Tool wear under the microscope

The issue of tool wear is not a simple one. What is the importance of controlling and predicting the behaviour of tools? How do you draw the right conclusions from wear images? What data can you use to predict tool condition? Or how do you use direct measurements from camera images in a production environment?

Sirris is investigating how the condition of tools during production can be determined on the basis of production data. This may be data from external sensors or from available machine information. Using machine-learning algorithms, this data can be processed into predictions about the amount of wear, the time remaining and even the type of wear. Based on these estimates, certain action can then be taken (e.g. change, adjust parameters, continue).

During the masterclass on tool wear on December 7, organised as part of the Machining 4.0 project, theoretical insights will be interspersed with practical tools and demos, and time will be provided for questions, interactions and discussions.

The following topics will be covered:

  • Background and basic knowledge around wear and tear of tools and actions
  • Simulation of the production environment to reduce wear and tear, and practical implementation of these measurements
  • Deploying sensors to monitor wear and tear
  • Using vision and artificial intelligence to determine wear and tear autonomously
  • Solutions to reduce wear, such as new cooling methods or dampened tools

Interested? Learn more about our masterclass and register!