Prediction of burr height formation in sheet metal trimming processes using acoustic signals and an artificial neural network
by Tushar Y. Badgujar; Vijay P. Wani
International Journal of Mechatronics and Manufacturing Systems (IJMMS), Vol. 16, No. 1, 2023

Abstract: Sheet metal trimming is an important manufacturing process in various industries. In trimmed components, burr formation is a significant defect, and the burr height is a key determinant of product quality. Punch wear and punch-die clearance are the two main factors affecting burr formation. An online burr height prediction system is required to improve the productivity of the process. In this research, the human hearing system was imitated for burr height prediction during trimming. Firstly, a discrete wavelet transform with the mel-frequency cepstral coefficients was employed to extract features from an acoustic signal. Subsequently, a feed-forward back-propagation artificial neural network was trained to determine the changes in the sheet metal thickness and punch wear state and to predict the burr height using the signal features. The proposed online burr height prediction system can improve productivity by mitigating defective production, reducing inspection time, and enabling timely regrinding of components.

Online publication date: Thu, 06-Jul-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
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 Mechatronics and Manufacturing Systems (IJMMS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your 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