Learn about the differences between preventative maintenance and predictive maintenance.
Are maintenance professionals, including reliability engineers, about to go the way of blacksmiths? Digital Transformation makes it possible for IT staff to deliver Predictive Maintenance (PdM) results, but there is still tremendous value and need for maintenance pros.
In the early 1800’s, the blacksmith was one of the most valuable citizens of any town. It was the blacksmith that kept the wheels of commerce rolling. They were essential to keeping the wagon trains, stage lines, and the farms and ranches working. If something broke, they fixed it. Then along came the industrial revolution, built in large part by mass production of interchangeable parts.
Before this, manufacturing shift parts were all hand made for each and every machine and if something broke a part had to be repaired or rebuilt, or a whole new part made to fit the machine had to be crafted. With interchangeable parts, the blacksmith’s ability to craft parts locally was made irrelevant because you could just carry spares for all the machinery. This gave rise to the role of the mechanic. Someone who could disassemble and reassemble machines to fix them. This relegated the blacksmith to the role of the artisan who today, ply their trade at craft fairs and folklife events.
The essayist and philosopher George Santayana said, in 1905, "Those who cannot remember the past are condemned to repeat it, " and I admonish maintenance professionals to think carefully about this in the context of the blacksmith.
Digital Transformation & the IIoT – Another Industrial Revolution
Industrie 4.0, Smart Manufacturing, or whatever other name you care to ascribe to the Digital Transformation that is driving industry today is dependent on and intertwined with the Industrial Internet of Things (IIoT). From the LNS perspective, an IIoT Platform includes not only the devices, the connectivity infrastructure, and the device management capabilities, but the Big Data and Analytics capabilities that let you derive value from IIoT-available data. Predictive analytics has become so intrinsic to Digital Transformation that no credible platform vendor doesn’t either provide it as base level functionality or have a partnership with IIoT ecosystem partners that have that functionality.
Everyone points to Uber as a transformative example of technology, but in manufacturing we see it unfolding somewhat differently. One area the IIoT has immediate payback is in improving asset reliability. LNS has written frequently on this topic. Therein lies both the problem and the opportunity for maintenance professionals.
Predictive Analytics No Longer Demands Mega Skills
PdM and reliability-centered-maintenance (RCM) served as the foundation for the concepts of Asset Performance Management (APM). Although most see APM as being broader than core RCM/PdM today, the analytics element was the trigger that made APM a critical process to many businesses. The earliest solutions often relied on deep domain knowledge and intimate analytics skills. This commonly meant solutions were custom, expensive, and applicable only in the most asset intensive forms of industry. As the cost of computing power has come down, devices have become more powerful, and data science has become more of a recognized discipline the situation is changing.
Still, there remains a skills shortage that is driving technology to do even more. Enter the next generation of analytics –Machine Learning. With systems now able to analyze such large volumes and disparate types of data, Machine Learning allows technology to teach itself what it should be monitoring. No longer is a highly skilled maintenance professional needed to spend days or weeks sifting through data to find the causes and indicators of problems; computers themselves can make reasonable inferences.
As Always, IT Seeks Business Relevance and Alignment
LNS’s survey data shows that in many cases the IT department has been tasked by business leadership “to drive the adoption of the IIoT and get the company on the path to Digital Transformation.” This is often because the IIoT is the place where IT and OT meet. I have been in industry for more than 45 years and for the vast majority of that time CIO’s, and before them, the IT directors have been trying to prove the value of IT to the business. The mandate to prove out the value of IIoT to the business is real, and IT organizations would be foolish to ignore the opportunity handed to them.
Since PdM and APM are such easy to justify ROI cases, it is no wonder that this is the area many are looking to make their mark. Fortunately, at least for the IT folks, Machine Learning makes this doable without having to become process or reliability experts. More importantly, the IT staff have access to ready-made analytics engines with some machine learning capabilities such as Splunk, SAP Leonardo IoT, or IBM Watson, among others, in many cases. LNS has seen a number of impressive use cases where IT-centric tools have been used to provide IIoT PdM value.
Reliability Engineers Need to Look at New Tools
Of all the maintenance professionals today, the reliability engineers are the ones most likely to become the next generation of blacksmiths. As Machine Learning makes it possible for many IT professionals to pilot IIoT projects to deliver PdM results, often with impressive ROI, reliability engineers will be challenged to show where they can still add value.
Fortunately, the door isn’t closed, and the horse isn’t out of the barn yet. Machine Learning and the IT based analytics tools are still evolving and not yet capable of tackling the most complex analysis of large and complex systems. Also, reliability engineers can use those IT based analytic tools just as readily as their IT counterparts to solve the easier problems and most likely they can do it faster and with better results. The blacksmiths of the 1800’s who thrived were those that understood the impact interchangeable parts were going to have and became mechanics, as well as blacksmiths.
All entries in this Industrial Transformation blog represent the opinions of the authors based on their industry experience and their view of the information collected using the methods described in our Research Integrity. All product and company names are trademarks™ or registered® trademarks of their respective holders. Use of them does not imply any affiliation with or endorsement by them.