Issue |
MATEC Web Conf.
Volume 217, 2018
2018 International Conference on Vibration, Sound and System Dynamics (ICVSSD 2018)
|
|
---|---|---|
Article Number | 03003 | |
Number of page(s) | 8 | |
Section | Sound | |
DOI | https://doi.org/10.1051/matecconf/201821703003 | |
Published online | 17 October 2018 |
Deep Neural Network Tool Chatter Model for Aluminum Surface Milling Using Acoustic Emmision Sensor
System Engineering and Energy Laboratory, Universiti Kuala Lumpur Malaysian Spanish Institute
* Email: muhamadhusaini@unikl.edu.my Phone: +6044035199; Fax: +6044035201
Chatter is a self-excited vibration in any machining processes which contributes to the system instability due to resonance and resulting in an inaccuracy in machining product. Due to demand for a high precision product, industries are nowadays moving towards implementing a tool monitoring system as a feedback. Currently, an electromagnetic sensor was used to detect chatter in tools, but this sensor introduces a drawback such as bulky in size, sensitive to noise and not suitable to be implemented in the small machining center. This paper aims to propose a chatter identification model for face milling tool based on acoustic emission data for tool monitoring system. Acoustic emission data is collected at four level of cutting depth in milling with linear tool path movement on aluminum T6 6061 materials. the Deep Neural Network (DNN) model was developed using multiple deep-learning frameworks for the chatter detection system. This model approach shows a good agreement with experimental data with 4% error. As a conclusion, the DNN chatter identification model was successfully developed for the aluminum milling process applications. This finding is essential for anomaly detection during machining process and able to suggest for a better machining parameter for the aluminum machining process.
Key words: Tool Chatter / Deep Neural Network / Acoustic Emission / Anomaly detection
© The Authors, published by EDP Sciences, 2018
This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.