Thermal drift prediction for improved tool tip accuracy

Participants

Etxetar

Universidad Polit├ęcnica de Madrid

Aingura insights

Transportation and storage Transportation and storage
Transformation Transformation
Data Acquisition Data Acquisition
Preprocessing Preprocessing

Sectors

Manufacturing Manufacturing

Applications

Maintenance Maintenance
Condition Monitoring Condition Monitoring

impact

  • 8% improvement in machine availability.
  • Improved machine design by detecting the part of the machine that is most sensitive to thermal changes.

Develop AI Technologies

  • Data intelligence.
  • Smart sensors.
  • Intelligent automation.
  • Machine learning.
  • Pattern analysis, prediction and intelligent classification.

objectives

  • To increase in machine availability in through high temperature gradients in production facilities. Due to these gradients, the machine/manufacturing line had to be idle around 2 hours.
  • Support to the PLC/CNC compensation system to withstand extreme temperature changes.
  • Improvement of the machine design according to the study of the sensitivity of different parts of the machine to extreme changes in temperature in a real productive environment.
  • To complement analyzes done with finite elements during the machine design phase.
Correlation between temperature and machine structure.
Correlation between temperature and machine structure.

results

  • Dataset size: 2GB
  • Number of variables: 15
  • Sampling time: 100ms
  • Development of the first unattended system for the acquisition and pre-processing of machine data and interaction with the PLC.
  • A predictive system for tool tip positioning has been developed.
  • Development of an off-line variable selection model.
  • Development of a multi-output regression model for continuous variables of temperature and flow.

Contact us