人類的感官判斷，不僅耗費人力成本，並且也有誤判而導致浪費的風險。因此假使能發展一套刀具磨耗監測與壽命預測系統，能夠提早預知刀具即將更換而有所準備，必然可使工廠的運作效率提升並且減少刀具浪費。本研究以CNC銑床為研究項目，直接在機台內部架設工業相機，拍攝端銑刀的磨耗，並撰寫一套影像處理程式來量測磨損量並產生刀具磨耗曲線，最後將前一把與當下的刀具磨損數據結合，更新成混合型磨耗曲線，再使用加權最小平方法取得模型最佳參數，預測出刀具壽命終了的時間。根據實驗結果，證明本文提出的方法，可以在刀具磨耗初期就有準確的預測，而即使中途更換加工參數，除了第一次預測誤差較大外，之後的預測仍然可以很快將誤差收斂至穩定的範圍。

關鍵字

刀具磨耗；影像處理；壽命預測

並列摘要

This study mainly focused on milling cutter condition montioring and remaining life predition. Cutter wear online monitoring and remaining useful life prediction play an important role in automation of manufacturing processes. Milling with severly weared cutter may not only devastate the machined part quality, but also cause the risk of machine damage. In order to avoid these problems, it is necessary to know the condition and remaining life of the cutter. To monitor the conditions of the milling cutter, a vast amount of research were investigated, such as acousic emission, tool temperature, cutting forces, and vibration signature, etc. These studies claim that these process parameters in the milling environment can be tapped and correlated to tool wear. Although these mehtods can be applied during the milling process, the values of meausrement do not directly imply the status of cutters. Recent advances in the field of image processing technology have led to the development of various vision sensors that can provide a direct measurement of the cutter condition. However, the literature on cutter life prediction is limited. Thus, this study porposed to measure the flank wear of the cutter using CCD camera, and predict the cutters’ remaining life using linear regression method. The experimental results show that, by integrating the wear status of current cutter and past cutter, the cutters' remaining useful life can be predicted accurately.

並列關鍵字

Tool wear ； Image processing ； Life prediction

參考文獻

[1] D. Snr and E. Dimla, "Sensor signals for tool-wear monitoring in metal cutting operations—a review of methods," International Journal of Machine Tools and Manufacture, vol. 40, pp. 1073-1098, 2000.

[3] S. Kurada and C. Bradley, "A review of machine vision sensors for tool condition monitoring," Computers in Industry, vol. 34, pp. 55-72, 1997.

[4] Tsai, M. K., B. Y. Lee, and S. F. Yu. "A predicted modelling of tool life of high-speed milling for SKD61 tool steel." The International Journal of Advanced Manufacturing Technology 26.7-8 (2005): 711-717.

[5] Zhang, Chen, and Jilin Zhang. "On-line tool wear measurement for ball-end milling cutter based on machine vision." Computers in industry 64.6 (2013): 708-719.

[6] S. Kurada, C. Kurada, and Bradley, "A machine vision system for tool wear assessment," Tribology international, vol. 30, pp. 295-304, 1997.

國際替代計量

端銑刀磨耗監測與壽命預測技術之研發

未授權

主題瀏覽