Tool wear condition monitoring method based on graph neural network with a single sensor Online publication date: Thu, 01-Sep-2022
by Chen Gao; Jie Zhou; Yuan Yang; Yukun Fang; Gaofeng Zhi; Bintao Sun
International Journal of Machining and Machinability of Materials (IJMMM), Vol. 24, No. 3/4, 2022
Abstract: Tool wear condition monitoring (TCM) is an important part of machining automation. In recent years, deep learning (DL)-based TCM methods have been widely researched. However, almost all DL-based methods need sufficient learning samples to obtain good accuracy, which is hard for TCM in terms of cost and time. In order to enhance the recognition accuracy of DL-based TCM under small samples, this paper proposed a new improved multi-scale edge-labelling graph neural network (MEGNN). Firstly, the signal of cutting force sensor is expanded to multi-dimensional data through phase space reconstruction. Secondly, these multi-dimensional data are encoded into a recurrence plot (RP). Then, the RP is input to multi-scale EGNN (MEGNN) to extract features. Finally, the tool condition is estimated through the updated edge labels using a weighted voting method. Our milling TCM experiments demonstrate the proposed MEGNN-based TCM method outperforms three DL-based methods under small samples.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Machining and Machinability of Materials (IJMMM):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook