Transfer Learning for Autonomous Chatter Detection in Machining
This addresses the challenge of limited data and feature universality for chatter detection in industrial machining, though it is incremental as it builds on existing methods.
This paper tackled the problem of automating chatter detection in machining by evaluating transfer learning across different processes, finding that Topological Data Analysis and Discrete Time Warping methods achieve accuracies comparable to traditional time-frequency features without manual preprocessing.
Large-amplitude chatter vibrations are one of the most important phenomena in machining processes. It is often detrimental in cutting operations causing a poor surface finish and decreased tool life. Therefore, chatter detection using machine learning has been an active research area over the last decade. Three challenges can be identified in applying machine learning for chatter detection at large in industry: an insufficient understanding of the universality of chatter features across different processes, the need for automating feature extraction, and the existence of limited data for each specific workpiece-machine tool combination. These three challenges can be grouped under the umbrella of transfer learning. This paper studies automating chatter detection by evaluating transfer learning of prominent as well as novel chatter detection methods. We investigate chatter classification accuracy using a variety of features extracted from turning and milling experiments with different cutting configurations. The studied methods include Fast Fourier Transform (FFT), Power Spectral Density (PSD), the Auto-correlation Function (ACF), Wavelet Packet Transform (WPT), and Ensemble Empirical Mode Decomposition (EEMD). We also examine more recent approaches based on Topological Data Analysis (TDA) and similarity measures of time series based on Discrete Time Warping (DTW). We evaluate the transfer learning potential of each approach by training and testing both within and across the turning and milling data sets. Our results show that carefully chosen time-frequency features can lead to high classification accuracies albeit at the cost of requiring manual pre-processing and the tagging of an expert user. On the other hand, we found that the TDA and DTW approaches can provide accuracies and F1 scores on par with the time-frequency methods without the need for manual preprocessing.