Chemical Plants
Ammonia, methanol, hydrogen and ethylene oxide plants all run a CO₂ removal loop on amine or hot potassium carbonate — the structure this platform was built on. But chemicals is the largest industrial energy consumer on earth, and almost none of that energy is in the removal loop. It is in the reformers, the crackers, the columns and the compressors around it.
SOURCEDIEA chemicals sector analysis · published steam cracking energy assessments. Every figure on this page is linked at the foot of it.
Part one — the capability
The engine does not know which solvent is in the loop. 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. That works on a removal loop, and it works on the fired equipment where the site’s energy actually goes.
What goes wrongFoaming, absorber flooding, lean/rich exchanger fouling, reboiler scaling and corrosion, filter plugging, solvent degradation.
What comes backThe closest unit on this page to the one we have already calibrated: absorber, flash, lean/rich exchange, regenerator and reboiler. The solvent changes — aMDEA, hot potassium carbonate, a physical solvent — the structure and the failure modes do not.
What goes wrongCatalyst deactivation and carbon lay-down, tube skin temperature drift, approach to equilibrium falling away, shift conversion loss, PSA recovery decay.
What comes backMeasured conversion against modelled conversion, with the shortfall attributed to catalyst, to firing or to feed — and the fuel each of those is costing per hour.
What goes wrongCoil fouling and coking, run length shortening, excess air and burner imbalance, selectivity drifting away from the target cut.
What comes backDecoking decided on a modelled cost curve rather than a calendar, and firing efficiency reported in fuel, money and CO₂ rather than as a percentage nobody can act on.
What goes wrongFlooding and weeping, tray or packing damage, reflux and reboiler imbalance, product specification giveaway that nobody prices.
What comes backSeparation efficiency against design, and the reboiler duty being spent to make a product purer than the specification requires — usually the quietest large loss on a chemical site.
What goes wrongPolytropic efficiency decay, fouled intercoolers, surge margin, seal and lube systems, refrigeration approach loss.
What comes backWhich constraint is actually binding right now, how far the unit is from it, and what that distance is worth per hour of run time.
What goes wrongLetdown that should have been a turbine, failed traps, imported power bought while steam is vented, and a site balance nobody has closed since commissioning.
What comes backA closed site energy balance, modelled against measured, so every unit’s share of the energy bill is a number rather than an allocation.
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
Chemicals buys more energy than any other industrial sector, which means a single percentage point is a large absolute number. On the left is how that energy is currently tracked. On the right is what independent studies say it is worth to track it properly.
To put one number on itA naphtha cracker making one million tonnes of ethylene a year at 29 GJ a tonne burns 29 million GJ. One percent of that is 290,000 GJ — on the order of $2–3 million a year at typical industrial fuel cost, from a single point of efficiency on a single unit. The assumption is stated so you can substitute your own fuel price; the arithmetic does not change.
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 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. A CO₂ removal loop in an ammonia or hydrogen plant is the same absorber-regenerator structure with a different solvent in it.
aMDEA, hot potassium carbonate or a physical solvent. What changes is the thermodynamic package and the fitted parameters; what stays is the equipment, the fault library and the way evidence is graded. This is the shortest calibration on the page.
Where the site’s energy actually goes, and where the published prize is largest. Conversion against modelled conversion and duty against modelled duty are exactly the questions a physics reference model exists to answer.
Separations, rotating equipment and the steam and power balance, reporting into a single objective function denominated in money. At that point every unit’s share of the energy bill is measured rather than allocated.
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. It is the same absorber-and-regenerator structure your CO₂ removal unit is built from.
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.