Case
Saving lives with intelligent technology
This Machine Health solution makes it so much easier to monitor our critical equipment. With minimal training, my technicians can quickly use and become familiar with the platform. That allows us to identify and diagnose issues before they become serious headaches.
Discover how a top-ranked hospital remained operational
- 75% cost reduction per monitored machine
- $750,000+ saved by early identification of issue
- 3 catastrophic failures prevented
The challenge
A leading educational and research hospital needed to ensure that its machines were up-and-running at all times. Since the hospital’s on-site power plant provides power for life-critical equipment, machine failure was not an option. Previously, the maintenance team contracted the Predictive Maintenance (PdM) analysis to a third party. However, results were vague, generic and unactionable. It culminated when a crucial pump failed unexpectedly. By that point, the maintenance team knew they needed to find a partner that would help transform their maintenance program.
The solution
Thanks to continuous monitoring, the hospital’s maintenance team is now able to schedule condition-based maintenance to proactively address developing issues and avoid downtime. Providing insights at both machine- and facility-level, the team can focus on the equipment needing the most immediate attention, reducing wasted Preventive Maintenance (PM) hours and eliminating unexpected failures, ensuring guaranteed uptime for the hospital’s most life-critical equipment.
The result
Within the first 12 months of deployment, the maintenance program at the hospital had been transformed. The intelligent algorithms detected 3 potential catastrophic failures in the chilled water and steam system – failures which, if left undetected, would have resulted in a total maintenance cost of more than $750,000. In addition to these cost savings, the ease of scalability meant that the maintenance team were able to increase the number of monitored machines from 44 to 155, while reducing the average cost per monitored machine by 75%.