Fleet Maintenance Analytics: What are the differences?

Data has introduced new business value for fleet management. And for good reason: fleet owners and operators can improve the uptime of their vehicles. All it takes is the right view of data to make it happen.

Fleets have a lot of data on their vehicles. Telematics, fault codes, fluid samples, and work orders are just some of the data captured on vehicle performance. With data in many separate places, it can be overwhelming and unhelpful to make sense of it all.

So how do you know which tools move beyond basic visibility and create actionable insights? In this blog, we’ll explore the difference between various maintenance analytics, and what business value each brings to the table.

Descriptive analytics summarize historical data to provide insight into past performance. It answers the questions “what happened” or “what is happening?”

Descriptive analytics surface insights like:

• Your engine was running hot.

• A hard braking event occurred last week.

• Truck X used 1,500 gallons of fuel last month.

Think of descriptive analytics as the symptoms you list off to your doctor when you’re sick: “I can’t stop sneezing and I have a cough.” Your doctor uses this information to determine what actions need to be taken, the same way fleet managers analyze descriptive analytics to determine what maintenance to perform.

By itself, this information describes what’s happening, but it might have observations that are not actionable.

This is why descriptive analytics are often associated with reactive maintenance. Fleet and maintenance managers react to truck breakdowns, broken parts, or failing systems as they occur.

Doing so often leads to costly on-demand parts shipments, expensive road-side repairs, or unplanned towing costs to get the truck to a nearby shop. Many times, the cost of a tow exceeds $2,000.

Perhaps most damaging is the impact this method has on the relationship with the drivers. Drivers rely on quality equipment to earn a living. Sidelined equipment spurs the urge to look for new employment.

Examples: fault code diagnostics, fluid readings, telematics, other sensor data, work orders

Preventive maintenance is performed regularly on your vehicles to reduce the likelihood of failure. This type of maintenance is proactively performed while a truck is still working in order to prevent unplanned downtime. Preventive maintenance uses metrics like mileage, engine hours, and fuel usage to estimate when your vehicles will breakdown, and as a result, when they should be serviced.

Going back to our health analogy, preventive behaviors are comparable to the sweeping guidelines doctors provide to all patients to help them maintain their health: drink at least eight glasses of water per day, visit your general practitioner at least once per year for a routine checkup, get regular exercise, etc. These routine behaviors certainly help prevent issues from arising, but they are often standard practice. They aren’t tailored to you as an individual.

Preventive maintenance plays a similar role. It relies on guidelines, often provided by original equipment manufacturers (OEMs). It doesn’t take into account contextual or condition-based factors affecting individual vehicle performance. Preventive maintenance aims to address the needs of the “average fleet” in average conditions, but fleets and the way they operate their business is not one-size-fits-all.

Preventive maintenance is helpful in that it has consistent inspection and repair schedules. However, this can often backfire, with unexpected repairs rolling into the shop, or a vehicle breaking down on the side of the road. Checklists don't have visibility into vehicle conditions.

As a result, fleets report having a truck come through for a scheduled PM, give it a stamp of approval and send it down the road, only to have an unplanned breakdown happen 2 days later miles from the shop. The risk to the business of the failure is now greater, as delivery or service hangs in the balance.

Repair shops might like to replace warranty parts regardless of vehicle conditions, but pulling vehicles off the road because of a checklist isn't the most profitable.

By leveraging this type of maintenance, you run the risk of over- or under-maintaining assets. For example, preventive maintenance guidelines might suggest that "at 400,000 miles, your diesel particulate filter may need to be be cleaned or replaced.” But a truck that operates in colder temperatures and at a higher idle percentage will need to be serviced earlier and more frequently.

Examples: OEM manuals, shop customs

Rather than performing maintenance when a truck breaks down or when a calendar tells you it is time, fleets with predictive maintenance analytics have insights about when a failure may occur.

Why predictive maintenance? The better question may instead be: why bring in a healthy truck, when only a small portion of your fleet is at risk?

Predictive maintenance uses the data fleets have to notify fleet managers of condition-based maintenance needs. This type of maintenance is proactively performed when your vehicles are still working but at high risk of severe failures.

The goal of predictive maintenance is to transition from unplanned downtime — which is expensive and disruptive to operations — to planned maintenance.

Predictive insights are based on an individual vehicle’s condition. This is like having a personalized doctor who knows your everyday version of ‘normal’ just as well as you do. They can tell the difference between symptoms — between a cough that is asthmatic and one that's from a cold — and recommend specific actions to alleviate your symptoms before they worsen.

Predictive maintenance uses condition-based indicators and alerts to surface maintenance needs only when your trucks are at risk of breaking down — optimizing your maintenance cadence and maximizing vehicle availability. The risk of under- or over-maintaining your vehicles is mitigated.

While predictive maintenance tasks massive amounts of data into account, it ultimately presents fewer, more meaningful insights and data points — helping you avoid data overload.

The key to successfully implementing maintenance operations that meet your business needs is understanding what data can offer you.

• Do you simply need to know what has already occurred so you can budget for next year?
• Or do you need to know how to prevent unplanned downtime, lower costs, expedite repairs, and drive greater reliability?

As data accessibility becomes cheaper and more widespread in transportation and logistics, predictive maintenance is becoming table stakes for companies looking to remain competitive.

Ready to put your data to work?