Cutting-edge technology and solutions powered by AI are embraced by specialist condition monitoring company, WearCheck, where the extreme accuracy of data used to assess and diagnose machine health is paramount. However, it is important that certain diagnostic responsibilities are not just assigned to AI tools without considering the need for human intervention and experience. Annemie Willer, manager of WearCheck’s Asset Reliability Care (ARC) division, explains what this means.
“We keep hearing claims from industry stakeholders and customers that if you throw enough data from vibration, oil, thermography, process sensors, ultrasound and acoustic emission (AE) into an AI system, it’ll somehow converge into a perfect picture of machine health, complete with the exact corrective action to take. It’s a nice idea. In fact, it sounds like the future, but I don’t buy it.
I am not anti-technology, quite the opposite. I’ve worked in diagnostics long enough to see the value of every tool we have; but I’ve also been around long enough to know that machines don’t behave according to theory, and AI doesn’t account for this. For example, I keep encountering the myth of ‘convergence’. This is the idea that all condition monitoring technologies can fuse into one holistic truth, which assumes that machines behave in predictable and repeatable ways, but they don’t. You can install ten pumps from the same OEM, running under the same process conditions, in the same plant, with the same lubrication, and they won’t age in the same way. One might run clean for six years. Another might seize up in eight months. No amount of sensor data is going to reliably tell you why.
This is because machines are not clones. They’re flawed. They are manufactured to tolerance, and not perfection. Machined surfaces differ microscopically and assembly is never identical. Added to this are human hands, production targets, rushed shutdowns and midnight-shift decisions. It is important to take the real-world situation into account when assessing an asset. AI relies on data, but data only captures what the sensors see, not what the maintenance person did when nobody was watching. It does not record the subtle looseness that a technician ‘felt’ but didn’t log. It does not register the fact that someone topped up the wrong grease, or skipped torque checks or ran a fan uncoupled for three minutes at startup.
No historian records that and without this real-world information, AI is blind to the issues that actually cause most failures. I believe that every condition monitoring technology has its place, and its limits. For example, vibration monitoring tells us about mechanical behaviour; oil analysis identifies lubricant condition and contamination; thermography picks up heat and load imbalance, AE and ultrasound testing give early warnings of friction, turbulence or sparking; and process data provides the operating context, but not the root cause of failure.
These monitoring techniques and their test results don’t converge neatly. One doesn’t combine them to get a better truth. Rather, they should be compared to demonstrate different perspectives. That’s what makes condition monitoring powerful, it’s a team effort, not a solo act.
Can we rely on AI?
AI is useful, just not in the way that the vendors keep claiming. It can spot changes over time, rank the risks, filter out noise and highlight anomalies − and all of this is valuable. However, AI cannot know the history of every shaft and housing. It cannot understand why a lube change worked for one gearbox and not the next. It cannot interpret subtle mechanical behaviour that only a human technician would notice, and it cannot predict how different people on different shifts handle the same piece of equipment. AI can help one find where to look, but not what to do when you get there.
I have always told our customers that machines are messy and that this is not a problem, it is merely the reality. Machines have personalities, not literally, but in how they wear, respond and behave under pressure. This is not related to engineering design or process control; it has to do with maintenance history, human touch and physical realities that no AI-powered model, however sophisticated, can learn.
The idea that AI will converge all technologies into one correct decision ignores this complexity. It reduces the craft of diagnostics to a logic problem, when in fact, it’s part science, part art and always tied to context. Let AI support us. Let it help us scale, see patterns and work smarter; but let’s stop pretending it can replace understanding or diagnose machines like a seasoned engineer can. Machines don’t live in the cloud, they live in the real world where convergence isn’t the goal, clarity is.”
For more information contact WearCheck,
© Technews Publishing (Pty) Ltd | All Rights Reserved
printer friendly version