Abstract
Acoustic monitoring presents itself as a flexible but under-reported method of tool condition monitoring in milling operations. This paper demonstrates the power of the monitoring paradigm by presenting a method of characterizing milling tool conditions by detecting anomalies in the time-frequency domain of the tools' acoustic spectrum during cutting operations. This is done by training a generative adversarial neural network on only a single, readily obtained class of acoustic data and then inverting the generator to perform anomaly detection. Anomalous and non-anomalous data are shown to be nearly linearly separable using the proposed method, resulting in 90.56% tool condition classification accuracy and a 24.49% improvement over classification without the method.
Original language | English |
---|---|
Pages (from-to) | 372-378 |
Number of pages | 7 |
Journal | 48th SME North American Manufacturing Research Conference, NAMRC 48 |
Volume | 48 |
DOIs | |
State | Published - 2020 |
Event | 48th SME North American Manufacturing Research Conference, NAMRC 48 - Cincinnati, United States Duration: Jun 22 2020 → Jun 26 2020 |
Bibliographical note
Publisher Copyright:© 2020 The Authors. Published by Elsevier B.V.
Keywords
- Acoustic signals
- Generative adversarial networks
- Single-class training
- Tool condition monitoring
ASJC Scopus subject areas
- Artificial Intelligence
- Industrial and Manufacturing Engineering