Preventive maintenance relies on average or expected machine-life statistics, and can at best predict when maintenance will be required. It cannot predict machine breakdown.
And it also fails to deliver expected machine uptime results.
SO, WHAT IS THE REAL CHALLENGE?
The real challenge is to determine the actual condition of each individual in-service equipment to predict when maintenance should be performed.
This approach promises cost savings over routine or time-based preventive maintenance because tasks are performed only when warranted.
WE BUILT A SOLUTION THAT WORKS
In one case, curating 4 million failure ticket records from over 8,500 ATMs helped us develop a machine learning model for predicting ATM failure in North America. We achieved 14.3% operational efficiency and 18% cost reduction in maintenance.
We use the same AI model for our ‘Insights-as-a-Service’ offering to provide ‘breakdown insights’ for other machines.
AND THE RESULTS ARE MEASURABLE!
In the case of the ATM predictive maintenance program, the algorithms predicted ATM fault in 60 milliseconds with 80% accuracy