Can AI fully understand machines? Cutting-edge technology and solutions powered by artificial intelligence are embraced by specialist condition monitoring company, WearCheck, where the extreme accuracy of data used to assess and diagnose machine health is paramount. However, Annemie Willer, Manager of WearCheck’s ARC (asset reliability care) division, warns that certain diagnostic responsibilities should not be assigned to AI tools without considering the need for human intervention and experience. Plant maintenance, test + measurement
W e keep hearing worrying claims from industry stakeholders and customers, says Willer, that if you throw enough data from vibration, oil, thermography, process sensors, ultrasound, and AE (acoustic emission) measurement into an AI system, it’ll somehow converge into a perfect picture of machine health, complete with the precise corrective action to take. It’s a nice idea. It sounds like the future. But I don’t
behave in predictable, 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 lube, and still... they won’t age the same. One might run clean for six years. Another might seize up in eight months. And no amount of sensor data is going to tell you why – not reliably. This is because machines are not clones. They’re flawed. They are manufactured to tolerance, not perfection. Machined surfaces dier microscopically, and assembly is never identical. And once you add human hands, production targets, rushed shutdowns, and midnight shi¦ decisions into the mix – it’s not easy to feed that into an algorithm! 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 human maintaining the asset did when nobody was watching. It does not record the subtle looseness that a technician ‘felt’ but did not log. It does not register the fact that someone topped up with the wrong
Annemie Willer, WearCheck.
buy it, she says. Willer continues. Importantly, this is not because I’m anti- technology – quite the opposite. I have worked in diagnostics long enough to see the value of every tool we have. But I have also been around long enough to know this: machines don’t behave according to theory. And AI doesn’t understand that. For example, I o¦en encounter the myth of ‘convergence’ – the idea that all condition monitoring technologies can fuse into one holistic truth, which assumes that machines
In diagnosing machine health, Willer recognises the value of artificial intelligence technology but emphasises the importance of working with the insight afforded by seasoned engineers.
16 Electricity + Control FEBRUARY 2026
Made with FlippingBook flipbook maker