Why the Internet of Things will lead to a rise in predictive maintenance



We bet that when thinking about ways to revolutionise your business, maintenance is one of the last things that springs to mind. But did you know there are an estimated 20 million maintenance technicians working from their vans every day?

From windmills on windfarms to elevator shafts in your office building, a whole host of upkeep is happening globally, 24/7.

Do the maths, and that’s an awful lot of manpower and expenditure on staffing and resourcing.

Right now, much of this maintenance is carried out on a scheduled basis. Take the elevator at work, for example: it probably gets checked by the maintenance team once every six months. This is commonly known as calendar-based maintenance. (The other main type of maintenance is reactive maintenance where things are fixed after they break down.)

If it was checked in February 2017, it will probably be checked again in August or September of that year. While this scheduled system works pretty well right now, it doesn’t take usage into consideration.

An event in your building such as a conference means usage will go up considerably. Where the schedule might have assumed a usage rate of 10,000 trips per month, that might spike considerably if there are unscheduled events.

The elevator might be used 20,000 times in one month – far above what was anticipated. Those extra uses could lead to a breakdown and loss in services long before the next round of scheduled maintenance.

Billions in savings

Under the traditional way of doing things, that usage spike would go unnoticed. But with Internet of Things-enabled components, the usage rate would be calculated by the elevator itself and sent to the maintenance team in hourly, daily, weekly and monthly reports.

According to research carried out by Dell, more and more people agree that predictive maintenance is the way of the future. Dell’s research said that IOT-aided predictive maintenance could:

  • Reduce overall maintenance costs by 13 percent per year
  • Reduce unplanned downtime to 3.5 percent
  • Increase return on investment in machinery by 24 percent

Maintenance can cost billions – especially around large-scale projects like utility or infrastructure networks. In Germany, the rail network has recently deployed IoT-enabled sensors on its rail tracks.

These sensors use algorithms to monitor the vibrations of the trains, then assesses the health of the tracks. The team behind the venture says that the IOT-enabled devices will lead to a reduction of 25 percent in maintenance costs over the next decade.

The rail industry is at the forefront of this model of predictive maintenance with VR Group, the state railway in Finland, using the Internet of Things to keep its fleet of 1,500 trains on the rails and provide a better, safer experience for its customers.

VR Group used scheduled maintenance to cover wheels and tracks and major systems – but used reactive maintenance to fix smaller items like train doors or seats. With the old way, if a door had to be replaced after suddenly breaking down, it could lead to delays, missed trains and ultimately, unhappy customers.

To remedy this, VR Group developed a predictive maintenance programme that focused on monitoring every single part 24 hours a day, 365 days a year. Kimmo Soini is the VP for maintenance at VR Group and he said that the predictive maintenance allows his technicians to fix problems before they become major issues.

"If a door on a train starts to open and close slower than usual, it is likely to break down within a certain time frame, and we must do something before that happens," said Soini. "Analytics allows us to develop our repair operations around predictive maintenance.

“In fact, we might be able to reduce the amount of maintenance work by one third. I believe that all maintenance will sooner or later be transformed by the Internet of Things, in all industries.”

It’s a strong prediction from Soini – and it’s one that few businesses can afford to ignore.

Are you considering a predictive maintenance model for your business?

If you want to integrate machine learning into your business, Statwolf’s data science service can help, with advanced online data visualisation and analysis simply running in your web browser. 

We offer a range of custom services to suit your needs: advanced data analysis and modelling, custom algorithm creation and implementation with a particular focus on Predictive Maintenance. Get in touch today to unleash your business’ potential.

Want to make sense of your data? Download our comprehensive guide: The Pedictive Maintenance Cookbook.

New Call-to-action