1 / 3

Surface Inspection

Our client is a German-based multinational engineering and technology company and was founded in the late 1800s surface inspection techniques. Our client set up their first manufacturing plant in India during the early 1950s. With a turnover of over $3 billion in India and over 31,000 employees, Visual Surface Inspection of Components they are spread across 10 locations and 7 application development centers Surface Inspection.

qualitas
Download Presentation

Surface Inspection

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Surface Inspection Client Our client is a German-based multinational engineering and technology company and was founded in the late 1800s surface inspection techniques. Our client set up their first manufacturing plant in India during the early 1950s. With a turnover of over $3 billion in India and over 31,000 employees, Visual Surface Inspection of Components they are spread across 10 locations and 7 application development centers Surface Inspection. Problem Faced ● Identification of defects on the samples. ● Manual visualization of the defects was done previously and the client wanted it automated. ● Distinguishing between good and bad variants. Also Read, Cylinder OCR Inspection Technology introduced by Qualitas

  2. Deep Neural Network image processing helps in optimal decision making & precise results. The previously used conventional rule-based image processing was a time-consuming task and wasn’t reliable when accuracy was asked for. This is how the previously used technology worked; the image processing was done by comparing captured images to a master image. During the comparison, any difference in captured image pattern above the pre-set threshold value resulted in rejection & images with pattern difference falling less than pre-set threshold value was accepted. But the issue here was with the accuracy and limitations of the application. Solution ● The disc was fed to the vision system conveyor (manual feeding). ● Proximity type or through-beam laser sensor triggered the camera and captured top & bottom surface images (2D). ● Both the images were processed & real-time results were displayed over Qualitas custom-built GUI and the defects were displayed with annotation. ● Results (OK/NOT OK) from the top and bottom inspections actuated the flapper & components were separated accordingly. Rejected components with defects on both top & bottom surfaces, or only on one face were collected in the same bin Images

  3. Results The proposed solution works for all variants. Read More: https://bit.ly/31o0be9

More Related