Cut break minutes
Break prediction with real lead time, plus the counter-move. Target: 60%+ of breaks flagged more than 90 seconds early.
Solutions
Pick the number you need to move.
Mills do not buy autonomy. They buy fewer breaks, cheaper steam, tighter profiles and less waste on every grade change. Each Pulpum solution starts from a number your mill already reports.
Live example: Grade change PM4 · 135 gsm kraftliner → 110 gsm testliner, no break, ≤14 min off-spec
By outcome
Six solutions, six baselines
Every engagement starts by agreeing what we are measuring and what it is today.
Lower steam per tonne
Per-group dryer scheduling and hood balance against live moisture. Target: 6–9% less steam per tonne without widening moisture 2σ.
Raise first-pass quality
CD profile control plus per-reel spec checking. Target: first-pass quality above 96% with claims down by half.
Shrink transition waste
Twin-rehearsed transitions with step-by-step execution. Target: 20%+ less off-spec tonnage per change.
Cut additive spend
Live dosing against charge and turbidity instead of a fixed recipe. Target: 10%+ lower additive cost per tonne.
Free the crew
Robotic reel and roll handling plus automated genealogy. Target: 3 hours per shift of manual work removed.
Run timeline
What a solution looks like in practice
The grade-change solution, running end to end on PM4.
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 agent shows its work
Every tool invocation, argument and result is written to an immutable, human-readable log — and every reasoning step is expandable. Nothing about a run is hidden from the mill.
- 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.
Engagement
How a 90-day pilot runs
No open-ended discovery. A pilot has a machine, a workflow, a baseline and a date. [ASPIRATIONAL — pilot programme structure]
Week 0 · Scope
Pick one machine and one workflow. Agree the baseline from the mill's own historian and reel records — not from our telemetry.
Week 1–3 · Connect
Mill-edge node installed, QCS/DCS/vision connectors configured, historian backfilled. Pulpum runs in shadow mode and writes nothing.
Week 4–8 · Advise
Agents run at L1 advisory. The crew sees recommendations in the HMI and accepts or rejects them; every rejection becomes training data.
Week 9–12 · Supervise
If the crew is satisfied, L2 supervised writes are enabled on the scoped tags. Each write is approved in the HMI before it executes.
Week 13 · Review
Results reconciled against the agreed baseline, in the mill's numbers. Expansion or exit is decided on that number alone.
After
Convert to the Machine tier, then expand by module, machine and autonomy level as the site clears its own gates.
Use cases
By grade
Different grades, different constraints
Containerboard SUCCEEDED
Speed and breaks
The fastest machines in the industry with the least tolerance for downtime. Break prediction and transition sequencing dominate the business case.
Tissue SUCCEEDED
Energy and crepe
Yankee energy and crepe consistency are the levers; sheet breaks are frequent and expensive.
Coated print & specialty SUCCEEDED
Profile and gloss
Claims come from CD variation. Profile control and coating consistency carry the return.
Board & food packaging SUCCEEDED
Conformance
Food-contact and chain-of-custody traceability turn reel genealogy from nice-to-have into a release requirement.
Business case
Two numbers most mills underestimate
The cost of a break and the cost of over-drying are both larger than they look on the monthly report.
Break economics
A break is not 40 minutes
By the time you count threading, broke, the ramp back to speed and the off-spec tail, a single web break on a fast containerboard machine routinely costs three to five hours of equivalent production.
- Threading and re-ramp time
- Broke repulping and energy
- Off-spec tail after restart
- Downstream finishing disruption
agent.defect_inspect SUCCEEDED
| Signal | Before | With Pulpum |
|---|---|---|
| Breaks / month | 14 | 5 |
| Equivalent hours lost | 52 | 19 |
| Broke tonnes / month | 410 | 160 |
Energy economics
Margin is a habit, not a spec
Most dryer sections run a moisture margin because the alternative — an off-spec reel — is worse. Tighten the variation and the margin becomes available immediately.
- 2σ tightened before the mean is moved
- Per-group scheduling, not a single header
- Hood balance included in the optimisation
- Energy budget enforced as a hard constraint
agent.dry_coat SUCCEEDED
| Signal | Before | With Pulpum |
|---|---|---|
| Reel moisture mean | 8.3% | 7.4% |
| Moisture 2σ | 0.31 | 0.19 |
| Steam / tonne | 2.41 GJ | 2.22 GJ |
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] |
Measured
Solution targets
Design targets used to scope pilots [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.
Multi-agent handoff
Agents negotiate, they do not collide
Two agents will want the same actuator. The orchestrator arbitrates on the run goal, not on who asked first — and the handoff is logged like any other step.
Contested move: press-2 nip load
-
01form_press.request(nip −0 kN/m) SUCCEEDED0.2 s
Form-and-Press wants to hold nip load to protect post-press dryness.
-
02defect_inspect.request(nip −40 kN/m) SUCCEEDED0.2 s
Defect-and-Inspect wants to reduce nip load to clear an edge-crack precursor.
-
03orchestrator.arbitrate SUCCEEDED0.4 s
Break risk 0.62 outranks a 0.4-point dryness loss under the run goal "zero breaks". Defect-and-Inspect wins the actuator for 120 s.
-
04form_press.handoff(returned) SUCCEEDED120 s
Actuator returned; Form-and-Press recovers dryness with vacuum instead. Post-press dryness lands at 47.1%.
Arbitration rules
- Run goal first. Every request is scored against the declared goal, not the requesting agent's local objective.
- Safety and breaks outrank quality. A break costs hours; a profile excursion costs minutes.
- Time-boxed ownership. An agent holds a contested actuator for a bounded window, then must re-justify.
- Everything is logged. The losing request, the score and the reason all appear in the run record.
- Deadlocks escalate to a human rather than resolving by timeout.
Anatomy
What you actually get
A run engine, an audit trail and a number that moves.
The orchestrator plans, the agents act
A run starts as a goal, becomes a plan, and executes as a graph of typed steps. The active path is always visible, always logged, always reversible.
RUNNING APPROVAL SUCCEEDED
Autonomy is a dial, not a switch
L1 advisory, L2 supervised writes, L3 bounded autonomy, L4 unattended within an envelope. Each site sets the level per agent, per tag, per shift — and every write above the threshold waits for a named approver.
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
Integrations
It speaks mill, not cloud
Pulpum reads and writes through the systems already on the floor. No rip-and-replace, no parallel historian, no new HMI to learn.
Valmet IQ, ABB 800xA QCS, Honeywell Experion MX
Profiles, scans, lab results
ABB 800xA, Valmet DNA, Honeywell Experion, Siemens PCS 7
Setpoint reads and guarded writes
WIS/WMS line-scan, IR and transmission cameras
Frames, defect maps, break replays
SAP PP/QM, ABB cpmPlus, custom historians
Orders, grades, reel genealogy
OSIsoft PI, Aspen IP.21, InfluxDB
Time-series backfill and replay
NVIDIA Isaac, winder and wrapper PLCs
Reel, roll and clamp-truck motion
Azure AD, Okta, on-prem LDAP
SSO, RBAC, named approvers
NVIDIA Jetson Orin, IGX, on-prem GPU
Sub-100 ms inference at the machine
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 |
Enterprise
Standardise autonomy across the group
One policy model, one audit trail, one benchmark across every machine in every mill — with the grade and furnish models kept private to each site.
- SSO, SCIM and role-based access down to the tag level
- Group-wide autonomy policy with per-site override and approval chains
- Cross-mill benchmarking on broke, breaks, steam and first-pass quality
- VPC, on-prem and fully air-gapped mill-edge deployment options
- 99.5% control-plane SLA; edge autonomy survives control-plane loss
- Dedicated deployment engineer and quarterly model review per site
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
Scope a 90-day pilot
Start with one paper machine and one measurable baseline. A 90-day mill-edge pilot on break prediction, drying energy or moisture profile shows the number before you commit further.