Open AccessTOOL CONDITION MONITORING AND TOOL DEFECT DETECTION FOR END MILLS BASED ON HIGH-FREQUENCY MACHINE TOOL DATA
Author(s) -
Alexander Fertig,
Lukas Grau,
Marius Altmannsberger,
Matthias Weigold
Publication year - 2021
Publication title -
mm science journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.195
H-Index - 10
eISSN - 1805-0476
pISSN - 1803-1269
DOI - 10.17973/mmsj.2021_11_2021174
Subject(s) - machine tool , process (computing) , context (archaeology) , computer science , manufacturing engineering , engineering , mechanical engineering , paleontology , biology , operating system
In the context of increasing digitalization, machine tools have a decisive impact on the manufacturing of technically sophisticated products. The resulting large amount of available data opens up new opportunities for process monitoring and optimization. In this paper, a new in-process tool condition monitoring (TCM) approach for end mills is developed. Besides in-process wear determination, the presented approach also enables the early detection of tool manufacturing defects on end mills. By applying machine learning algorithms, high prediction accuracies can be achieved. The results allow the implementation of an in-process TCM system based on internal machine tool data.