Abstract
The final step of the bearing production line constitutes the inspection of the bearing which is mostly performed by visual inspection. Three groups of bearings namely, properly assembled samples, conversely assembled rubber seal and samples where rubber seals were missing are classified using visible range images of these samples. According to the proposed method, extraction of seal regions from the bearing images using circular Hough transform is followed by a higher-order statistical analysis to finalize the classification. Experimental results show that this system may be employed as an assistive tool for bearing inspectors.
Translated title of the contribution | Bearing fault detection method based on statistical analysis and KL distance |
---|---|
Original language | Turkish |
Title of host publication | 2016 24th Signal Processing and Communication Application Conference, SIU 2016 - Proceedings |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 1881-1884 |
Number of pages | 4 |
ISBN (Electronic) | 9781509016792 |
DOIs | |
Publication status | Published - 20 Jun 2016 |
Event | 24th Signal Processing and Communication Application Conference, SIU 2016 - Zonguldak, Turkey Duration: 16 May 2016 → 19 May 2016 |
Publication series
Name | 2016 24th Signal Processing and Communication Application Conference, SIU 2016 - Proceedings |
---|
Conference
Conference | 24th Signal Processing and Communication Application Conference, SIU 2016 |
---|---|
Country/Territory | Turkey |
City | Zonguldak |
Period | 16/05/16 → 19/05/16 |
Bibliographical note
Publisher Copyright:© 2016 IEEE.