This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Extending intelligent monitoring of onboard machinery
Artificial intelligence for predictive maintenance
Real-time analytics and improved performance
Pankaj Sharma
Artificial Intelligence for predictive maintenanceModernization Project: Fully connected Yacht
Problems• Lack of existing sensors and integration
• Lagging in Digitalization curve
• High Risk of losses due to hotel equipment failure
Application• Hybrid approach to Digitalization
• Layering of information with new generation IOT sensors
• AI application for predicting trends
Artificial Intelligence for predictive maintenanceVibration sensors & Predictive maintenance
Artificial Intelligence for predictive maintenanceValue delivered: Breakdown averted
• Machine learning AI application was able to create thresholds by benchmarking all 4 AC units• In a very short period angular alignment issue was identified with a potential for motor break down in
future• Timely intervention and alignment check avoided a major breakdown
Real-time analytics and improved performanceValue of monitoring by experts
Issues and Actions list by monitoring analysts (Example)
Ref Boiler Pump II: The Vessel Engineer should investigate the possiblestiffening of the mounting structure of boiler pump II in the horizontal direction to avoid fatigue and potential damage to the mounting structure.
AC Compressors Root Cause investigation: Stop and lock out the compressor after it finished its running cycle. While still at operating temperature,remove the coupling cover and carry out a laser alignment as per laser system instructions. Align motor and compressor. If the motor/compressormounting plate is bowed it will require shimming of both the motor and the compressor feet
Update turbocharger, engine and generator alarm limits based on latest measuring results: New frequency ranges have also been defined, and measurements taken in the background. The dashboards will be updatedwith the revised Alarm limits accordingly.
‘3 P’ of Performance management at Columbia
Platform ProcessPeople
• Expert operators working in a 24/7 environment
• Robust processes key for End to End optimization
• AI capable State of the art system for monitoring