With predictive maintenance, AI keeps the wheels rolling

Whether you’re talking about a fleet of city buses, a coffee chain’s espresso machines, an office’s networked laptops and printers, or even a natural gas pipeline, these things need regular restocking and servicing to avoid breakdowns. You want to avoid disruptions in service, unhappy customers, revenue losses, maybe even threats to public safety.

The traditional solution has been to set up a routine maintenance schedule: Change the oil every 5,000 miles, stress-test each pipeline joint every five years, sharpen the grinder burrs on your espresso machine every 1,000 pounds of coffee.

Schedules can’t foresee the future

The problem is, schedule-based maintenance doesn’t account for machines wearing out sooner than planned – or staying in working condition longer, which means they’re taken out of service for routine checkups and getting new parts “just in case,” cutting into profitability.

The ideal would be to intuit when your machine is starting to run low, and take it in for servicing just before it starts developing problems. But until recently, that was hardly a realistic option, since it relies on either frequent, labor-intensive checks or a sixth sense.

However, technology has now matured enough to do the checking for you. The first ingredient is small, inexpensive, ubiquitous sensors, connected by the Internet of Things (IoT), which relay steady streams of data about temperature, pressure, capacity, location, and many other important factors.

The other key ingredient is predictive analytics, infused with artificial intelligence (AI). Properly instructed, this type of software can tirelessly sum up all the factors reported on by IoT sensors, superimpose them on performance history and standards, and make real-time predictions about when a component needs service. The result is predictive maintenance.

The intelligence is key because it monitors the millions of signals your IoT network could be sending – a task that would drive your staff mad, if you could even hire that many people to stare endlessly at screens – and screens for just the ones that are significant.

Focus on what makes a difference

Using predictive maintenance means organizations get updated status reports on all their fleet members, down to the last train wheel or panini toaster, and can focus their efforts on only the components that need it. This kind of AI-enriched insight delivers:

• Smoother, more predictable operations because problems can be addressed pre-emptively, not after a disruption
• More uptime, which equals more revenue generation opportunity
• Happier customers, since there’s less risk planes will get stuck on the tarmac or the power will go out
• Lower repair and maintenance costs and labor overhead
• Higher safety levels, as the need for service can be detected before a failure occurs
• Less risk of litigation or penalties for unscheduled failures

In fact, predictive maintenance typically reduces machine downtime by 30 to 50 percent and increases machine life by 20 to 40 percent.

Recent estimates are that it can save 20% or more of maintenance costs for industrial machinery. For some cases, such as engine oil changes, it could reduce the overall cost of failure by up to 67%. Considering that industrial machinery repair costs $36 billion a year just in the U.S., it’s clear that predictive maintenance offers large potential savings.

Predictive maintenance saves money and time

Where you have large numbers of relatively inexpensive assets in heavy use, such as espresso machines or shared bikes, predictive maintenance saves money by focusing maintenance techs’ attention preferentially on the machines closest to failure, rather than performing unneeded inspections on machines that were chugging along just fine. It improves uptime, boosts revenue opportunities, and increases customer satisfaction.

Predictive maintenance also helps public and nonprofit institutions such as hospitals, utilities, and mass transit agencies, which generally have more expensive assets (from MRI machines to dams to natural gas pipelines), though fewer of them. It can more thoroughly highlight maintenance needs, targeting the components that most need attention. This can reduce the risk of inconvenient or even dangerous outages through accidents, downed lines, and so forth.

Citizens are happier when they can rely on their buses or flights leaving on time, their medical treatments taking place as scheduled, and the lights staying on.

Intrigued? Learn more about the benefits of AI-enriched analytics.

Stannie Holt

Stannie Holt is a Marketing Content Writer at OpenText. She has over 20 years' experience as a journalist, market research analyst, and content marketing expert in the fields of enterprise business software, machine learning, e-discovery, and analytics.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Close