The whole train, in numbers an engineer can read.
Discover is the analytics layer. KPI cards for the unit, and the charts behind every one of them — laid out the way a process engineer actually works through an amine plant: product first, then solvent, then energy, then hydraulics.
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
Overview, gas treating, solvent circuit, regeneration and energy, hydraulics and stability, relationships, and faults and events. You navigate the way you would walk the unit, rather than hunting for tag names.
KPI walls, trends, column temperature profiles, slow laboratory series, correlation matrices, a scatter explorer, ranked drivers, fault episode timelines, fault frequency bars and stored diagnosis snapshots.
Treated gas H₂S against its limit, and the distance remaining to it. Zero means off-spec. Removal efficiency is plotted against the acid gas load actually arriving, so a drop in performance can be separated from a rise in duty.
Fault episodes found by the engine are overlaid on the data that produced them. You can see the event and its evidence without switching tools.
How it works
Any period in the loaded history.
Latest value, the change over the last day, the range, and a status against the operating band — with a short trend behind each card.
Every KPI opens into the charts it was built from. No dead ends, no exporting to a spreadsheet to see the detail.
Ranked drivers against product quality, a correlation matrix across the circuit, and a free scatter explorer for anything the standard views do not cover.
The fault episode timeline, on the same axis as the data.
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