Visual Inspections Perfected Using AI

The project will integrate an Artificial Intelligence inspection system with the Digital Thread to provide timely, actionable insights about the quality of adhesive dots deposited on a planar surface.


Boeing makes reflective space cells and assembles them into panels. One of the highest risks in the manufacturing process is the placement of a large number of adhesive dots that bond the reflective cells to the small structural backboard. The process currently requires a team of 14 to apply and inspect the glue dots, and to rework any that are unacceptable. Operators are regularly trained and tested for dot quality, yet costly problems occur, halting production and costing money and time. A real-time inspection system is needed. One that introduces automated scientific measurement and evaluation to ensure consistency and quality.

Proposed Solution

The team is developing a quality controlled visual inspection system called SMART-VIStA, which combines real-time inspection with AI learning to prevent faulty dots. After a robot deposits an adhesive dot, the first feedback loop uses one or more cameras mounted on a second robotic arm to inspect the dot from another angle. A second feedback loop employs machine learning to make up-stream adjustments and eliminate errors before the next dot is applied. Finally, a digital twin of the equipment assesses the inspection data and entire Digital Thread, and gives operators real-time insights and recommendations to improve performance and quality.


SMART-VIStA not only addresses quality control challenges for Boeing, it also has several other applications for processes that currently require human inspection and interpretation— such as welding, painting and soldering. SMART-VIStA will be able to respond quickly to defects, predict future quality issues and pre-emptively tune parameters up-stream. This technology can help large and small companies maximize quality and efficiency and minimize cost. SMART-VIStA also has applications for the semiconductor industry in detecting defects in PCBs; detecting flaws in leather or sheet metal; and monitoring the quality of automotive or aircraft parts.