Industries · Chemicals & process manufacturing
Chemicals & process manufacturing
Written for
Plant scheduling, supply-chain planning and formulation R&D at a specialty or bulk chemicals maker.
The decision
Which production plan to run this shift; which formulation to make next.
How it is done today
Scheduling in spreadsheets or a legacy APS that takes hours to re-plan, so the plant runs yesterday’s plan.
When it goes wrong Every hour of re-planning is an hour of changeovers and due dates decided on stale data.
Applications
| Application | You give | You get | Status |
|---|---|---|---|
| Production scheduling across grades and changeovers Proof 6 h → 1 min, across 100+ product grades, in daily use | Grades, due dates and capacity | A checked plan in minutes | Deployed through the platform network |
| Nesting and job-shop scheduling (sheet, batch, multi-machine) | Jobs, machines and sequences | The sequence and the nesting | Deployed through the platform network |
| Formulation and additive candidate ranking Proof Four of four formulations ranked correctly on IBM Heron, materials lane | Candidate molecules | A ranked list with the gaps | Live on quantum hardware |
| Catalyst and process-chemistry screening | Candidate catalysts or intermediates | A ranking with binding and activation energies | Ready · computed, hardware next |
| Revenue management and order acceptance | Orders, margins and capacity | Which orders to accept | Deployed through the platform network |
| Predictive maintenance on cable and rotating assets Proof Early warning on cable breaks moved from 2 days to 5–7 days | Sensor history | Earlier warning | Deployed through the platform network |
What changes for you
- Re-plan on demand instead of once a shift.
- Formulations ranked before the pilot plant.
- A straight answer when your current solver already wins.
First engagement
You send One week of plant data: grades, orders, changeovers, capacity.
You get back The re-plan and the comparison with your current plan. Two weeks.
Proof · Production scheduling
Customer deployment · platform network
6 h → 1 min
production schedule across 100+ product grades, recalculated in 1–10 minutes instead of 2–6 hours, in daily use
Baseline The plant’s prior manual and spreadsheet planning
Platform Classical optimisation solvers, delivered through our platform network
Decision
Which production plan to run this shift
What is modelled
100+ product grades with changeovers, due dates and capacity, as a constrained scheduling model.
Operational outcome
- Re-planning on demand when conditions change
- Verification included in the run time
- In daily production use
Problem size 100+ grades · one plant · minutes per re-plan · Scope A classical optimisation deployment; quantum hardware was not used.
Benchmark
Published reference No published production-scheduling result on quantum hardware at industrial scale; visible results are challenge prototypes. arXiv:2411.10303
Merlin 6 h → 1 min across 100+ grades, in production
Baseline The plant’s prior manual planning
Further results in this industry
- Formulation screening from the semiconductor row applies to specialty chemicals: candidates ranked on a quantum processor before any are made.
Case studies
Semiconductors · materialsQuantum hardware · Simulation
Resist candidates ranked before any were made, so only the lead goes to synthesis and wafer testing. Award winner, 2nd place worldwide, GIC 2026 Advanced Materials track (Mitsubishi Chemical Group × AIST).
Platform network results
Results delivered through Merlin’s platform network, with the client anonymised to its sector and the figure quoted with its published conditions. These are not Merlin hardware runs.
Chemicals & process manufacturingPlatform network
Production scheduling in minutes, not hours
2–6 h → 1–10 min
A Japanese chemicals manufacturer rebuilt its production schedule in two to six hours — too slow to react to a change within the same shift.
Production scheduling cut from 2–6 hours to 1–10 minutes, using classical optimisation.
Delivered through Merlin’s platform network · classical optimisation
Other industries
Semiconductors & advanced materials · Energy & utilities · Mobility & automotive · Telecom · Pharma & life sciences · Finance · Security & critical infrastructure · Aerospace & sovereign programmes