Real moments or typed cases
A case is either a moment from the plant history or a set of inputs typed by hand. Both can sit in the same table.

Two cases, one screen. The difference is the answer.
Compare puts operating cases next to each other: this shift against the last, a good day against a bad one, or a proposed operating point against the one running now. Each value says where it came from — measured, lab, typed in, or modelled.
MVPEvery figure above is counted in the minimum viable product: the amine train modelled for gas sweetening and post-combustion carbon capture.
What it does
A case is either a moment from the plant history or a set of inputs typed by hand. Both can sit in the same table.
Measured, lab, default, edited or modelled. What no instrument measures is filled in by the reference model and marked so.
Change any input on a real moment and every output is recalculated by the model — the plant never ran there, so the page says so.
Compare calls the same engine as Run, so a number here is the number Run would show for the same inputs.
How it works
Pick moments from history or type inputs by hand, up to five.
Any of the 31 inputs can be changed on any case.
Measured values stay measured; everything else is modelled.
The table highlights what changed between cases.
Where it applies
The platform is focused on acid gas removal — gas sweetening and post-combustion carbon capture — because that is where the model is calibrated and where the fault library is real. The method underneath is not amine-specific: a physics reference model, residuals against expected-healthy, fuzzy diagnosis over graded indicators, and costed consequences. Extending it to another unit means new datasheets and a new calibration, not a new platform.
The platform runs on a real amine train with thirteen days of one-minute history behind it. Nothing on these pages is a mock-up.
Open the platform