Now live: a hybrid process digital twin for amine gas sweetening — it names the fault and the root cause, not just the alarm. Explore the platform →

QEM & OPS logo

Data & Analytics

Discover

Live in the platform

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.

See it in the platform How it works
7Sections, ordered like the plant
19View groups
85Logged channels
1 minSample resolution

What it does

Four things it does that a dashboard does not.

01

Structured like the process, not the database

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.

02

Eleven kinds of view

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.

03

Spec margin as a first-class number

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.

04

The diagnosis sits on the same timeline

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

The pipeline, end to end.

  1. 1

    Pick a window

    Any period in the loaded history.

  2. 2

    Read the KPI wall

    Latest value, the change over the last day, the range, and a status against the operating band — with a short trend behind each card.

  3. 3

    Open what looks wrong

    Every KPI opens into the charts it was built from. No dead ends, no exporting to a spreadsheet to see the detail.

  4. 4

    Ask what is driving it

    Ranked drivers against product quality, a correlation matrix across the circuit, and a free scatter explorer for anything the standard views do not cover.

  5. 5

    Overlay the events

    The fault episode timeline, on the same axis as the data.

Under the hood

The engineering, stated plainly.

Every figure on this page is countable in the delivered system. If you want to see where a number comes from, ask us and we will show you the record it is read from.

History
85 logged channels at 1-minute resolution, plus a slow lab series
Sections
Overview · treating · solvent · regeneration · hydraulics · relationships · events
Panel kinds
kpi · lines · profile · lab · corr · scatter · explorer · drivers · episodes · bars · snapshots
Precision
Each tag is displayed at its own engineering precision, not float noise
Assistant
Every panel publishes its summary to qemIntel

What it does not do

The limits, published on the same page as the promise.

  • It reads the history that has been loaded. It is not yet a live historian client — that connection is the next step, not a shipped feature.
  • A correlation ranking shows association, not causation. The causal map lives in Detect, and the two are deliberately kept apart.

Where it applies

Built for amine systems today. Not limited to them by design.

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.

  • Gas sweeteningLive today
  • Post-combustion carbon captureLive today
  • Other acid gas removalMethod applies
  • Wider process unitsFuture

The rest of the platform

One model. Seven ways to use it.

RunThe process digital twin that says what a healthy train should be doing.DetectNames the fault, the root cause, and what it costs per hour.PrognoseProjects the slow-wear faults against the threshold that declares them.qemIntelAsk the plant a question, and get an answer grounded in real data.OTSIn developmentTrain crews on faults they have never seen. In development.TuneIn developmentFind the valves and loops working against you. In development.

The fastest way to judge this is to open it.

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