Wavelet transform and mel-frequency cepstral coefficient-based feature extraction of the sheet metal trimming process to study burr formation
by Tushar Y. Badgujar; Vijay P. Wani
International Journal of Mechatronics and Manufacturing Systems (IJMMS), Vol. 15, No. 1, 2022

Abstract: The sheet metal trimming process is extensively employed to achieve the final shape of components. However, burr formation is a major quality related issue of trimmed parts, and the burr height could be utilised to assess the quality of the component. Punch wear and material thickness variation were considered significant parameters, causing deviation in the burr height. This study proposes the pragmatism of the wavelet transform (WT) coupled with mel-frequency cepstral coefficients (MFCCs) to extract acoustic signal features to examine burr formation. The MFCCs of features indicate variations in the process parameters. Furthermore, the experimental results reveal a correlation between burr formation and MFCCs. These results suggest that the WT, coupled with MFCCs, can be useful in retrieving features pointing burr formation. Thus, features of the signal could be used to monitor the burr height, and these would prevent the need for offline burr height measurement, reworking, and scrapping.

Online publication date: Mon, 16-May-2022

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