Break rate cut from 14 to 5 per month
Break prediction with a 92-second median lead time gave the crew time to trim a nip or a draw instead of threading. 33 equivalent production hours recovered per month.
Case studies
The numbers, and how they were measured.
Every figure on this page is reconciled against the mill's own historian and reel records over a defined baseline period, not against our telemetry. All engagements are design-partner pilots [ASPIRATIONAL — pre-launch].
Live example: Grade change PM4 · 135 gsm kraftliner → 110 gsm testliner, no break, ≤14 min off-spec
Studies
Four engagements in detail
Different grades, different wedges, same measurement discipline.
Grade-change waste down 22%
Twin-rehearsed transition sequencing across 11 changes a week took off-spec tonnage from 9.8 t to 6.2 t per change and transition time from 19:05 to 11:42.
First-pass quality 91.4% → 96.8%
Full CD actuator control tightened basis-weight 2σ from 2.6 to 1.7 g/m² and reduced quarterly customer claims from seven to two.
Dryer steam down 7.9% per tonne
Yankee and hood rebalancing against live moisture removed the over-dry margin while tightening moisture 2σ from 0.31 to 0.19.
Run timeline
Case study: Aurora Board BM2 grade change
The exact run the 22% figure is built on — 135 gsm kraftliner to 110 gsm testliner, executed under bounded autonomy with one human approval gate.
run_8f21c4
PM4 · 6.8 m trim · 1,180 m/min
SUCCEEDED
-
01
ingest.grade_target
SUCCEEDED
0.8 s
Mill Orchestrator — Pulled the 110 gsm testliner spec, customer tolerances and the standing energy budget from mill MES; locked the target envelope for the run.
-
02
twin.simulate
SUCCEEDED
34 s
Mill Orchestrator — Simulated 48 candidate transition recipes on the as-run paper-machine twin — forming, press, dryer and calender — and ranked them on off-spec tonnes, break risk and steam.
-
03
stock.refine
SUCCEEDED
2 m 10 s
Pulp-and-Stock — Stepped refiner specific edge load 1.9 → 1.4 Ws/m and pushed freeness toward 412 CSF while consistency held at 3.4%.
-
04
wetend.dose
SUCCEEDED
1 m 26 s
Wetend-and-Chemistry — Retention aid trimmed to 214 g/t and sizing to 1.1 kg/t against live charge and turbidity; first-pass retention recovered to 78% inside 90 seconds.
-
05
form.headbox
SUCCEEDED
1 m 05 s
Form-and-Press — Re-cut the slice profile across 78 actuators and set jet-to-wire to 0.994 to hold formation index through the basis-weight ramp.
-
06
press.nip
SUCCEEDED
48 s
Form-and-Press — Nip load reduced 620 → 540 kN/m to protect the lighter web; post-press dryness landed at 47.1%.
-
07
dry.steam
SUCCEEDED
3 m 18 s
Dry-and-Coat — Re-phased the steam schedule across 6 dryer groups and rebalanced the hood; reel moisture converged to 7.4% ±0.19 2σ at 6.1% less steam than the standing recipe.
-
08
inspect.web
SUCCEEDED
continuous
Defect-and-Inspect — 18 line-scan cameras streaming; two edge-crack precursors detected at the drive side and cleared by a 40 kN/m nip trim before either propagated.
-
09
approve.human
APPROVAL
52 s
Mill Orchestrator — Speed ramp 1,180 → 1,245 m/min exceeded the site autonomy threshold. Held for the machine tender; approved by J. Okonkwo at 04:57:12.
-
10
reel.qualify
SUCCEEDED
1 m 31 s
Quality-and-Conformance — Reel R-24188 released: full genealogy written (furnish, chemistry, CD profiles, defect map, operator actions) and checked against grade spec.
Tool calls
The tool calls behind the result
Nothing in the case study is a claim you cannot trace back to a timestamped call.
- 04:51:04mes.read_orders({ machine: "PM4", next_grade: "TL-110" })
- 04:51:04ok spec locked · basis 110 g/m² · moisture 7.4% ±0.5
- 04:51:05twin.simulate({ candidates: 48, horizon: "18 min" })
- 04:51:39ok best recipe #31 · est. off-spec 6.4 t · break risk 0.07
- 04:51:40policy.evaluate({ recipe: 31, autonomy: "L3" })
- 04:51:40ok 9 writes permitted · 1 write requires human approval
- 04:51:41dcs.write_setpoint({ tag: "REF4.SEL", from: 1.9, to: 1.4 })
- 04:53:51ok freeness 388 → 412 CSF · consistency 3.4%
- 04:53:52chem.dose({ retention_aid: "214 g/t", sizing: "1.1 kg/t" })
- 04:55:18ok first-pass retention 71% → 78%
- 04:55:19dcs.slice_profile({ actuators: 78, jet_to_wire: 0.994 })
- 04:56:24ok formation index 84 · CD basis 2σ 1.7 g/m²
- 04:56:25vision.stream({ cameras: 18, model: "webdefect-v7" })
- 04:56:41precursor: edge crack risk 0.62 · drive side · 1,412 mm
- 04:56:42dcs.nip_load({ delta: "-40 kN/m", zone: "press-2" })
- 04:56:58ok edge crack risk 0.62 → 0.09 · web stable
- 04:56:59approval.request({ action: "speed_ramp", to: "1245 m/min" })
- 04:57:12ok approved by J. Okonkwo (machine tender) · logged
- 04:58:44mes.log_reel({ reel: "R-24188", genealogy: "full" })
- 05:02:46ok run complete · 11m42s · off-spec 6.2 t · breaks 0
Reasoning trace
Plan → thought → action → observation, exactly as the orchestrator recorded it.
GoalMove PM4 from 135 gsm kraftliner to 110 gsm testliner with zer…
Move PM4 from 135 gsm kraftliner to 110 gsm testliner with zero breaks and under 14 minutes of off-spec production.
PlanSimulate the transition on the twin first. Lead with stock and…
Simulate the transition on the twin first. Lead with stock and chemistry so the furnish is right before the basis weight ramps, then trim forming and press, then re-phase drying. Watch the web continuously; hold the speed ramp for a human.
ThoughtThe standing recipe drops basis weight and speed together. On …
The standing recipe drops basis weight and speed together. On the twin that produces a 3-minute moisture excursion because the dryer section unloads faster than the steam schedule can follow. Sequencing the steam re-phase ahead of the basis-weight ramp removes it.
Actiontwin.simulate(candidates=48) → recipe #31 re-phases steam 40 s…
twin.simulate(candidates=48) → recipe #31 re-phases steam 40 s before the basis-weight ramp and holds nip load until post-press dryness confirms.
ObservationRecipe #31 estimates 6.4 t off-spec against 9.8 t for the stan…
Recipe #31 estimates 6.4 t off-spec against 9.8 t for the standing recipe, with break risk 0.07. Two candidates scored lower on steam but raised break risk above the 0.15 site limit and were discarded.
ActionExecute recipe #31 under autonomy level L3: nine setpoint writ…
Execute recipe #31 under autonomy level L3: nine setpoint writes permitted, speed ramp routed to the machine tender.
ObservationEdge-crack precursor at 1,412 mm drive side at 04:56:41. Nip t…
Edge-crack precursor at 1,412 mm drive side at 04:56:41. Nip trim of −40 kN/m in press-2 cleared it in 16 s without a break.
OutcomeRun complete in 11 m 42 s. 6.2 t off-spec, zero breaks, 6.1% l…
Run complete in 11 m 42 s. 6.2 t off-spec, zero breaks, 6.1% less dryer steam than the standing recipe. Reel R-24188 released with full genealogy.
Results
Before and after, by engagement
Baseline period is 13 weeks immediately preceding deployment; measurement period is 13 weeks after the supervised-write phase began.
| Mill · machine | Metric | Baseline | With Pulpum | Change |
|---|---|---|---|---|
| Nordkraft PM4 | Breaks / month | 14 | 5 | −64% |
| Nordkraft PM4 | Threading hours / month | 19.6 | 7.0 | −64% |
| Aurora BM2 | Off-spec t / change | 9.8 | 6.2 | −37% |
| Aurora BM2 | Transition time | 19:05 | 11:42 | −39% |
| Ternvik PM1 | CD basis 2σ (g/m²) | 2.6 | 1.7 | −35% |
| Ternvik PM1 | First-pass quality | 91.4% | 96.8% | +5.4 pts |
| Cascadia TM3 | Steam / tonne (GJ) | 2.41 | 2.22 | −7.9% |
| Cascadia TM3 | Moisture 2σ | 0.31 | 0.19 | −39% |
| Valle PM2 | Freeness deviation (CSF) | ±11 | ±4 | −64% |
| Hokuriku PM5 | Release records complete | 86% | 99.2% | +13.2 pts |
In detail
Two studies, unpacked
What actually changed on the machine, not just what changed on the report.
Nordkraft PM4
Break prediction as the wedge
The mill had a break rate it could not explain and a break log with no precursor characterisation. Eleven weeks of labelled break replays trained an edge model that surfaces edge-crack, flutter and wrinkle precursors with usable lead time.
- 18 line-scan cameras, sub-100 ms classification
- 92-second median lead time on predicted breaks
- Counter-move recommended, not just an alarm
- 33 equivalent production hours recovered per month
agent.defect_inspect SUCCEEDED
| Signal | Before | With Pulpum |
|---|---|---|
| Breaks / month | 14 | 5 |
| Median lead time | 0 s | 92 s |
| Broke t / month | 410 | 160 |
Cascadia TM3
Energy without touching crepe
The site had a hard energy target and had already taken the easy reductions. The remaining margin was in over-drying, protected by moisture variation nobody wanted to touch on a tissue machine.
- Moisture 2σ tightened before the mean was moved
- Per-group scheduling with hood balance
- Crepe structure and bulk held within spec throughout
- Energy budget enforced as a hard constraint
agent.dry_coat SUCCEEDED
| Signal | Before | With Pulpum |
|---|---|---|
| Steam / tonne | 2.41 GJ | 2.22 GJ |
| Moisture 2σ | 0.31 | 0.19 |
| Crepe deviation | baseline | unchanged |
Method
How we measure, and what we exclude
A case study is only useful if the method survives scrutiny from the mill's own process engineers.
Baseline from your historian
Thirteen weeks immediately preceding deployment, extracted from the mill's systems, agreed in writing before anything is installed.
Like-for-like grade mix
Results are normalised for grade mix and machine speed. A quarter with an easier order book does not become a Pulpum result.
Excluded periods
Planned shutdowns, known equipment failures unrelated to control, and commissioning weeks are excluded from both periods.
Attribution stated honestly
Where a mechanical upgrade or a furnish change coincided with deployment, it is named in the study and the figure is qualified.
Mill sign-off
Every published figure is signed off by the site's process engineering lead before it appears here.
Audit log attached
The underlying run records are available to the customer in full, and to prospects under NDA.
Measured
Aggregate
Across all design-partner engagements [ASPIRATIONAL].
11 m 42 s
Grade change on PM4 · baseline 19 m 05 s
6.2 t
Off-spec tonnes per transition · baseline 9.8 t
68%
Web breaks predicted more than 90 s early
7.9%
Less dryer steam per tonne of paper
Figures are design targets and pilot-scoped results [ASPIRATIONAL]. Every number is reproduced from the mill's own reel genealogy, not our telemetry.
From the control room
What machine tenders say
Autonomy earns trust one shift at a time. These are design-partner quotes from pilot deployments [ASPIRATIONAL].
"The first thing that convinced the crew wasn't the control — it was the log. You can scroll back and see exactly why it dropped the nip. Nobody argues with a timestamp."
Machine tender · PM4 · Nordkraft Mills
"We had two people who could do a clean 135-to-110 transition. One retired in March. The twin now does the sequencing and the second one supervises it."
Production manager · Aurora Board
"Break prediction was the wedge. Ninety seconds of warning is the difference between a nip trim and four hours of threading."
Process engineer · Ternvik Paper
Autonomy
Four levels, set per agent and per tag
A mill does not go from manual to unattended in one step. Pulpum makes the level explicit, auditable and reversible at any time.
| Level | What the agent does | What the human does | Typical time to reach |
|---|---|---|---|
| L1 · Advisory | Recommends setpoints and explains why | Enters every change manually | Week 1 |
| L2 · Supervised | Proposes a write; it executes on approval | Approves each write in the HMI | Week 3–6 |
| L3 · Bounded | Writes inside tag, rate and magnitude limits | Approves ramps and grade releases | Month 2–4 |
| L4 · Unattended | Runs the envelope without prompting | Sets the envelope; reviews the shift record | Month 6+ [ASPIRATIONAL] |
Guardrails
An agent that can move a nip needs a leash
Pulpum writes to production equipment. Every capability is scoped, every write is policy-checked, and every action is written to an append-only audit log the mill owns.
- Bounded action space. Each agent can only write to an explicit tag allow-list, inside per-tag rate and magnitude limits.
- Policy engine before every write. Autonomy level, shift, grade, interlock state and operator presence are all evaluated before a setpoint moves.
- Human-in-the-loop gates. Anything above the site threshold — speed ramps, grade releases, safety-adjacent moves — waits for a named approver.
- Immutable audit log. Append-only, hash-chained, exportable, and retained on the mill's own storage.
- Hard fallback. Loss of the edge node, the network or the model returns control to the DCS's last known-good state within one scan cycle.
- Tenant and IP isolation. Furnish recipes, grade models and defect libraries never cross a customer boundary. On-prem deployment available.
Compliance posture
| Standard | Scope | Status |
|---|---|---|
| SOC 2 Type II | Cloud control plane | RUNNING In progress [ASPIRATIONAL] |
| ISO 27001 | Company-wide ISMS | QUEUED Planned [ASPIRATIONAL] |
| IEC 62443 | Mill-edge OT security | RUNNING Design-aligned |
| GDPR | Operator data | SUCCEEDED Compliant |
| ISO 9001 / FSC | Quality + chain of custody records | SUCCEEDED Supported |
FAQ
Straight answers
The questions mill managers and process engineers actually ask in the first meeting.
Yes, but only within an explicit tag allow-list with per-tag rate and magnitude limits, and only at the autonomy level your site has set. Level 1 is advisory-only: Pulpum recommends and a human enters everything. Most mills spend their first weeks there before enabling supervised writes.
Control returns to the DCS last known-good state within one scan cycle. Pulpum is designed as a supervisory layer on top of your existing control system, never as a replacement for it, so a Pulpum outage degrades the mill to its current way of running — not to a stop.
Break prediction and defect classification typically need 8 to 12 weeks of QCS, DCS and inspection history per grade family, plus labelled break events. Advisory recommendations start in week one from the physics-based twin, and improve as mill-specific history accumulates.
Only if you choose cloud training. Recipes, grade models and defect libraries are tenant-isolated and never used to train another customer's models. A fully on-prem deployment with an air-gapped mill edge is available for sensitive producers.
You are, the same as with any control strategy — which is why every write is policy-checked, bounded, logged and reversible, and why anything above your risk threshold waits for a named approver. The audit log records the request, the reasoning, the limits applied and the human decision.
A 90 to 120 day mill-edge deployment on one paper machine, scoped to a single workflow with a pre-agreed baseline [ASPIRATIONAL]. Weeks 1–3 are connection and shadow-mode observation; weeks 4–8 advisory; weeks 9+ supervised or bounded writes if the mill is satisfied with the recommendations.
Get started
Run the same measurement on your machine
A mill review starts with your historian extract and ends with a wedge, a baseline and a payback estimate in your own numbers.