of honing through better
coolant condition control Applied science
Castrol & Gehring are working
together to improve the results
Andrew Allcock has news of three practical Industry 4.0-style developments, in machine tool
maintenance, automotive part grinding/honing and rotor grinding and milling
Not yet ready for industrial application,
but a very good example of the
practical use of high technology such
as AI-analysis of images to a rather
mundane task is one that Germany’s
Karlsruhe Institute of Technology has
developed. It is a system for the fully
automated monitoring of ballscrew drives in
machine tools.
In mechanical engineering, the timely
maintenance and replacement of defective
components in machine tools is an
important part of maintaining reliable
manufacturing process. In the case of
ballscrew drives, such as those used in
lathes, wear has until now been determined
manually.
Explains Professor Jürgen Fleischer from
the Institute for Production Technology
(WBK) at the Karlsruhe Institute of
Technology (KIT): “Maintenance is therefore
associated with installation work, which
means the machine comes to a standstill.
Our approach, on the other hand, integrates
an intelligent camera system directly into the
drive, which enables a user to continuously
monitor the spindle status. If there is a need
for action, the system informs the user
automatically.”
INDUSTRY 4.0 & AUTOMATION PRACTICAL APPLICATION
The new system combines a camera with
light source attached to the nut of the drive
and arti cial intelligence (AI) that evaluates
the image data. As the ballnut moves on the
screw, it takes individual pictures of each
screw section, enabling the analysis of the
entire spindle surface.
Combining image data from ongoing
operations with machine-learning methods
enables system users to assess the
condition of the spindle surface. “We trained
our algorithm with thousands of images, so
that it can now con dently distinguish
between spindles with defects and those
without,” WBK’s Tobias Schlagenhauf, who
helped development the system, says. “By
further evaluating the image data, we can
precisely qualify and interpret wear and thus
distinguish if discoloration is simply dirt or
harmful pitting.”
When training the AI system, the team
took account of all conceivable forms of
visible degeneration and validated the
algorithm’s functionality with new image
data that the model had never seen before.
The algorithm is suitable for all applications
that identify image-based defects on the
screw surface and is transferrable to other
applications. This example will be on display
at next month’s Hannover Messe.
A practical example that is ready for
application is Castrol’s SmartControl, a realtime
uid condition monitoring solution. It is
being employed on Gehring’s machine tools,
an automotive expert supplying advanced
honing solutions. The surface structure of
1. Housing, including lighting
2. Connecting piece between camera system
and ballscrew nut
3. Camera for recording images
www.machinery.co.uk @MachineryTweets March 2020 35
/www.machinery.co.uk