Billet heating & taper
Autonomous taper control front-to-back so exit temperature stays flat across the push instead of drifting with the billet.
Solutions
Start where it hurts.Expand where it pays.
Extruon lands on one high-pain workflow with measurable press-recovery, scrap or energy ROI, then expands press by press, module by module, site by site. Here is the map of where extruders start.
By workflow
Nine places Extruontakes work off the plant.
Each is a standalone wedge with its own baseline and its own ROI metric. Most extruders start with one and add the second within two quarters.
Press speed & pressure
Adaptive ram speed, breakthrough pressure and container and die temperature to hold isothermal extrusion at maximum safe speed.
Profile dimensions
Continuous wall thickness, width, straightness and twist sensing at the press exit — not spot checks between pushes.
Surface defects
Die lines, pickup, scoring and blisters classified at line speed, tied back to the die and the push that caused them.
Die trials & flow
Die temperature, correction and flow balance optimised in the twin so new dies need fewer proving pushes.
Quench & stretch
Press-quench cooling rate and stretch-straightening controlled for temper and flatness on the first pass.
Cut & age
Cut-to-length nesting, batching and aging-oven recipes tuned to reach T5 and T6 without over-soaking.
Robotic handling
Robotic pulling, stacking, racking and packing of long, hot, delicate profiles — the shifts nobody wants to staff.
Recovery & energy
Press recovery, butt and offcut loss, throughput and kWh per tonne optimised across the whole line at once.
By segment
The same loop,different tolerances.
Alloys, profiles, tempers and tolerances differ by end market. The autonomy loop does not.
Windows, curtain wall, façade systems
High-volume 6063 architectural families where surface quality drives anodising and powder-coat acceptance, and die lines are the dominant reject.
- Surface-defect sensing tuned for anodising-grade finish
- Straightness and twist control ahead of the stretcher
- Die-family learning across repeat architectural profiles
- Recovery uplift on long, thin-wall sections
Battery enclosures and crash structures
Safety-critical structural profiles where temper and dimensional traceability per rack are contractual, not optional.
- T6 temper prediction and quench control per rack
- Dimensional traceability against EN 755 and ASTM B221
- Multi-void hollow flow balance and port-weld quality
- Immutable audit trail for OEM quality audits
Module frames and mounting systems
Cost-per-metre businesses where recovery, butt loss and energy per tonne decide whether the contract is profitable.
- Recovery and butt-loss optimisation on repeat profiles
- Energy-window scheduling for heating and aging
- Throughput lift at constant reject rate
- Fast changeover between near-identical dies
Heat sinks, tube, and general engineering
High-difficulty thin-fin and multi-void profiles where the die is the constraint and trials burn the schedule.
- Die-trial reduction on complex fin geometries
- Flow-imbalance detection before twist becomes scrap
- Exit-temperature control on speed-limited sections
- Twin sweeps before committing press time
Profile, tube and co-extrusion lines
The same closed loop applied to melt temperature, screw speed, die pressure, haul-off and cooling. [ASPIRATIONAL — roadmap expansion]
- Melt temperature and screw-speed control
- Dimensional and surface sensing on the haul-off
- Cooling-tank and calibration control
- Scrap and start-up-waste reduction
Wherever you start
One push proves it.One press pays for it.
The wedge is whichever workflow has the biggest gap between what your best operator achieves and what your average shift achieves. Extruon closes that gap first.
The wedge workflow is chosen during the plant assessment, from your own baseline data.
The loop, per workflow
Perceive. Plan. Push.Prove. Learn.
One closed loop runs at the plant edge on every billet. Nothing is advisory-only unless you want it to be — and nothing acts outside an envelope your engineers signed.
01Perceive
Sense the billet, the profile, the temper
Fused line-scan and RGB vision, thermal imaging, laser gauging and press PLC telemetry describe the push as it happens — dimensions, wall thickness, straightness, surface, exit temperature.
02Plan
Set the taper, the speed, the die, the quench
The agents plan billet-heating taper, ram speed, pressure and temperature, die-flow correction, quench rate, stretch, cut length and aging recipe as one coupled decision, not five isolated setpoints.
03Act
Run with adaptive control at the press
Approved moves write back into the press PLC, the furnace and the quench inside bounded action envelopes, with rollback and alarm interlocks wired to the same fail-safe stop your line already trusts.
04Prove
Predict defects and recovery before they cost metal
The loop predicts off-spec dimensions, surface defects, twist and temper misses, and flags die-trial risk early enough to change the push instead of scrapping it.
05Learn
Every correction trains the plant
Engineer approvals and corrections are logged to an immutable, assurance-grade audit trail and fed back into training — so the site's craft compounds instead of retiring.
Measured on the press
The ROI metricis picked before we start.
Every Extruon engagement starts with a baseline and ends with an audited delta. These are the target bands we underwrite in a paid pilot.
+4.2 pts
Press recovery uplift, saleable vs charged metal
−38%
Surface-defect and dimensional rejects
−61%
Die-trial pushes before a die is signed off
−12%
kWh per tonne across heating, quench and aging
Target outcome bands modelled from design-partner baselines. [ASPIRATIONAL — to be replaced with audited pilot results.]
Pain → outcome
What each stakeholderstops fighting.
Profiles that miss tight tolerances
Continuous wall, width, straightness and twist sensing with adaptive press control, instead of spot gauging and after-the-fact stretching.
Die lines, pickup, scoring, blisters
Classification at line speed tied back to die and push, so the cause is corrected rather than the symptom sorted at packing.
Slow, expensive proving pushes
Twin-side flow balancing and correction so dies arrive at the press closer to right, burning less metal and less press time.
Butt and offcut scrap, speed limits
Whole-line recovery optimisation that treats butt length, cut nesting and press speed as one decision.
T5/T6 and flatness failures
Quench-rate and aging control tied to predicted mechanical properties, with per-rack traceability.
The retiring press operator
The craft is captured as supervised corrections and encoded into models that keep running on the night shift.
Seven agents, one orchestrator
The plant runs as a crewof specialised agents.
Each agent owns a physical stage of the line, senses it directly, and acts inside an approved envelope. A plant orchestrator arbitrates between them so nobody optimises recovery at the expense of temper.
Heat-and-press agent
Controls billet temperature taper, ram speed, breakthrough pressure, container and die temperature, and exit temperature to keep metal flow balanced and the profile on dimension.
Profile-and-defect agent
Senses and predicts cross-section dimensions, wall thickness, straightness and surface defects — die lines, pickup, scoring, blisters — from fused vision and laser gauge.
Die-and-flow agent
Optimises die temperature, correction and flow balance to cut die trials and the twist and bow that send profiles back to the stretcher.
Quench-and-stretch agent
Controls press-quench cooling rate and stretch-straightening so temper and flatness land inside spec on the first pass.
Cut-and-age agent
Controls cut-to-length, batching and aging ovens to reach T5 and T6 mechanical properties without over-soaking the oven.
Robot-and-handling agent
Drives robotic pulling, stacking, racking and packing of long, hot, delicate profiles — the handling nobody wants to staff at 3am.
Yield-and-throughput agent
Optimises press recovery, scrap, butt and offcut loss, and energy per tonne across the whole line rather than one station at a time.
Extrusion-knowledge agent
Answers metallurgy and die-design questions with citations into your die books, profile drawings, press recipes and alloy specs.
Press-and-die digital twin
Simulates billet heating, metal flow through the die, quench and profile properties — hitting the target profile and yield before the push, not after the scrap.
Assurance-grade by default
Trust is the gateto autonomy.
Extruon never asks for control it has not earned. Shadow mode proves accuracy against your operators and gauges; advisory mode proves ROI; bounded autonomy only follows once the gates are met.
Per-tenant everything
Data, models, retrieval indexes and memory are scoped per tenant and per entity. On-prem deployment is available for sensitive producers.
Your die geometry stays yours
Die designs, customer drawings and recipes never leave your boundary. Fleet learning shares defect signatures and process priors, never geometry.
Immutable action log
Every perception, recommendation, approval and setpoint write is recorded with its evidence, ready for quality and customer audits.
SSO, RBAC, encryption
SSO and role-based access, encryption in transit and at rest, SOC 2 programme in progress, and fail-safe interlocks on every write path.
Before you choose
Questions extruders askwhen picking a wedge.
The one with the largest measurable gap and the cleanest data. In practice that is usually press-speed and exit-temperature control, or profile-dimension and surface-defect sensing. The plant assessment picks it from your own baseline, not from a template.
No, but it shortens the path. Where gauging exists we integrate it; where it does not we deploy press-exit vision, thermal and laser sensing as part of the wedge.
Yes. The Press tier covers press and heating control or profile and defect sensing for a single extrusion press. Expansion is a decision you make after the pilot, not before.
Age matters less than access. If the press PLC exposes ram speed, pressure and position over OPC UA or Modbus and the furnace exposes zone setpoints, the loop can close. Where it cannot, we run advisory until the interface exists.
Full multi-module autonomy across the entire plant, long-tail integrations beyond design-partner stacks, and self-serve enterprise onboarding. The first release is deliberately narrow and deep.
The finale
Find your wedgein one assessment.
We baseline recovery, scrap, die trials and energy across your presses, then propose the single workflow with the fastest payback.
Land on one press. Expand press by press, module by module, site by site.