论文信息 - Detecting machine chatter using audio data and machine learning

Detecting machine chatter using audio data and machine learning

We present a method for detecting chatter in CNC machining. Our method uses machining learning to train a classifier to determine the chatter threshold, and we use an autoencoder to reduce the dimensionality of the data. We test our method on machining audio data, and successfully detect chatter in the validation data. Our method is amenable to use on the shop floor, as a machinist using our method needs only to classify audio as chatter and non-chatter.

[1] Hongrui Cao,et al. Chatter detection in milling process based on synchrosqueezing transform of sound signals , 2017 .

[2] Ilarion Kvitnevskiy. Making CNC Machines Smarter , 2019 .

[3] M. A. Selles,et al. Machining Chatter Prediction Using a Data Learning Model , 2019, Journal of Manufacturing and Materials Processing.

[4] B. Mehlig. Artificial Neural Networks , 2019, ArXiv.

[5] Pierre Baldi,et al. Autoencoders, Unsupervised Learning, and Deep Architectures , 2011, ICML Unsupervised and Transfer Learning.

[6] Kai Zhou,et al. Early chatter detection in end milling based on multi-feature fusion and 3σ criterion , 2017 .

[7] Sepp Hochreiter,et al. Self-Normalizing Neural Networks , 2017, NIPS.

[8] Yusuf Altintas,et al. Manufacturing Automation: Metal Cutting Mechanics, Machine Tool Vibrations, and CNC Design , 2000 .

[9] Alexander Verl,et al. On-line learning artificial neural networks for stability classification of milling processes , 2016, 2016 IEEE International Conference on Advanced Intelligent Mechatronics (AIM).

[10] Alexander Verl,et al. Estimation of stability lobe diagrams in milling with continuous learning algorithms , 2017 .