Blog

Additive and autonomy, written plainly.

Short pieces from the Powdrix team on melt pools, qualification, build simulation and what it takes to let software trim a laser. Four so far. Each one is drawn from the thinking in our own planning documents, not from customer work, because there is none yet.

Read the latest About Powdrix

4 postsPowdrix team2026-10-08

Latest

The parts changed. The floor did not.

Additive used to mean prototypes. Now it means implants and flight hardware. The floor still runs on fixed parameters, spot CT and craft.

2026-10-08 · 5 min read

2026-10-08 · 5 min read · Powdrix team

The parts changed. The floor did not.

Additive used to mean prototypes. Now it means implants and flight hardware. The floor still runs on fixed parameters, spot CT and craft.

Aerospace brackets and fuel nozzles, spinal and hip implants, tooling, energy and defence parts are now printed layer by layer from metal powder and qualified to fly, to be implanted, to hold pressure. The parts changed. Running the floor that makes them is still one of the most craft-bound, failure-prone processes in advanced manufacturing.

The failure modes are unforgiving. A wrong orientation or parameter set, a melt pool that goes unstable at layer 2,000, a recoat streak, a thermal excursion that pulls a part out of geometry, or a pore too small to see: any one turns into a scrapped multi-hour build, a failed qualification or a part that fails in the field. In-situ sensors already produce terabytes of melt-pool video, layer images and thermal data per build, and almost none of it is interpreted in real time.

The insight behind Powdrix is that build prep, printing, in-situ monitoring, post-processing and inspection are not separate problems. They are one loop that no one closes. Powdrix links the recipe to the in-situ signal to the CT result to the disposition, and acts on it.

2026-10-08 · 4 min read · Powdrix team

Autonomy is a dial, not a switch

A qualified floor does not go from manual to unattended in one step. The level has to be explicit, auditable and reversible.

Design partners start in shadow mode. Powdrix connects to the existing melt-pool cameras and CT on one machine, watches, and measures the baseline for build failure, yield and qualification cost. Nothing is written. In assist mode it predicts porosity, distortion and failure and recommends parameter, orientation or thermal moves, and an engineer approves each one against real CT outcomes. Graduated autonomy follows for low-risk loops, inside the OEM-approved parameter envelope, with exceptions escalated.

Human approval stays mandatory for anything that affects qualification until validation exists. Every agent action carries its model version, data lineage, source signals, predicted impact, allowed range, approval status and qualification impact. That is what makes the system legible to operations, quality and certification engineers, and it is what makes trust possible before autonomy.

2026-10-08 · 4 min read · Powdrix team

Hit density before the build

Build success is decided before the first layer. The twin changes when that decision gets tested.

Orientation, supports, nesting and the parameter recipe decide whether a build hits density, geometry and takt. Today that is found out on the machine, through scrapped builds and coupon campaigns, by engineers who cannot explore the design space fast enough to scale the fleet.

Parttwin simulates the build first: thermal fields, a melt-pool proxy, residual stress and distortion for each candidate recipe, ranked against the targets and stress-tested against rare defect scenarios. The winner is released to the printer inside the qualified envelope, and when the CT result comes back the twin calibrates against it.

Thermal and distortion simulation and thousand-scenario sweeps are massively parallel workloads. Running them at production cadence is the reason the twin is built on GPUs.

2026-10-08 · 3 min read · Powdrix team

The engineer who could not be everywhere

A floor full of expensive printers, pouring out data, paced by a handful of people who can read it.

Talk to any AM production team and the stories rhyme: a multi-hour build lost to a recoat fault no one caught, a qualification campaign stalled by manual CT review, a part that passed inspection and still failed because the pore was too small to see, a retiring engineer whose parameter intuition walked out of the door.

Powdrix encodes that intuition as a model: the full sequence of recipe, in-situ signal, approved action and inspection outcome, per build. Every supervised correction trains the system. The floor runs at expert attention on every machine, and the record of how is written down.

Run timeline · scenario

The scenario the posts refer to

Every Powdrix run is an ordered, inspectable sequence. This is run_7c2e4b on PBF-2 · Ti-6Al-4V bracket family, 24-part build. Scenario completes in 10 steps with one approval gate. Twin recipe #14 selected, one lack-of-fusion precursor at layer 1,872 cleared by a bounded power trim, CT triage in 11 minutes, 23 of 24 parts released with full genealogy and one held for review.

run_7c2e4b PBF-2 · Ti-6Al-4V bracket family, 24-part build illustrative scenario SUCCEEDED
  1. 01 ingest.job SUCCEEDED 0.7 s

    Floor Orchestrator · Pulled the job from AM MES: 24 Ti-6Al-4V brackets, 60 µm layers, 3,140 layers, density target 99.7%, geometry tolerance ±0.10 mm, AS9100 evidence packet required. Locked the OEM-approved parameter envelope for PBF-2.

  2. 02 twin.simulate SUCCEEDED 6 m 12 s

    Part Twin · Simulated 40 candidate orientation, support and parameter recipes for thermal field, residual stress and distortion, ranked on predicted density, geometry deviation, takt and energy.

  3. 03 prep.release SUCCEEDED 48 s

    Prep-and-Parameter · Recipe #14 released: 32° orientation, lattice supports on two faces, laser power and speed inside the qualified envelope. Predicted distortion 0.06 mm, predicted density 99.8%.

  4. 04 recoat.check SUCCEEDED continuous

    Recoat-and-Powder · Recoater image checked every layer. Powder lot L-2291 on its third reuse, humidity in window. One short-feed at layer 412 corrected with a dosing increase before the next layer fused.

  5. 05 melt.stabilise SUCCEEDED continuous

    Melt-and-Layer · Melt-pool, photodiode and thermal streams fused at 120 fps. Lack-of-fusion risk rose to 0.61 on part 17 at layer 1,872 and was cleared by a 3% power trim inside the envelope within four layers.

  6. 06 thermal.compensate SUCCEEDED 2 m 04 s

    Thermal-and-Distortion · Interlayer temperature on the tall brackets ran 14 °C above the twin's prediction from layer 2,300. A 1.5 s interlayer dwell held the thermal field inside the predicted band through the top section.

  7. 07 approve.human APPROVAL 4 m 30 s

    Floor Orchestrator · Melt-and-Layer proposed a hatch-spacing change on part 17 beyond the qualified envelope. Held for the AM process engineer, who declined it and chose to flag part 17 for CT priority instead. Decision logged.

  8. 08 handle.depowder SUCCEEDED 38 m

    Robot-and-Handling · Plate unloaded by the handling cell on build complete, depowdered, and parts transferred to stress relief. Powder returned to the sieve with lot L-2291 reuse count incremented in genealogy.

  9. 09 inspect.ct SUCCEEDED 11 m

    Defect-and-Inspect · 24 CT volumes segmented for pores, cracks and lack of fusion in 11 minutes. 23 parts graded accept against the acceptance criteria. Part 17 shows a 180 µm indication at layer 1,870 and is routed to the inspector for disposition.

  10. 10 release.qualify SUCCEEDED 1 m 20 s

    Quality-and-Conformance · 23 parts released with the full genealogy: recipe, layer tags, melt-pool events, thermal trace, approvals, post-processing cycles and CT result. Part 17 held with a non-conformance opened. Evidence packet assembled for sign-off.

Autonomy

Four levels, set per agent and per machine

A qualified floor does not go from manual to unattended in one step. Powdrix makes the level explicit, auditable and reversible at any time, and human approval for anything that affects qualification stays mandatory until validation exists. The first release runs shadow mode, then assist mode, then graduated autonomy.

Autonomy levels and the human role at each
LevelWhat the agent doesWhat the human doesWhere it sits in a pilot
L1 · AdvisoryPredicts and recommends, with citations; nothing is writtenEnters every change manuallyShadow mode on one machine, first weeks of a pilot
L2 · SupervisedProposes a parameter, thermal or inspection move; it executes on approvalApproves each move in the review consoleAssist mode once accuracy is measured against CT
L3 · BoundedWrites inside the OEM-approved parameter envelope and per-tag limitsApproves anything that leaves the envelope or affects qualificationGraduated autonomy on low-risk loops, if the floor is satisfied
L4 · UnattendedRuns the envelope without promptingSets the envelope; reviews the shift recordPlanned; only after validation on the part family
Accelerated computing

Physical AI, at the melt pool

A build is thousands of layers and a day of machine time. Perception has to be local, deterministic and fast, CT has to be triaged in minutes, and the twin has to run before the build. Powdrix runs GPU inference at the printer edge and keeps training, simulation and optimisation in the cloud or on-prem.

Jetson Orin · DeepStream · Holoscan · TensorRT

Edge perception

One Jetson node per printer for 30 to 240 fps melt-pool, layer and recoater streams with photodiode and thermal fusion. Sub-250 ms alerting and 1 to 2 s bounded recommendations are the design targets. Jetson Thor is planned for multi-laser machines.

Triton · TensorRT · L4, L40S, A100

CT and vision inference

2D and 3D segmentation models for porosity, cracks, lack of fusion, surface defects and metrology comparison, served per inspection cell. Sub-15-minute CT triage per build is the design target.

DGX or HGX · NeMo

Training

Defect, melt-pool-instability, build-failure and AM reasoning models trained weekly over multimodal build data, with gated promotion from shadow to assist to bounded. Dedicated capacity is planned.

Omniverse · OVX

Part twin

Thermal, melt-pool-proxy, residual-stress and distortion simulation for recipe ranking, plus robot-cell and queue simulation. Modulus surrogates are planned so sweeps run at production cadence.

Cosmos · Omniverse Replicator

Synthetic data

Rare pore, lack-of-fusion, spatter, recoat-streak and distortion scenarios generated and validated against real CT and in-situ data before promotion. 1,000 to 10,000 per qualified part family is the initial target.

cuOpt · RAPIDS

Optimisation and analytics

Build nesting, fleet scheduling across machines, ovens, HIP, inspection and robots, energy windows, and GPU analytics over genealogy tables.

Isaac · Isaac Sim · NIM

Robot handling and serving

Plate, powder and part handling policies trained in simulation and run on Jetson in the cell. NIM packages perception, prediction and reasoning services behind the floor orchestrator.

Who it is for

Built for the people who run the floor

We have no customer quotes to show yet and will not invent any. These are the three roles on an additive floor we build for, and the problems they bring to the first meeting.

AM or Operations Director

Owns build throughput, quality, build-failure and yield, qualification and cost per part.

What this person is dealing with today

  • Fixed parameters and manual build prep that cap density, geometry and yield
  • Scrapped multi-hour or multi-day builds and high energy eroding cost per part
  • A severe, scarce AM process-engineer shortage that caps fleet scale-up

AM Process Engineer

Owns build prep, parameters, in-situ interpretation, thermal and distortion, and post-processing recipes.

What this person is dealing with today

  • Melt-pool instability, porosity, lack of fusion and spatter driving scrapped builds
  • Recoat streaks and powder-quality faults ruining long builds
  • Terabytes of in-situ data that nobody has time to read

Quality or Certification Engineer

Owns part quality to AS9100, ISO 13485 and ASTM and ISO AM standards, defect conformance and build genealogy.

What this person is dealing with today

  • Failed qualifications and evidence assembled by hand
  • Hidden pores and lack of fusion that pass spot CT and fail in the field
  • Build prep, in-situ, post-processing and inspection siloed and reactive across the fleet
FAQ

Straight answers

The questions operations directors, process engineers and certification engineers ask in the first meeting.

Only inside the OEM-approved parameter envelope, only on an explicit allow-list with per-tag limits, and only at the autonomy level your floor has set. Level 1 is advisory: Powdrix predicts and recommends and a human enters everything. Design partners start there, in shadow mode. Anything that leaves the envelope or affects qualification always waits for a named approver.

Get started

Talk to the people who wrote this

Start with one printer or one inspection cell and one measurable baseline. A paid pilot on melt-pool and build-failure prediction, CT porosity triage or pre-build recipe optimisation shows the number before you commit further.

Book a floor review See pricing