Publication Type : Journal Article
Publisher : Journal of Ceramic Processing Research
Source : Journal of Ceramic Processing Research
Campus : Coimbatore
School : School of Engineering
Department : Mechanical Engineering
Year : 2022
Abstract : Chatter during machining operations is extremely detrimental to cutting tool life and the surface quality of the workpiece. Online monitoring methods are becoming more relevant for chatter detection and prediction in automated machiningoperations. While the utilization of vibration signals for the direct detection of chatter has been extensively researched, thereare limited studies that explore the use of certain other sensor signatures, such as force signals. The present work aims toexpand on the area of chatter detection in the turning of difficult-to-machine materials through Machine Learning (ML) usingforce signals acquired through multi-component tool dynamometer. An experimental setup has been established to collect forcesignature during dry turning operation under various process parameters selected on the basis of analytical Stability LobeDiagrams (SLDs). Statistical features of Standard Deviation (SD) & Moving Window Standard Deviation (MWSD) extractedfrom the time-domain force signatures for different machining conditions are used to build statistical models using the DecisionTree (DT) Algorithm. The feasibility and performance of classifier models using the feature of MWSD are studied in thepresent paper. The DT classifier trained using MWSD of window size 100 has been found to provide a classification accuracyof 97.511%.
Cite this Research Publication : Nair, V. S., Rameshkumar, K., & Saravanamurugan, S. (2022). Chatter identification in turning of difficult-to-machine materials using moving window standard deviation and decision tree algorithm. Journal of Ceramic Processing Research, 23(4), 503–510. https://doi.org/10.36410/jcpr.2022.23.4.503