KPIs against the last period
Each headline number shows its value, the previous period and the change, marked better or worse.

The month, in one document.
Report rolls the shifts up into a week or a month for the people who do not read trends: production and on-spec time, energy and its cost, every fault and what it cost, availability, and what changed against the period before.
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
Each headline number shows its value, the previous period and the change, marked better or worse.
Every fault that fired, its hours, its share of the period, its peak confidence and its main root cause.
Steam used and what it cost, with the consequence costs of faults alongside.
Charts and short text instead of trends, so the report can go straight to people who were not on shift.
How it works
A preset week or month, or any range up to a quarter.
The diagnostic engine runs across every hour, on real timestamps.
Every KPI gets its change and a direction.
One document, ready to share.
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