Research report: Predictive Maintenance 4.0
A growing number of companies want to use big data analytics in their predictive maintenance and are also investing in the resources needed for this. Of the companies already using this technology, no less than 95 percent say that they have already achieved concrete results. This is the conclusion of a follow-up study conducted by PwC and Mainnovation among 268 companies in the Netherlands, Germany and Belgium.
Following the 2017 study into the maturity of companies in the field of predictive maintenance with big data analytics, PwC’s Michel Mulders and Mark Haarman, managing partner at Mainnovation, wanted to know to what extent companies have taken steps in the past year. Predictive maintenance with big data, level four within the maturity model, is called 'predictive maintenance 4.0' or PdM 4.0. PdM 4.0 makes it possible to predict failures that had been unpredictable up to now.
- We were interested to find out whether awareness of PdM 4.0 has grown, whether more use is being made of data, and in which areas investments are being made. But also the reasons why companies do not start using PdM 4.0, and especially what results the frontrunners in this field are achieving with this technology, says Michel Mulders, partner and industry lead Industrial Manufacturing at PwC.
Ninety-five percent of respondents indicated that PdM 4.0 is responsible for improving one or more key maintenance value drivers (uptime improvement, cost savings, reducing safety risks, extending asset lifetime). Meanwhile 60 percent of respondents managed to increase their 'uptime' with PdM 4.0, with an average improvement of nine percent.
The survey also shows that companies that achieve the greatest improvements in results thanks to PdM 4.0 clearly distinguish themselves from the other respondents. These 'PdM 4.0 champions' make significantly more use of 'environmental data' (such as weather conditions), characteristic of big data, and involve data scientists, reliability engineers and IT specialists in maintenance much more often.
Despite the fact that the number of companies using predictive maintenance with big data has remained stable, the study shows that there are clear indications that many companies have the ambition to increase their maturity in predictive maintenance. Sixty percent of the companies now indicate that they have concrete plans to use PdM 4.0, a significant increase compared to 49 percent in 2017. They clearly see the added value that PdM 4.0 can deliver.
More and more companies invest in competencies and personnel in order to get the most out of PdM 4.0. The research shows a sharp increase in the use of varied datasets, more advanced data sources and data software, data platforms and connectivity solutions. In comparison to 2017, there is also an increase in the number of data scientists, IT specialists and reliability engineers who are hired to realize the ambition to make full use of PdM 4.0.
Text: Seppo Rantanen
PdM 4.0 as a service
There are reasons to expect ‘PdM 4.0 as a service’ to become increasingly important, in particular for OEMs. For instance, consider the ‘power-by-the-hour’ business model adopted by some manufacturers of jet engines. Rather than selling jet engines as a product, these manufacturers sell its output – namely the power it generates - as a service, which obviously gives them a major incentive to improve reliability and uptime.
Continuous improvements in the digitization and connectivity of industrial assets are allowing their performance to be monitored remotely. As a result, OEMs that collect asset performance data from their customer base will have access to much richer data than is available to individual users of these assets. In turn, this gives these OEMs a distinct advantage when it comes to predictive analytics.
- We can thus speculate that OEMs will want to tap into this advantage by offering PdM 4.0 as a service, and that goals like ‘New revenue stream’ and ‘Better product design’ will become increasingly important value drivers for PdM 4.0, Mark Haarman, managing partner at Mainnovation says.
A wealth of plant and equipment data is now available to help process companies make operational improvements, but managing this data can be time-consuming. The latest asset performance platforms aggregate predictive intelligence and deliver concise information to the right people, wherever they are located.
With demands constantly increasing it is important that the production line remains at peak operational levels. Equipment maintenance is one of the key factors in achieving this goal and with today’s breakthrough technologies and practices, advanced maintenance is now affordable, easy and effective.