The Draweon platform is a plant-edge inference runtime on NVIDIA Jetson, a plant orchestrator with a policy engine, specialist agents for every section of the line, and an as-run twin that rehearses each run. Everything an agent does is typed, bounded and logged.
Illustrative scenario: EX-3 · 2.5 mm² class 2 PVC building wire, changeover, no spark faults
Perceive the conductor, plan the run, act inside limits, inspect continuously, optimise yield and takt, log everything, retrain. The layers below are the design, not a description of a shipped system.
PLC and SCADA on drawing, stranding and extrusion lines, laser diameter and eccentricity gauges, eddy-current heads, spark testers, cameras, drives, annealer controls, extrusion heads, cooling zones, capstans, take-ups and quality systems. Signals are normalised into one time-aligned reel and length record.
DeepStream and Holoscan process video and sensor streams on Jetson Orin. TensorRT-optimised models detect defects and drift; time-series models predict die wear, breaks, wall variation, conductivity risk and spark probability. Triton serves them with canary rollout by line.
The plant orchestrator assigns work to specialist agents. Agents retrieve procedures and specs through permission-aware retrieval, evaluate action envelopes, ask for approval when required, and write through OT connectors only when safety gates pass.
The Omniverse twin receives as-run telemetry, compares it with planned process windows, and tests candidate recipes before the next run. GPU CFD and thermal simulation for extrusion, drawing and stranding dynamics.
Training, fleet model registry, versioning and enterprise reporting. Federated aggregation across plants is planned and waits on customer data-rights agreements. Per-tenant isolation throughout.
A review console for process and extrusion engineers to approve, correct and give feedback. Corrections train the models. An append-only quality and safety audit log records every agent action from day one.
The core user flow, in order. Outputs are reviewed by a process or extrusion engineer whose corrections train the models.
Every Draweon run is an ordered, inspectable sequence. This is run_3d7a1e on EX-3 · 2.5 mm² class 2 PVC building wire. Scenario completes in 10 steps with one approval gate. Wall settles at 0.80 mm nominal, minimum 0.66 mm, concentricity 0.93, no spark faults, reel R-30417 released with full genealogy.
Plant Orchestrator · Pulled the construction spec for 2.5 mm² class 2 PVC building wire from MES: 7 × 0.67 mm conductor, 0.80 mm nominal wall, 0.62 mm minimum spot wall, 6 kV spark test, 48 km order. Locked the target envelope.
Line Twin · Simulated 36 candidate recipes on the as-run line twin for draw schedule, lay length and extrusion setpoints, ranked on wall variance, concentricity, predicted spark risk and polymer give-away.
Draw-and-Anneal · Capstan tension on RB1 stepped down 6% as the die-wear estimate crossed its threshold. Diameter held at 0.670 mm ± 0.004 mm and the break-risk score fell from 0.31 to 0.09.
Draw-and-Anneal · Annealer current trimmed against the live conductivity reading to hold the softness target without over-anneal through the speed change.
Strand-and-Cable · Lay length set to 28 mm on bunching line ST2 with payoff tension balanced across 7 spools. Roundness index held above 0.97 into the extrusion payoff.
Insulate-and-Jacket · Screw speed and zone 3 temperature re-cut against melt pressure and material-lot moisture. Wall settled at 0.80 mm nominal, minimum 0.66 mm, concentricity 0.93.
Defect-and-Inspect · 6 cameras, the laser gauge, the eddy-current head and the spark tester fused at the edge. One neckdown precursor at 12,480 m flagged and cleared by a screw-speed trim before it reached the reel.
Plant Orchestrator · Line-speed ramp 1,100 to 1,250 m/min exceeded the site autonomy threshold. Held for the shift process engineer and approved at 06:41:52.
Robot-and-Handling · Reel change on take-up TU3 planned and executed by the handling robot. Payoff aligned and tension re-established inside the changeover window.
Quality-and-Conformance · Reel R-30417 released: genealogy written (conductor lot, draw and anneal record, lay, wall and concentricity trace, defect map, approvals) and checked against the construction spec.
Every tool invocation, argument and result is written to an append-only, human-readable log, and every reasoning step is expandable. Nothing about a run is hidden from the plant.
Plan, thought, action, observation, exactly as the orchestrator would record it.
Change line EX-3 over to 2.5 mm² class 2 PVC building wire, hold 0.80 mm nominal wall and concentricity, and finish the run with zero spark faults.
Simulate the changeover on the twin first. Lead with drawing and annealing so the conductor is right before stranding, then set lay, then re-cut extrusion against the live wall reading. Fuse inspection continuously. Hold the line-speed ramp for a human.
The standing recipe raises line speed and screw speed together. On the twin that produces a wall dip at zone 3 because the melt pressure lags the speed step. Sequencing the zone 3 temperature move ahead of the speed ramp removes it.
twin.simulate(candidates=36) returns recipe #22: zone 3 up 4 °C before the ramp, screw speed trimmed to the live wall reading, lay 28 mm.
Recipe #22 predicts wall variance 0.018 mm, spark risk 0.04 and give-away 2.1%. Three candidates scored lower on give-away but pushed predicted minimum wall under the spec floor and were discarded.
Execute recipe #22 under autonomy level L3: eight setpoint writes permitted, the line-speed ramp routed to the shift process engineer.
Neckdown precursor at 12,480 m at 06:39:04. A 1.5% screw-speed trim cleared it in 16 s with no reel quarantined.
Scenario complete. Wall 0.80 mm nominal, minimum 0.66 mm, concentricity 0.93, zero spark faults. Reel R-30417 released with full genealogy.
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.
Yield-and-Takt wants to trim screw speed to reduce polymer give-away on the thick side of the wall.
Defect-and-Inspect wants to raise screw speed to clear a neckdown precursor at 12,480 m.
Neckdown risk 0.58 outranks 0.3% give-away under the run goal "zero spark faults". Defect-and-Inspect wins the actuator for 120 s.
Actuator returned. Yield-and-Takt recovers give-away through the cooling trough instead. Wall holds at 0.80 mm nominal.
Illustrative scenario.
A plant does not go from manual to unattended in one step. Draweon makes the level explicit, auditable and reversible at any time. The first release runs shadow mode, then assist mode, then graduated autonomy.
| Level | What the agent does | What the human does | Where it sits in a pilot |
|---|---|---|---|
| L1 · Advisory | Recommends setpoints and explains why, with citations | Enters every change manually | Shadow mode, weeks 1 to 3 |
| L2 · Supervised | Proposes a write; it executes on approval | Approves each write in the review console | Assist mode, weeks 4 to 8 |
| L3 · Bounded | Writes inside tag, rate and magnitude limits | Approves ramps, die changes and reel release | Graduated autonomy, from week 9 if the plant is satisfied |
| L4 · Unattended | Runs the envelope without prompting | Sets the envelope; reviews the shift record | Planned; after qualification on the construction |
Conductor moves at over a thousand metres a minute. Perception has to be local, deterministic and fast, so Draweon runs GPU inference at the plant edge and keeps training, simulation and optimisation in the cloud or on-prem.
4 to 12 cameras per line plus laser, eddy-current and spark streams fused at the line. Sub-50 ms alerting and sub-250 ms bounded control are the design targets. Jetson Thor is planned for higher sensor density.
Vision, time-series, anomaly and quality models behind one orchestrator at the plant edge, with canary rollout by line and fallback to the previous validated version.
Defect classifiers, sensor-fusion models, time-series prognostics and cable-process reasoning models trained on reel telemetry and engineer corrections. Dedicated training capacity is planned.
As-run drawing, stranding, extrusion, thermal and tension simulation. Physics-informed surrogates are planned so recipes can be optimised at production cadence.
Rare spark, pinhole, eccentricity, neckdown and break variants generated and validated against real gauge, spark and vision distributions before promotion. Planned.
Line sequencing, reel changeovers, energy allocation, takt and constrained setpoint proposals.
Spool, reel and payoff and take-up motion planned and validated in simulation before it runs next to moving conductor.
Draweon reads and writes through the systems already on the floor. No rip and replace, no parallel historian, no new HMI to learn. Vendor names are examples of systems found on cable lines; connector availability is confirmed per site.
PLC and SCADA on drawing, stranding and extrusion lines (Siemens, Rockwell and OEM controllers)
Setpoint reads and guarded writes
Laser gauges and X-ray wall scanners (Sikora, Zumbach, Beta LaserMike and NDC class systems)
Wall, diameter, eccentricity traces
Eddy-current heads and spark testers
Fault events with length position
Line-scan and area cameras on the line
Frames for lumps, neckdowns, surface faults
Rod breakdown, intermediate and fine drawing, annealers (Niehoff and Properzi class lines)
Tension, die force, annealer current, conductivity
Bunchers, planetary, rigid and tubular stranders (Gauder, Pourtier, Nextrom class lines)
Payoff tension, take-up, lay, geometry
Insulation and jacket lines (Maillefer, Rosendahl Nextrom, Troester, Davis-Standard class lines)
Screw, zones, melt pressure, cooling
Cable MES, quality systems and in-house records
Orders, constructions, reel genealogy
Draweon 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 plant owns.
| Item | Scope | Status |
|---|---|---|
| SOC 2 Type I | Cloud control plane | QUEUED Planned, first 6 months |
| SOC 2 Type II | Cloud control plane | QUEUED Planned, 6 to 12 months |
| SSO and RBAC | Console and approvals | QUEUED Planned, 6 to 12 months |
| Standards-cited reasoning | UL, IEC, IPC, USCAR documents | RUNNING In the design, every answer cites its source |
| Per-tenant isolation | Recipes, models, memory | RUNNING In the design from day one |
| On-prem and plant-edge deployment | Sensitive producers | RUNNING Design option |
The questions plant directors and process engineers 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 plant has set. Level 1 is advisory: Draweon recommends and a human enters everything. Design partners start there, in shadow mode, before supervised writes.
Control returns to the line controller's last known-good state. Draweon is a supervisory layer on top of the PLCs and gauges you already run, never a replacement for them, so an outage degrades the line to its current way of running, not to a stop.
Advisory recommendations start from the physics-based twin and the construction spec in the first weeks. Defect prediction and break prediction improve as line history and labelled events accumulate per construction. The first training sets are sized at 5 to 20 million labelled frames and events, a design target.
Only if you choose cloud training. Recipes, process models and defect libraries are isolated per tenant and never used to train another customer's models. A fully on-prem deployment at the plant 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 paid pilot on one line, scoped to a single workflow with a baseline agreed in writing. Weeks 1 to 3 are connection and shadow-mode observation, weeks 4 to 8 are assist mode with engineer approval, and bounded autonomy follows if the plant is satisfied with the recommendations.
Start with one drawing, stranding or extrusion line and one measurable baseline. A paid pilot on wall and concentricity, break prediction or spark prediction shows the number before you commit further.
↑↓ navigate↵ openesc close
