Automated System for Surface Pitting Analysis on Airplane Jet Engine

A system that can identify and evaluate surface defects on airplane jet engine components

“Pitting” is a surface defect found on critical jet engine components of complex shapes and different sizes. It is currently detected by naked-eye inspection. Such task takes up significant man-hours, and embodies human errors which limit engine maintenance performance in terms of cost, time, quality, and safety. Combining robotics, image processing, deep learning, and non-destructive testing technologies, this automated system can identify and measure pitting. A robot is used to conduct inspection on engine components. The system shortens the inspection process, enhances the quality of work with more consistent workmanship and accuracy, and cuts down the operation costs.

Special Features and Advantages

Employs deep learning to identify tiny defects on metal surface and extract defect features
Captures the 3D information of inspected surface and the dimensions of individual defects automatically at micrometer scale

Applications

Detect pitting automatically and analyze airfoil surface of jet engine blades or vanes
Detect and measure surface defects on cylindrical components of jet engine
Search for any surface anomaly (e.g. lightning strike marks) on the airplane fuselage and wing

Award

Gold Medal – 46th International Exhibition of Inventions of Geneva, Switzerland (Apr 2018)

Principal Investigator

Dr Stephen O’BRIEN

Aviation Services Research Centre

Download PDF version Technoology frontier

Automated System for Surface Pitting Analysis on Airplane Jet Engine

A system that can identify and evaluate surface defects on airplane jet engine components