Why break prediction needs 90 seconds, not 9
Lead time is the entire product. We walk through why a model that detects a break as it happens is an expensive event log, and what it takes to get usable warning from web-monitoring signals.
Blog
Notes from the wet end, the dryer section and the control room.
We publish when we learn something a process engineer would find useful — including the things that did not work. No thought leadership, no AI futurism.
Live example: Grade change PM4 · 135 gsm kraftliner → 110 gsm testliner, no break, ≤14 min off-spec
Latest
Recent posts
Ordered newest first.
The steam schedule should move before the basis weight
The standard grade-change sequence creates an avoidable moisture excursion because the dryer section unloads faster than the header can follow. Here is what 48 twin candidates found instead.
Nobody trusts a model. Everybody trusts a timestamp.
What actually changed crew attitudes during our first supervised-write deployment — and it was not accuracy.
Correcting an as-run twin without overfitting last week
How often to correct a machine twin against real reels, and how to avoid a twin that perfectly predicts the past.
Over-drying is a variance problem wearing an energy costume
Why tightening moisture 2σ has to come before moving the mean, and what happens when mills try it the other way around.
Sub-100 ms is not a benchmark, it is a constraint
What actually has to be true in the perception pipeline when the web moves 20 metres per second.
The rejected recommendation is the valuable one
Why we keep every override, and how crew rejections became our best training signal.
Wet-end chemistry does not need more sensors
It needs the existing charge and turbidity signals used against a live model instead of a fixed recipe.
Guarded writes: what actually sits between a model and a nip
A walkthrough of the six layers a recommendation passes before it reaches the DCS, with the failure modes for each.
Run timeline
The run most posts refer to
We use one worked example across the blog so comparisons stay honest.
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.
Series
Longer series
Multi-part writing on the harder subjects.
Building an as-run twin
Snapshotting a machine, choosing the physics that matter, correcting against real reels, and knowing when the twin is wrong.
Perception at the mill edge
Camera synchronisation, model optimisation with TensorRT, and what changes when you deploy to a machine rather than a benchmark.
Autonomy in practice
From advisory to bounded writes: the policy model, the approval design, the crew conversation and the two rollbacks we did.
Topics
What we write about
Six recurring threads.
Web vision and break prediction
Camera pipelines, defect classification, precursor modelling and the latency budget.
Papermaking science
Freeness, retention, formation, drainage, drying and the physics behind each control move.
Guardrails and trust
Policy engines, approval design, audit logging and what earns a crew's confidence.
Digital twins
As-run correction, candidate scoring, risk limits and where simulation stops being useful.
Steam and carbon
Dryer section economics, hood balance and the difference between margin and spec.
Field notes
What actually happens between the rack arriving and the first supervised write.
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] |
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
Measured
Figures we cite most
The numbers behind the writing [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.
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 |
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
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
Get new posts
We send a short note when something substantial is published. No newsletter cadence, no drip campaign.