Pumps, plantwide, and digital transformation

I engage with hundreds of customers every year and regardless of the industry, when the discussion turns to plantwide monitoring - let alone enterprise-wide monitoring - pumps always manage to steal the spotlight.

The reason is simple: every industry has them - LOTS of them - and virtually every industry spends too much money maintaining them. The attitude towards pumps has historically been that because many or perhaps most are spared, a pump failure wasn't really too consequential in terms of process impact and thus didn't justify permanent monitoring - just a walk-around program instead. Of course, that doesn't account for pumps handling toxic and/or flammable materials and the ensuing havoc when one fails, catches fire, and brings not just its own process loop but the entire plant to a screeching halt. Those applications generally do merit more than monthly rounds with a portable data collector and thus get bona-fide machinery protection. In fact, that's one of the primary use cases for the 2300 series monitors in our portfolio. But those aren't the class of pumps I'm focused on in this article.

It's instead the class of pumps where the impetus to do things differently isn't necessarily driven by the consequences of failure - its driven by the high costs of maintenance. On those machines, it isn't death by a single cut. It's death by a thousand cuts because each one of them can - and often does - inflict a small cut in terms of maintenance costs and the costs of acquiring data. If we were talking about a few dozen machines, those costs might get lost in the rounding errors of the overall maintenance budget.

But rarely is it a few dozen.

The number of garden-variety pumps in many industrial facilities often exceeds one hundred and frequently exceeds several thousand.  Speaking with the individuals responsible for these machines, most report using a labor-intensive, manual approach to data collection.  And while this approach may work in terms of avoiding fires or other major events, when management look at how much money is spent, the questions start coming. 

When baselined against more critical machines, it becomes clear that the maintenance costs of pumps are excessive on a percentage basis.  Yes, the reliability levels may be acceptable in aggregate because the machines are often spared. However, what’s not acceptable is the costs to achieve these levels.

Pumps are ripe for digital transformation in age of AI

I frequently talk to another group of people in many plants. These are individuals in roles that didn’t even exist 15 years ago: digital transformation leaders. 

Many are not rotating machinery experts, nor should they be. They typically take a high-altitude view of all the things happening within an organization and look at all the possible ways that digitally transforming an approach or process can be beneficial. They then decide which projects offer the most compelling return on investment. Pumps are frequently emerging at the top of their list. 

Here’s why.

For starters, the large number of pumps within any given plant mean that small improvements to the maintenance or performance of each one can lead to significant benefits. Secondly, the price of wireless sensing has dropped dramatically which has made it economically feasible to digitize data collection.

Unfortunately, a lot of companies stop at the point of digitizing data collection, thinking they’ve transformed their process.  What they quickly realize though is that somebody must now review all the incoming data, and alarm management turns into a full-time job.

What many digital transformation leaders are seeing, however, is not a challenge but an opportunity.  That’s because many of them understand the power of AI – they’ve seen it used elsewhere with good results.  In contrast, many rotating equipment personnel are highly skeptical because they’ve seen all the hype but rarely the promised results.  In fact, in a recent survey of customers with a rotating machinery focus, 46% told us that they were skeptical of AI in these applications, and 27% told us they’d tried using AI and it underperformed.  

Many of us in the business shared some skepticism about AI until we saw it done right. Then the lightbulbs came on. 

AI can do the diagnostics, meaning people no longer need to sift through data looking for problems.  And increasingly, AI can go beyond diagnostics to prescriptive recommendations. This frees people up to spend time fixing problems and eliminating defects, rather than looking for and analyzing problems.  That’s the real opportunity provided by digital transformation: digitizing the collection and analysis of data and translating it into simple, actionable insights like the one below. 

“Your bearing is showing signs of wear, most likely from unbalance.  We saw the same issue on this machine 31 months ago.  Bearing replacement within the next 45 days is strongly recommended along with balancing before returning the machine to service.  In the meantime, we’ll be monitoring it daily and notify you of any substantial changes that warrant more immediate intervention.”

The key is purpose-built AI that is trained to understand what a pump, a motor, a fan, or other asset is and to know the difference between unbalance, misalignment, a bearing defect, or a loose foundation bolt.  The AI also needs training to understand the operating and failure modes of these assets, not just at room temperature in a lab setting, but across different settings and 100’s of millions of hours of runtime. 

The AI we use has already been trained in this way and the numbers show that, when applied to this class of machines, it is delivering on its promise.   Its ability to detect a problem exceeds 95% accuracy while its ability to precisely identify the type of problem – in other words, diagnostic accuracy – exceeds 99%. 

In part 2 of this blog, I will translate what this means in terms of ROI and scalability from plantwide to enterprise-wide levels. I will also share how the delivery model we’ve chosen offers rapid payback and ease of deployment, helping businesses exceed the ROI thresholds used to separate the so-what projects from the must-dos.