Predicting Tool Wear in Precision Machining through Unsupervised Machine Learning

Posted on by

PUBLICATION

Debasish Mishra, Utsav Awasthi, Krishna R. Pattipati & George M. Bollas. Tool wear classification in precision machining using distance metrics and unsupervised machine learning. J Intell Manuf (2023). https://doi.org/10.1007/s10845-023-02239-5

tooth gear wheel machining In this article, Debasish Mishra, PostDoc (UConn ‘23) and coauthors introduce a novel approach that applies unsupervised Machine Learning to predict tool wear in precision machining accurately. Tested across multiple machines, workpieces, toolings, and cutting settings, the research offers a promising new methodology for improving efficiency and reliability in machining operations by predicting tool replacement decisions.

This research was supported by the Air Force Research Laboratory, Materials and Manufacturing Directorate [FA8650-20-C-5206].

A hole is milled on a CNC machining center