Gas Processing & LNG
Acid gas removal is where this platform was built, tested and proven: a real train, thirteen days of one-minute history, twenty-two named faults. But the method underneath it is not amine chemistry. Dehydration, NGL recovery, refrigeration and the liquefaction train fail in ways a physics reference model is built to catch — and in LNG each of them is measured in millions a day.
SOURCEDIGU 2025 World LNG Report · IEA LNG capacity tracker · US EIA · published LNG value-chain downtime analysis. Every figure on this page is linked at the foot of it.
Part one — the capability
The engine does not know it is looking at amine. It compares what the plant is doing against what physics says a healthy unit should be doing, ranks the gaps, names the cause behind each one and prices the consequence. Every block below is that same loop pointed at a different unit — which is why extending it is calibration work rather than invention.
What goes wrongFoaming, absorber flooding, lean/rich exchanger fouling, reboiler scaling and corrosion, filter plugging, pump cavitation.
What comes back22 named faults, each with the root cause behind it, the evidence that fired, and the cost per hour of leaving it alone. CO₂ slip caught before it reaches the cold box, H₂S before it reaches a specification.
What goes wrongGlycol carryover and losses, regeneration temperature drift, molecular sieve capacity decay, breakthrough earlier than the cycle assumed.
What comes backBed capacity against design capacity, how many cycles are genuinely left, and how much dry-gas margin stands between the plant and water in the cold box.
What goes wrongTurboexpander performance decay, column flooding, reflux and reboiler imbalance, product specification drift between the C2 and C3 cuts.
What comes backRecovery against modelled recovery, with the shortfall attributed to a machine, a column or a feed change — and priced per hour rather than argued at the morning meeting.
What goes wrongMixed refrigerant composition drift, cold box fouling and approach loss, compressor surge margin, driver limits, ambient-driven derate.
What comes backSpecific power against the model at today’s ambient conditions — which separates a hot afternoon from real degradation, something a trend line comparing this week to last cannot do.
What goes wrongSeal gas systems, anti-surge control fighting the machine, fouled coolers, lube oil, fuel gas quality and the steam and power that everything else depends on.
What comes backWhich constraint is actually binding right now, how far the train is from it, and what the distance is worth per hour of run time.
What goes wrongBoil-off gas handled by habit, losses estimated rather than measured, and a methane intensity figure assembled by hand for buyers who increasingly audit it.
What comes backModelled against measured balances across the plant, so a loss has a location and a methane intensity number has a derivation a buyer’s auditor can follow.
One answer, four audiences
A finding only a specialist can read gets ignored; a finding only a manager can read gets distrusted. Because every call is denominated in both engineering units and money, one output serves everybody without being rewritten.
One ranked list at the start of a shift, in plant units, with the evidence attached. Not four hundred alarms and a colour.
The residual against expected-healthy, the indicators that fired, the ones that corroborate, and the ones that would have ruled the fault out. Something concrete to disagree with.
Which item is degrading, how quickly, and what each week of delay costs. Cleaning and outage scope argued from a number instead of from a habit.
Energy and losses per unit, priced daily. The margin review and the emissions report draw on one model, so they stop disagreeing with each other.
Part two — the market
LNG is the clearest form of the argument on this page. The assets are enormous, the instrumentation is complete, and the operating decisions are still made from trend screens and a morning meeting. On the left is how the industry handles its measurements today. On the right is what independent studies say that habit costs.
To put one number on itOne avoided day of unplanned downtime on a mid-scale train is over $5 million in gross production, before take-or-pay. A platform that prevents a single trip in a year has returned its cost many times over on that one event — and the trip worth preventing is usually the one whose cause was sitting in the data for a week beforehand.
Why this and not another dashboard
A statistical model has to be shown the fault before it can find it. A physics reference model needs equipment datasheets. On a unit that has never failed inside its recorded history — which is most units, and every new-build — only one of those two is any use.
Every diagnosis carries the indicators that fired, the ones that corroborate it, and the ones that would have ruled it out. An engineer can argue with it. That is the only reason anyone in a control room ever acts on it.
Six consequences are priced directly, so a finding arrives as a cost per hour rather than a severity colour. The same output serves the operator, the planner and the board without being rewritten for each.
The cost of the next unit is datasheets, a tag list and a fitting pass — not a new product. That is the whole scaling argument: the platform grows by calibration, and calibration is the cheapest thing in this business to change.
The path from the calibrated unit
Each stage below reuses the same engine and the same knowledge-base structure. What changes is the unit it is fitted to — and that is deliberately the cheapest thing in this business to change.
Fitted against an operating amine gas sweetening train with thirteen days of one-minute history: 26 equipment items, 161 tags, 22 faults, 19 root causes, 54 indicators, 6 costed consequences. Calibration is fitted on the training history; single-point diagnoses run on data the model has never seen, and the separation is enforced in the code.
Inlet separation, dehydration and the mercury guard. Same solvent-and-adsorbent physics, same fouling and capacity questions, and units we can already describe from datasheets. This step is calibration and knowledge-base work, not new science.
Columns, exchangers and the turboexpander. Recovery against modelled recovery is a heat and mass balance question, which is what a reference model is for — and it is where the difference between a good month and a bad one usually hides.
Specific power, approach temperatures, surge margin and ambient correction, reporting into one objective function denominated in money. At that point the platform is not a monitoring tool. It is how the train decides what to do next.
Being straight about it
The platform runs on a real amine train with thirteen days of one-minute history behind it — live diagnosis, ranked evidence, root causes and cost per hour. Ten minutes in it says more about whether this extends to the cold end than any slide can.
Sources
The industry figures on this page are public and third-party. The amine figures — 22 faults, 19 root causes, 54 indicators, 6 costed consequences, thirteen days of one-minute history — are ours, and are countable in the platform.