Page 5 - June

NEWS
Zagorsk Pipe Plant introduces AI technologies

for product quality control

The company has successfully put into
operation a pipe quality control system using
computer vision and deep machine learning
methods.
At the Zagorsk Pipe Plant, a system
was put into operation using computer
vision algorithms and deep machine
learning methods, which makes it possible
to significantly simplify and increase
the efficiency of product manufacturing
technology control. The hardware and
software complex is deployed at the area
for applying the outer coating. The partner
in the development of the solution and its
integration into the production system of
ZTZ was the Tochka ai company (Yaroslavl).
Within the framework of the implemented project, more than ten video surveillance cameras
were installed in the coating shop, which record the production process in open sections of the
line. Video data from cameras are sent to the company's servers, where they are processed
using computer vision algorithms that separate individual product units from the video stream.
The following intelligent algorithm allows you to "accompany" the found objects, that is,
to determine on which section of the line each particular pipe is located at a given time. An
important feature of the system is the calculation of the position of the pipe in closed areas.
Thus, it is possible to trace each individual pipe in the overall flow.
The system allows you to calculate the speed of rotation and movement of pipes, as well
as to bind the values of technological parameters - readings of sensors installed on the line - for
example, heating sensors, insulation thickness and others with which this pipe was produced.
All information is fed into the production IT system and analyzed by quality specialists. If
any deviations are detected, the corresponding pipes are removed from production and sent for
revision.

metallicheckiy-portal.ru

Stanochniy park 5