# On Transfer Learning of Traditional Frequency and Time Domain Features in Turning

arXiv: https://arxiv.org/abs/2008.12691 · HTML: https://mlsanity.com/paper/2008.12691/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2020.

## Built on by (most cited first, 4 of 4)

- [Data-driven and Automatic Surface Texture Analysis Using Persistent Homology](https://mlsanity.com/paper/2110.10005/) (2021)
- [Persistent Homology of Coarse Grained State Space Networks](https://mlsanity.com/paper/2206.02530/) (2022)
- [Transfer Learning for Autonomous Chatter Detection in Machining](https://mlsanity.com/paper/2204.05400/) (2022)
- [Automated Surface Texture Analysis via Discrete Cosine Transform and Discrete Wavelet Transform](https://mlsanity.com/paper/2204.05968/) (2022)

## Abstract (arXiv)

There has been an increasing interest in leveraging machine learning tools for chatter prediction and diagnosis in discrete manufacturing processes. Some of the most common features for studying chatter include traditional signal processing tools such as Fast Fourier Transform (FFT), Power Spectral Density (PSD), and the Auto-correlation Function (ACF). In this study, we use these tools in a supervised learning setting to identify chatter in accelerometer signals obtained from a turning experiment. The experiment is performed using four different tool overhang lengths with varying cutting speed and the depth of cut. We then examine the resulting signals and tag them as either chatter or chatter-free. The tagged signals are then used to train a classifier. The classification methods include the most common algorithms: Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and Gradient Boost (GB). Our results show that features extracted from the Fourier spectrum are the most informative when training a classifier and testing on data from the same cutting configuration yielding accuracy as high as %96. However, the accuracy drops significantly when training and testing on two different configurations with different structural eigenfrequencies. Thus, we conclude that while these traditional features can be highly tuned to a certain process, their transfer learning ability is limited. We also compare our results against two other methods with rising popularity in the literature: Wavelet Packet Transform (WPT) and Ensemble Empirical Mode Decomposition (EEMD). The latter two methods, especially EEMD, show better transfer learning capabilities for our dataset.