What’s Happening to Maintenance?
Klaus M. Blache | October 24, 2018
Every day we see and read articles, reports, and studies about new technologies and ways of doing business that will drastically change how we need to perform our jobs.
According to this information, all we must do is set up 3D printing for spare parts on demand, sensors to collect data, virtual reality for training, and augmented-reality to deliver maintenance instructions to the plant floor. Add to that a smart assistant (probably integrated into your personalized IoT wearable), lots of predictive analytics with data from your historian, and ongoing machine intelligence that builds algorithms for continual improvement on ROI decisions.
Then put this all on a cloud-based platform to enable easy access and use the cumulative data to enable life-cycle decisions at point of purchase and guide better designed-in parameters for new machinery and equipment.
Yet, most companies are still struggling with the fundamentals of implementing and sustaining a basic reliability and maintainability process. Many typically do not trust their data. A usual comment is, “I think our data is at best 50% accurate.” Doing more condition-based data collection will help these situations over time as more real-time facts are collected. It will not instill the culture of discipline needed to reap the benefits of a top-quartile process.
The Summit IBM supercomputer, developed at Oak Ridge National Laboratory, TN, as of June 2018, is the fastest in the world, capable of 200 petaflops. That’s 200 quadrillion (x1015) floating-point operations per second (FLOPS). At the same time, they have done a very good job of PM optimization to support the infrastructure that keeps things running. This was done at the much slower speed of several decisions per hour with regular meetings to review current tasks and make decisions toward better maintenance practices (it’s that culture of discipline that enables infrastructure success).
Much of this new technology is still in its infancy, especially when it comes to practical and affordable applications. For most, it’s an enormous void from current practices (just trying to get product out the door and reacting to maintenance issues) to using the digitally enhanced tools, big data, and machine intelligence.
With so much new digital technology coming our way and practical applications to better run the business not keeping up, companies are unsure of what to do next. A five- to seven-year time of uncertainty is normal when there is such a global and disruptive transition. The accompanying graph is Gartner’s “hype cycle”, which visually displays the maturity of emerging technologies through five phases. Currently the global maintenance-digital transition is in the second phase: Peak of inflated expectations.
I recommend doing at least two things. This sounds simple, but if it was, companies would all be doing it:
• Do a pilot project in one area (no matter how small) to demonstrate the practices and advantages of a properly run reliability and maintenance process.
• Clean up your data so it’s believable or most of the benefits of the upcoming technologies will be useless.
The point is to do something. As Mark Twain said, “The secret of getting ahead is getting started.” EP
Based in Knoxville, Klaus M. Blache is director of the Reliability & Maintainability Center at the Univ. of Tennessee, and a research professor in the College of Engineering. Contact him at email@example.com.