Portfolio


Tags

Inspection Type

Industry

Technology

CHALLENGE

The inside of a tire is manually inspected for surface defects and pentrations by foreign objects. It can be physically awkward and difficult to see small objects manually so the vision system handles that task.


SOLUTION

For this pilot project, a camera on a linear slide and rotating mirror constrained to a 12” x 3” package was mounted on the end of linear arm and joysticked into the center of the tire. Laser gauges provide feedback to the operator for its ideal placement. Interior is laser profiled to calculate optimal camera distance such that the entire field of view is within focus. The mirror is centered to the field of view and the tire is rotated while the camera acquires a series of images. After each series of images, the mirror is adjusted to the next field of view and the process is repeated until the interior is fully imaged. Images are then presented to the operator on a 34” curve monitor for manual inspection. The operator reviews the images and draws boxes around possible defects. Afterwards this information is archived with an identifier. At a later date, this data can be used to train a Deep Learning system.


TAGS
Deep Learning, Aerospace, Automotive, PC-based Vision
CHALLENGE

Animal Health Sciences start-up was seeking a subject matter expert to develop machine vision solution to determine the orientation of a baby chickens head for the application of vaccine.


SOLUTION

For this SBIR Phase 1 project, a custom lighting and optical solution was developed to acquire images of baby chicks as they passed under the camera. 1000 images where collected and annotated, 2/3rd of the images were then fed into Deep Learning algrothims. Detection performance was 97% with an execution time of 19-22ms.


TAGS
Deep Learning, Identification, Life Sciences, PC-based Vision
CHALLENGE

From new to end of life, welding tips used to spot weld the housing to the band create varied results. From time to time, a weld would fail to fully engage and would produce a light or no weld.


SOLUTION

5000 images were collected and annotated, then applied to a neural network-based descision engine (predecessor to modern deep learning algrothims). System performed well after new tips were broken in after 2000 cycles. (Average life cylce of tips 35k - 40k)


TAGS
Deep Learning, Gauging, Inspection, Industrial Products, PC-based Vision