Scenario analysis workspace
PHL Simulate
Compare a baseline with an alternative before anything changes on the floor. The first release offers two deterministic scenario models whose arithmetic you can read, with every assumption written down next to the result.
- Status
- Two models in first release Available in MVP
- Models
- S1 threshold replay · S2 cell capacity
- Method
- Deterministic. No stochastic or physics model yet
- Output tag
- SCEN
- Physics
- External validated engines only Future capability
01S2 · Cell capacity model
What happens if the conveyor runs faster?
Change the speed of CNV-001 and watch the bottleneck move to the packer. Every number comes from the formula shown under the table.
SCEN S2 · Cell capacity model · deterministic
Illustrative scenario| Output | Baseline 100 % | Alternative 115 % | Change |
|---|---|---|---|
| CNV-001 conveyor rate (units/h) | 1,200 | 1,380 | +180 |
| Cell throughput (units/h) | 1,200 | 1,214 | +14 |
| Bottleneck station | CNV-001 | PKG-001 | changed |
| Packer infeed buffer | Not filling | Full in ≈ 43 min | changed |
| MTR-001 load (linear estimate) (%) | 68 | 78.2 | +10.2 |
- MTR-001 load ≤ 85 % (assumed limit)78.2 % estimated
- Packer infeed buffer does not fill within 60 minFull in ≈ 43 min
Calculation and assumptions
throughput = min(1,200 × speed, 1,320 × 0.92) · buffer fill = 120 ÷ surplus · load = 68 % × speed
- Steady state only: no start-up, changeover or stochastic stoppages.
- PKG-001 effective rate = rated 1,320 units/h × 92 % planned availability, treated as a constant.
- CNV-001 rate scales linearly with belt speed from its rated 1,200 units/h.
- MTR-001 load scales linearly with conveyor speed from its 30-day mean. Not validated for this drive.
- Packer infeed buffer holds 120 units and starts empty.
Results follow from the model and assumptions listed. This is not a physics simulation and not a validated prediction.
02S1 · Threshold policy replay
Would a lower limit have warned us earlier?
Replay PMP-001’s last 30 days of vibration readings against an alternative warning threshold, using exactly the logic the live rules engine uses.
SCEN S1 · Threshold policy replay · PMP-001 vibration, last 30 days
Illustrative scenario| Output | Current 4.5 mm/s | Alternative 4.0 mm/s |
|---|---|---|
| Alert episodes | 16 | 18 |
| Total time in alert | 1 d 23 h | 5 d 21 h |
| First alert before the 21 Sep inspection | 2026-09-18 17:50 | 2026-09-15 17:00 |
| Lead time vs current rule | — | 3 d earlier |
Replay applies the live rule logic to recorded readings only. 5 h of missing data is excluded. It describes the past; it does not predict future behaviour.
03How a scenario runs
From baseline to a reproducible result.
Pick a model and baseline
Choose S1 or S2 and the twin version and data window it should use.
Check model requirements
Pre-run validation lists any missing input, such as a station’s rated rate, and links to where to set it.
Set parameters and constraints
Parameters are bounded and unit-checked. Accepted defaults are written into the assumptions.
Run and compare
Baseline and up to three alternatives side by side, with signed deltas and units.
Interpret with limits
Assumptions and limitations stay visible under every result; nothing is collapsed away.
04Model requirements
Each model needs specific inputs.
| Model | Needs | Produces | Claim allowed |
|---|---|---|---|
| S1 Threshold replay | Stored readings for the signal; one or more rule sets | Alert episodes, time in alert, lead time vs a reference event | “With this history, policy B would have raised N alerts.” Exact, about the past |
| S2 Cell capacity | Station rated rates, availability, buffer sizes, the feeds graph, baseline motor load | Throughput, bottleneck, buffer fill time, linear load estimate | “Under the stated assumptions…” Steady-state approximation |
| Physics models | Validated engineering models, an external engine, a named model owner | Engine outputs with the engine’s name and validation status | Only what the engine and its validation support Future capability |
05Capabilities and status
Available, planned and future.
| Capability | What it does | Status |
|---|---|---|
| Scenario creation from a twin baseline | A scenario references a twin version and a data window; it never copies assets. | Available in MVP |
| Parameter adjustment | Bounded, unit-checked parameters with the change from baseline marked. | Available in MVP |
| Constraints | For example maximum motor load or buffer fill time. | Available in MVP |
| S1 · Threshold policy replay | Re-runs the live rule logic over recorded readings. | Available in MVP |
| S2 · Cell capacity model | Steady-state throughput, bottleneck and buffer fill time. | Available in MVP |
| Assumption tracking & run history | Every run stores inputs, assumptions, model version and an input hash. | Available in MVP |
| Scenario comparison reports | Exportable, with limitations stated. | Available in MVP |
| Pump and fan affinity-law estimates | Idealised estimates, labelled as such. | Planned |
| Discrete-event line model | Stochastic stoppages and queues; uncertainty only when computed from replications. | Planned |
| Physics-based simulation | FEA, CFD or multibody through an external engine with validated models. | Future capability |
| Omniverse / USD scene-linked simulation | For customers with engineering-grade models. | Future capability |
Bring your industrial systems into clearer view.
Start with a focused equipment workflow and expand toward connected digital twins and industrial simulation as your requirements evolve.
Illustrative demo · no signup · not connected to equipment