UEC-Saturn will assess the quality of aircraft engine parts using neural networks

Photo by © UEC press service

United Engine Corporation has implemented a new method of luminescent quality control of aircraft engine parts using machine vision and neural network technologies. The innovation of the Rybinsk-based company UEC-Saturn also made it possible to automate the process of evaluating the quality of power plant blades and includes the use of advanced image processing algorithms.

The new method of automated luminescent inspection provides imaging of all surfaces of the part, searching for defects, calculation of their geometric characteristics, classification and determination of the product’s fitness for use according to the regulatory documentation. This method makes it possible to detect all types of defects, including cracks, boles, junctions, etc. Application of this method of control in the technological production process increases the accuracy and reliability of the results obtained.

An additional effect of using this method is the formation of a “digital footprint” of the manufactured product, which will allow retrospective analysis of the production process in order to optimize it.

“We are actively working on various options for using machine vision specifically for product quality control. The use of image processing algorithms and neural network technology has been tested and refined on a specially created test bench. Application of the machine vision technology at our production facilities multiplies the throughput capacity of the inspection area and reduces the requirements to the personnel,” noted Yevgeny Alekseev, IT Director of UEC-Saturn.

1 Star2 Stars3 Stars4 Stars5 Stars (No Ratings Yet)
Loading...