One of the most notable advances in recent years when it comes to air gases is the opportunity to drive greater efficiencies with the latest real-time sensors and with data-driven self-learning tech.
It is something that was explored in a wider context at the recent EIGA Winter Summit in Antwerp and is backed up by lots of on-the-ground improvements at specific projects, with more in the pipeline.
The air separation units (ASUs) that make most the world’s air gases can deliver more with the application of artificial intelligence-driven automation, predictive analytics, and digital twins. These advances can, among other things, drive the efficiency, reliability, and energy use of the plants.
Most ASUs have until recently relied on manual controls allied to maintenance schedules to deliver the most efficient separation of atmospheric air into oxygen, nitrogen, and argon (as well as neon on occasion). But now machine learnings and AI is reshaping the operational paradigm.
... to continue reading you must be subscribed
