The future of maintenance: Applying analytics for predictive performance

Companies across the globe continue to invest in equipment, process, software and services to support their fleet maintenance and service programs. In fact, some original equipment manufacturer suppliers and third-party companies provide technology-capable equipment, intelligent analytics and software applications to help better understand what has been repaired, at what cost and why. But something vital is missing: collecting useful data while equipment is down for repair or in need of maintenance.

New demands for facility and warehouse managers
Facility and warehouse managers are expected to ensure equipment is available to move products as necessary. At the same time, there is a growing demand for data analytics to understand equipment maintenance needs from the beginning to end of service. For example, if equipment goes down at a facility or warehouse, a dispatcher calls a technician who specializes in repairing that equipment. That technician responds as directed. The technician may or may not respond quickly, depending on his or her availability. This creates additional downtime.

By collecting and analyzing data during downtime, operations can improve. Key performance indicators (KPIs) critical to understanding the time and cost dedicated to equipment maintenance include total time down, time to respond to repair, time to complete repair, first-time completion and equipment count in down status. Companies that capture these data can better analyze maintenance costs.

Once a company begins to look at analytics before a repair, it can better predict equipment needs, critical down or inoperable states, proper inventory for critical business needs, and cost to serve before any maintenance takes place.  

In addition, companies can more easily determine the status of equipment to plan for and ensure successful operation during busy periods. Vendors, partners and in-house technicians can start to identify performance requirements so they can respond when a critical piece of equipment needs maintenance or is down. For example, analytics captured can allow warehouse managers to know the status of equipment at any given moment — whether it is up, down or in repair — so he or she can make intelligent decisions for material handling efficiencies and needs.

The future: Integration of analytics and maintenance
In the future, software and service products will analyze these KPIs alongside various telematics and fleet maintenance programs.

Telematics pinpoint where equipment has been, who has been operating it and when something happened that may have caused the needed repair. These data reveal various insights ranging from impacts that occurred during operation to utilization of the equipment. Fleet maintenance programs analyze cost types, repair analytics and equipment deficiencies. Some of the most impactful metrics to analyze include cost per hour, avoidable repair costs, top parts used and cost trends by asset and location. This type of analysis helps users make better decisions on truck replacement versus repair, vendor billing and fleet management by area.

The bottom-line result: building a partnership between a company and its fleet management or service provider that enables both to manage smarter. Imagine having data analytics that clearly show:

  • Truck 13 in Warehouse 5 has a 78 percent uptime and averages 5.5 impacts per day across three operators. During that time, it has 60 percent utilization with appropriate lift and travel hours.
  • It’s a 2012 truck that has logged 2,990 hours with monthly maintenance costs of nearly $330 and an hourly operating cost of $3.27.  
  • Nearly 40 percent of Truck 13’s maintenance needs — and related costs — are avoidable, link directly to its daily impacts and contribute to 10 percent of its downtime.  

By analyzing what takes place throughout the equipment maintenance and repair process, managers can use that data to improve business practices, reduce costs and build a robust fleet maintenance program.

For more information, please visit