MPC holds the unit. RTO decides where.
Plant-wide optimisation that computes the most profitable operating targets for your MPC and APC systems — every hour, at today's prices.
How Real-Time Optimisation works for your plant.
Real-Time Optimisation sits above the control layer. Using a plant-wide model, current constraints and current economics, it computes the most profitable feasible operating point — and passes those targets down to your MPC and APC controllers to execute.
Change the prices. Watch the optimum move.
A unit with two decisions — feed rate and reactor temperature — and three constraints. The colours are profit per hour; the hatched region is infeasible. Move the prices and the optimiser finds the new best feasible point and dispatches it to the controllers.
- Profit = product value − feed cost − energy cost
- Constraints: max throughput, max temperature, min quality
- Toy model — the method is the product's
Plant-wide steady-state model built.
Model matched to live plant data.
Most profitable feasible point computed.
Targets passed to the MPC/APC layer.
Three layers, three timescales.
“Your MPC holds the unit steady. RTO decides where steady should be — in money.”
From the field · SMHcoders
Do we need MPC before RTO?
In practice, yes. RTO computes profit-optimal targets; MPC or APC is the layer that executes them. If you run MPC today, RTO is the natural next step.
What data do we need to start?
Most engagements start with 6–24 months of historian, lab or document data. We audit coverage in the first week and tell you plainly if it is not enough — before you commit.
How long until we see results?
A proof of concept on your historical data typically lands in 4–8 weeks. Production deployment follows once the KPI target is met and your team signs off.
Where does it run, and who sees our data?
On your infrastructure — plant-side servers, your Azure or AWS tenancy, or an air-gapped network. Data never leaves your boundary, and nothing is used to train third-party models.
Who owns the result?
You do. Handover includes source code, documentation, training sessions and a retraining plan.