Learning to Love Data Science

Chapter 8. Predictive Maintenance: A World of Zero Unplanned Downtime

For want of a nail, the shoe was lost. For want of a shoe, the horse was lost. For want of a horse, the rider was lost. For want of a rider, the message was lost. For want of a message, the battle was lost. For want of a battle, the kingdom was lost. And all for the want of a horseshoe nail.

Traditional rhyme

Topline Summary

In the old days, the only real way to measure the life span of a machine was running it until it broke. The problem with that approach is that you can never be quite sure when a machine will break. If it breaks on a Sunday morning, when nobody desperately needs whatever the machine does, then it’s not a big deal. But if it breaks on a busy day, during peak business hours, then you’re looking at problems. If the machine in question is a jet engine on an airliner crossing the Pacific, you’re looking at really serious problems.

Now imagine a world in which machines and systems never break down unexpectedly. That’s the goal of predictive maintenance: no surprises. Predictive maintenance requires a combination of sensor-equipped machines, networks, and advanced analytics. This report, written in January 2015, examines the emerging field of predictive maintenance and describes its role in our increasingly automated societies.

Breaking News

Nothing grabs the attention of C-suite executives more effectively than talk of profits, which explains the current buzz around predictive maintenance. ...