Chatter Diagnosis in Milling Using Supervised Learning and Topological Features Vector

Abstract

Chatter detection has become a prominent subject of interest due to its effect on cutting tool life, surface finish and spindle of machine tool. Most of the existing methods in chatter detection literature are based on signal processing and signal decomposition. In this study, we use topological features of data simulating cutting tool vibrations, combined with four supervised machine learning algorithms to diagnose chatter in the milling process. Persistence diagrams, a method of representing topological features, are not easily used in the context of machine learning, so they must be transformed into a form that is more amenable. Specifically, we will focus on two different methods for featurizing persistence diagrams, Carlsson coordinates and template functions. In this paper, we provide classification results for simulated data from various cutting configurations, including upmilling and downmilling, in addition to the same data with some added noise. Our results show that Carlsson Coordinates and Template Functions yield accuracies as high as 96% and 95%, respectively. We also provide evidence that these topological methods are noise robust descriptors for chatter detection.

Spatial applications of topological data analysis: Cities, snowflakes, random structures, and spiders spinning under the influence

“…PH is helpful for characterizing the "shape" of data, and the myriad applications of it include studies of protein structure [24][25][26][27], DNA structure [28], neuronal morphologies [29], computer vision [30], diurnal cycles in hurricanes [31], chaotic dynamics in differential equations [32], spatial percolation problems [33], and many others. Additionally, combining machine-learning approaches with PH has also been very useful for several classification problems [34][35][36][37].…”

An introduction to persistent homology for time series

“…Tralie and Harer (2017) and Tralie (2018) describe TDA for music structure analysis and visualization. Myers et al (2019); Khasawneh et al (2018); and Yesilli et al (2019) discuss ways other than delay coordinate embedding to apply persistence to time series problems, and describe intersections between these approaches and machine learning. Berwald et al (2013) discussed the use of TDA for tagging different regimes in dynamical systems.…”

Recent Advances on Machine Learning Applications in Machining Processes

“…Yesili et al [52] focused on the feature extraction method to determine the presence of chatter based on the simulated oscillations of the milling tool (1DOF) data with high noise. They implemented the Topological Data Analysis-more specifically, Carlsson Coordinates and Template Functions-obtaining high accuracies with several algorithms; the ones with the highest accuracies were the SVM and Gradient Boosting.…”