Why isothermal extrusion is a taper problem
Holding exit temperature flat across a push is mostly about setting the billet gradient correctly before the ram moves. We look at why fixed tapers fail and what per-billet control changes.
Blog
Notes fromthe plant floor.
What we are learning building perception, control and simulation for extrusion — written for press engineers, die designers and the software people who work with them.
Latest
Recent posts.
Attributing die lines to dies, not shifts
Surface defects cluster by die far more than by shift or operator. Attribution at the press exit turns a diffuse quality complaint into a short, actionable list.
Predicting T6 before the oven runs
Quench rate and aging recipe determine temper, but confirmation arrives days later in the lab. What it takes to predict mechanical properties per rack at the stretcher.
What a recovery point is actually worth
Press recovery is the most quoted and least consistently defined number in extrusion. We work through the arithmetic and the three definitions plants use.
The latency budget of one push
From frame to setpoint inside a moving ram: where the milliseconds go across capture, inference, arbitration, envelope check and write.
A twin you can actually trust before a push
Physics-informed models calibrated against measured outcomes, and the validation gate that decides whether a sweep is allowed to influence a real die correction.
Deep dives
Longer pieces.
The black art, formalised
A four-part series taking the coupled thermomechanics of extrusion — taper, speed, container and die temperature, exit temperature — and expressing it as a control problem with measurable state.
Earning write access
How a model goes from shadow prediction to moving a real ram: the accuracy gates, the approval-rate signal, twin validation and the envelope review that makes it safe.
What we learned installing sensing on ten presses
Mounting positions, vibration, heat, cable runs and the unglamorous realities of getting line-scan cameras to survive on a runout table.
The baseline conversation
Why the hardest week of a pilot is week zero, and how three definitions of recovery inside one company nearly killed a deployment.
The subject
Everything we writeis about this.
One billet, one die, one profile, one set of coupled decisions. Every post is a slice of the same problem.
Written by the engineers building it, not by a content team.
The loop we write about
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.
Topics
What wecover.
Press control
Ram speed, breakthrough pressure, container and die temperature, isothermal extrusion.
Profile quality
Dimensions, wall thickness, straightness, twist and bow, surface defect taxonomy.
Die & flow
Flow balance, die correction, trials, die life and port-weld quality on hollows.
Temper & aging
Quench rate, stretch, T5/T6 development, flatness and mechanical property prediction.
Recovery & energy
Butt loss, offcut nesting, kWh per tonne, decarbonisation pressure on extruders.
Edge AI
Sensor fusion, TensorRT pipelines, Triton serving, latency budgets at the press.
Simulation
Twin calibration, synthetic rare faults, validation gates, sweeps before the push.
Autonomy & safety
Envelopes, interlocks, approval workflows, audit trails and graduated control.
Subscribe
One emailwhen something is worth reading.
No cadence commitment, no newsletter theatre. We write when we have learned something on a press that another extruder would want to know.
- Engineering and metallurgy depth, not product announcements.
- Written by the people doing the work.
- Unsubscribe in one click, obviously.
- Field notes
What actually happened when we installed sensing on a live runout. - Benchmarks
Anonymised recovery, reject and die-trial distributions as the fleet grows. [ASPIRATIONAL] - Method posts
How a control policy is validated before it touches a press.
Measured on the press
The numberswe write about.
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.]
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.
Blog
Prefer a conversationto a blog post?
Bring us a hard push — a profile that twists, a die that will not settle, a recovery number that will not move — and we will dig into it with you.
Land on one press. Expand press by press, module by module, site by site.