Camera-based Spindle Control

  Enquiry / contact me

An AI for machine tool maintenance

Artificial Intelligence, Vision & Identification

System developed at KIT for fully automatic wear control of ball screws by using artificial intelligence.
System developed at KIT for fully automatic wear control of ball screws by using artificial intelligence.
An integrated camera with lighting enables continuous monitoring of the spindle in the ball screw drive.
An integrated camera with lighting enables continuous monitoring of the spindle in the ball screw drive.

Researchers at the Karlsruhe Institute of Technology (KIT) engineered a system for fully automated monitoring of ball screw drives in machine tools. It consists of a camera which is directly integrated into the nut of the drive generates images that an AI continuously monitors for signs of wear. The aim is to reduce machine downtime.

In mechanical engineering, maintaining, and replacing defective components timely in machine tools is an important part of the manufacturing process. In the case of ball screw drives, such as those used in lathes to precisely guide the production of cylindrical components, wear has until now been determined manually.

Wear on the spindle in ball screws can be continuously monitored and evaluated with an intelligent system by KIT

“Maintenance is therefore associated with installation work, which means the machine comes to a standstill,” says Professor Jürgen Fleischer from the Institute for Production Technology (wbk) at the Karlsruhe Institute of Technology (KIT). “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.”

The new system combines a camera with light source attached to the nut of the drive and an artificial intelligence that evaluates the image data. As the nut moves on the spindle, it takes individual pictures of each spindle section, enabling the analysis of the entire spindle surface.

Artificial intelligence for mechanical engineering

Combining image data from ongoing operations with Machine Learning methods enables system users to assess directly the condition of the spindle surface. “We trained our algorithm with thousands of images so that it can now confidently distinguish between spindles with defects and those without,” says Tobias Schlagenhauf who helped develop the system. “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, 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 spindle surface and is transferrable to other applications.

Posted on June 15, 2020 - (84 views)
Karlsruhe Institute of Technology - Institute for Anthropomatics and Robotics (IAR)
Engler-Bunte-Ring 8
76131 Karlsruhe - Germany
+49-721 608-48935
View full company profile
Location
Related articles
Rugged COM Express Type 6 Module
EuroTech enters IBM Edge Ecosystem
ROS 2 Robot Controller
''Artificial Intelligence Helps Simplify Telecommunications''
Compact Embedded PC with AI Computing Power
Easy-handling Cobot
Polarisation Reveals Details That Were “Invisible”
AnotherBrain Accelerates its Development in 2020 to Deliver New AI Solutions Based on New Approaches
Samsung and Xilinx Team Up for Worldwide 5G Commercial Deployments
Defining a ''Roadmap of Promising Initiatives'' for the Digital Transformation
FLIR A8580 Compact LWIR HD Thermal Camera
FLIR A6750 SLS Thermal Camera
Thyristor Power Controllers
Highly-scalable Paperless Recorder
VisuNet HMI Systems
Microscope Optics for IR cameras
Faster Than a Speeding Bullet
Vision and Measuring Machines in Different Sizes
Faster Than a Speeding Bullet
High Precision Laser Scanner
Rugged COM Express Type 6 Module
Compact Embedded PC with AI Computing Power
FLIR A8580 Compact LWIR HD Thermal Camera
Scanner for Fast Tracking of Coronavirus Patient Samples
Smart Patrol Robots with Edge Gateway
PC System with 56 PCI-Express Lanes
Four-channel Laser Diode Driver Ics
Arm-based Qseven Module
FLIR A6750 SLS Thermal Camera
Deep Learning Segmentation & Classification Libraries
FLIR A8580 Compact LWIR HD Thermal Camera
Visual Inspection with Plug & Inspect™ Technology
Elevated Body Temperature Visualization Through Thermal Imaging
Visual Alert System in Case of Fall
Digital Platform for Energy Optimization
Automated ML Platform
Anti-collision Camera
Eurotech Congratulated by Frost & Sullivan for its Everyware Cloud
DataWalk Extends Data Analysis Solution to Help Goverments Fight Coronavirus
Data Extraction with AI-powered Anomaly Detection