Blog

Rolling stock and autonomy, written plainly.

Short pieces from the Railira team on carbody welding, bogies, livery, the train twin, takt and what it takes to let software recommend a weld sequence in a rolling-stock plant. 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 Railira

4 postsRailira team2026-10-09

Latest

A stopped line rents by the minute

A rolling-stock plant is a chain of tightly coupled, safety-critical steps, and the line that joins them costs tens of thousands of dollars a minute when it stops.

2026-10-09 · 5 min read

2026-10-09 · 5 min read · Railira team

A stopped line rents by the minute

A rolling-stock plant is a chain of tightly coupled, safety-critical steps, and the line that joins them costs tens of thousands of dollars a minute when it stops.

A locomotive, high-speed trainset, metro car, passenger coach or freight wagon has to hold EN 15085 weld quality, millimetre carbody geometry, bogie torque and press-fit tolerances, wiring continuity, brake performance, signaling readiness, ride quality, coating durability and IRIS traceability, all while staying on delivery cadence. One fixture drift, cold weld, out-of-tolerance bogie interface, coating contamination event, missing harness, torque escape or late commissioning fault can cascade into rework, a stopped line, delayed acceptance, warranty exposure or recall risk.

Plants still rely on periodic audits, offline metrology, sampled inspection and tribal line-side knowledge, even as fleet renewal, electrification and transit expansion compress launch timelines and multiply variants. The tools exist: robotic welding and coating, in-line metrology, vision, torque telemetry, plant simulation. Each owns a slice. None closes the loop from sensing a problem to acting on it before the schedule slips.

The insight behind Railira is that carbody fabrication, bogie assembly, coating, fit-out, marriage and sequencing are not separate problems. They are one coupled chain, and the chain is what has to be controlled. Railira fuses the signals, predicts the defect and the takt loss, and acts, before the shift where it can and inside approved limits where it cannot.

2026-10-09 · 4 min read · Railira team

Autonomy is a dial, not a switch

A rolling-stock plant does not go from manual to unattended in one step, and a weld procedure should not be the first thing an agent changes.

Design partners start in shadow mode. Railira connects read-only to weld, metrology, torque, coating, wiring, test, robot and MES signals, measures the baseline for rework, line uptime and first-time-through from the plant's own records, and writes nothing. In assist mode it recommends weld-sequence, geometry, coating, torque and sequencing moves, each with source evidence, confidence, the control-plan envelope and a rollback path, and an engineer approves each one.

Bounded autonomy follows for the low-risk actions: inspection routing, rework priority, kit feeding, robot path variants and parameter adjustments inside approved bounds. Weld-parameter adaptation comes last, supervised, inside pre-approved control-plan envelopes, after audited ROI, golden-dataset evaluation, simulation validation and quality sign-off, and only once IRIS, plant and OEM acceptance has been earned.

Every action carries its evidence, envelope, confidence, estimated quality and takt impact, rollback path and audit entry. That format is what makes autonomy acceptable to plant, quality and OT teams, and it is what makes trust possible before autonomy.

2026-10-09 · 4 min read · Railira team

Hit quality and takt before the shift

Plants commit a shell, a bogie and a booth to a car before they know the geometry will fit or the cure window will hold. The twin changes the order.

Whether a car fits, passes brake test, holds its livery and leaves on its slot depends on a coupled chain of weld sequence, fixture state, geometry build-up, coating environment, bogie readiness and line sequence. Today that chain is tuned by offline distortion studies, line-sequencing studies and the craft of a shrinking workforce.

Fitura hosts an as-built train-and-plant twin. It consumes shell geometry from Carbra, running-gear data from Bogira and coating state from Coatyx, simulates weld distortion, geometry build-up, coating coverage, marriage fit, commissioning readiness and line flow, and ranks candidate weld sequences, geometry strategies and build orders before the shift. Taktos then sequences the plant against that readiness, and every real outcome recalibrates the twin.

Carbody weld-distortion and geometry FEA, structural simulation and point-cloud metrology are compute-heavy workloads. Running them fast enough to inform a decision before the shift is the reason the twin is built on GPUs.

2026-10-09 · 3 min read · Railira team

The craft is retiring faster than plants can hire

The operators, body engineers and quality engineers who hold rail vehicles to spec are leaving, right as the launch cadence multiplies variants.

Ask a plant director and the same losses come up: weld rework in the body shop, geometry escapes found at fit-out, repaints after a coating fault, torque escapes caught at brake test or in service, and a sequence that breaks when one bogie is late. The craft that prevents these lives in a handful of people who can read a seam, a trace or a booth, and they are retiring by the year.

Railira captures that craft as a model: the full chain of weld parameters, fixture state, geometry, coating conditions, torque traces, fit, test results and disposition, per car. Every supervised correction trains the system. The plant runs at expert judgment on every shift, and the record of how is written down and tied to the car's genealogy.

Run timeline · scenario

The scenario the posts refer to

Every Railira run is an ordered, inspectable sequence. This is run_9b4e27: Car 07 of a 4-car metro consist · shell line B · bogie shop · booth 2 · marriage station. Scenario completes in 10 steps with one approval gate. Shell geometry held inside tolerance after a twin-ranked weld sequence, one heat-input change approved by the shift weld engineer, two torque traces routed to rework before brake test, the livery cure window protected in the sequence, marriage interface inside tolerance, car released with full genealogy.

run_9b4e27 car 07 · 4-car metro consist illustrative scenario SUCCEEDED
  1. 01 ingest.order SUCCEEDED 0.8 s

    Plant Orchestrator · Pulled the work packages for car 07 from MES and PLM: aluminium extrusion shell, EN 15085 weld class per joint, control-plan geometry tolerances, bogie torque specifications, livery recipe and cure window, fit-out and marriage sequence. Locked the approved control-plan envelope for the shift.

  2. 02 takt.sequence SUCCEEDED 41 s

    Line-and-Logistics · Sequenced the shift against live readiness: booth 2 cure window, bogie B-14 readiness, brake-test slot at 13:40, AMR fleet state and kit inventory. The plan moves car 07 marriage behind car 06 to keep the cure window and the test slot.

  3. 03 twin.simulate SUCCEEDED 58 s

    Train Twin · Simulated 18 candidate weld sequences for the roof-to-sidewall joints on the as-built twin and ranked them on predicted distortion, door-aperture geometry and heat input. Sequence #6 keeps the aperture inside tolerance with 2% less heat input than the standing sequence.

  4. 04 weld.sequence SUCCEEDED 3 m 12 s

    Weld-and-Structure · Recommended sequence #6 and the matching clamping plan to the shell line. Seam vision and laser-tracker geometry confirmed the roof-to-sidewall joints inside the control-plan tolerance on the first four seams.

  5. 05 approve.human APPROVAL 52 s

    Plant Orchestrator · Sequence #6 lowers heat input on the roof joints 2% below the standing weld procedure. Heat-input changes stay with a named engineer, so the step was held for the shift weld engineer and approved at 06:12:44 with the twin evidence attached.

  6. 06 bogie.torque SUCCEEDED continuous

    Bogie-and-Running-Gear · Press-fit curves and torque traces on bogie B-14 read at the station. Two traction-motor mounting traces fell outside the expected profile and were routed to rework before brake test; the remaining safety-critical joints verified to spec.

  7. 07 coat.cure SUCCEEDED continuous

    Coat-and-Livery · Booth 2 humidity and temperature, film thickness and flash time watched through the livery pass. One masking misalignment on the door band flagged by booth vision before the second coat; the cure window held and handed to the sequence as a hard constraint.

  8. 08 marry.align SUCCEEDED 2 m 05 s

    Marry-and-Couple · Carbody and bogie scans compared against target interface geometry before the lift. Fit-out readiness confirmed by Fitout-and-Interior for doors and glazing. Marriage guided inside tolerance; coupler and gangway checks verified and written to the twin.

  9. 09 inspect.fuse SUCCEEDED continuous

    Quality-and-Anomaly · Weld and coating vision, in-line metrology, torque, wiring continuity and brake-test results fused at the edge across the car. Every finding localised to station, work package and shift, with the two torque reworks and the masking flag already closed.

  10. 10 car.release SUCCEEDED 1 m 30 s

    Conformance · Car 07 released: genealogy written (weld records per joint, geometry scans, torque traces, coating recipe and cure record, fit-out checks, marriage interface, approvals, test results) and dispositioned against the control plan and IRIS / ISO/TS 22163 criteria with cited evidence for the quality engineer's sign-off.

Autonomy

Four levels, set per agent and per tool

A rolling-stock plant does not go from manual to unattended in one step. Railira makes the level explicit, auditable and reversible at any time. The first release runs shadow mode, then assist mode, then bounded autonomy on low-risk actions. Weld parameters, schedule release and car release stay with named humans until acceptance is earned.

Autonomy levels and the human role at each
LevelWhat the agent doesWhat the human doesWhere it sits in a pilot
L1 · ShadowReads weld, metrology, torque, coating, wiring, test, robot and MES signals; predicts and recommends; writes nothingRuns the line as today; compares predictions to inspection and engineer outcomesShadow mode; baseline measured from the plant's own records
L2 · AssistProposes weld-sequence, geometry, coating, torque and sequencing moves with evidence, confidence, envelope and rollback pathApproves each move in the review consoleAssist mode; accuracy and ROI proven against the baseline
L3 · BoundedExecutes pre-approved low-risk actions: inspection routing, rework priority, kit feeding, robot path variants and parameter adjustments inside approved boundsApproves heat-input and weld-sequence changes, schedule release and car releaseGraduated autonomy, after audited accuracy and ROI and safety gates
L4 · ScaledSupervised weld-parameter adaptation inside pre-approved control-plan envelopes, across lines and plantsSets the envelope; reviews the shift record and the evaluation resultsPlanned; after IRIS, plant and OEM acceptance is earned
Accelerated computing

Physical AI, at the station

A seam is welded in seconds and a booth cannot wait for the cloud. Perception has to be local, deterministic and fast, so Railira runs GPU inference at the plant edge and keeps training, simulation and optimisation in the cloud or on-prem.

Jetson Orin · DeepStream · Holoscan · TensorRT

Edge perception

8 to 32 cameras per process area plus metrology, torque, thermal, robot and booth-instrument streams fused at the plant edge. Sub-50 ms weld and seam alerts and sub-150 ms coating and metrology prompts are the design targets. Jetson Thor is planned for higher sensor density.

Triton · NIM

Model serving

Weld-defect, geometry-risk, coating-risk, point-cloud and takt-risk models served at the plant edge with per-model versioning and rollback, routed by latency, tenant, sensitivity and cost.

DGX or HGX · NeMo

Training

Weld and coating defect vision, metrology classification, control-plan reasoning and FEA-surrogate models fine-tuned on plant data and engineer corrections. 100 to 500 GPU-hours per plant during onboarding is the design target; dedicated capacity is planned.

Omniverse · OVX

Train-and-plant twin

As-built carbody, coating, marriage and line-flow twin. Weld distortion, geometry build-up, robot reach, coating coverage and layout simulated before the shift. GPU FEA and point-cloud metrology are the workloads; OVX scale is planned.

Cosmos · Omniverse Replicator

Synthetic data

Rare weld defects, coating contamination, geometry deviations, occluded seams and torque-escape cases generated and validated against real inspection distributions before promotion. Planned.

cuOpt

Optimisation

Line sequencing, JIS feeding, AMR and AGV routing, buffer management and commissioning-slot scheduling against live readiness.

Isaac · Isaac ROS

Robot cells

Robotic weld, coating and assembly cells and AMR or AGV flow; path variants validated in simulation before release to the floor.

RAPIDS

GPU ETL

Telemetry features from weld parameters, metrology, coating readings, torque, non-conformance and takt history for retraining, drift detection and network analytics.

Who it is for

Built for the people who run the plant

We have no customer quotes to show yet and will not invent any. These are the three roles in a rolling-stock plant we build for, and the problems they bring to the first meeting.

Plant or Manufacturing Director

Owns launch dates, takt, line uptime, rework and cost.

What this person is dealing with today

  • Periodic audits, offline metrology and sampled inspection that let geometry, weld, coating and torque quality drift
  • Line stoppages and takt loss cascading across the build schedule
  • A severe skilled-operator and quality-engineer shortage that cannot staff the launch cadence

Body, Livery or Manufacturing-Engineering Lead

Owns joining and coating processes, carbody geometry strategy, robot programming and process capability.

What this person is dealing with today

  • Carbody shell distortion and fixture drift driving weld-defect scrap and downstream geometry problems
  • Geometry build-up and alignment error costing rework, door and glazing leaks and ride quality
  • Coating contamination, runs and film-thickness faults driving repaint and class-A livery rejects

Quality, STA or Compliance Lead

Owns weld, coating, geometry and torque quality, non-conformance, PPAP, and IRIS / ISO/TS 22163 and TSI, AAR, APTA traceability.

What this person is dealing with today

  • Marriage and coupling misalignment and torque escapes creating safety-critical rework and recall risk
  • Traceability for IRIS and PPAP audits assembled by hand after the fact
  • Carbody fabrication, bogie assembly, coating, fit-out and systems integration siloed and reactive
FAQ

Straight answers

The questions plant directors, body and coating engineers and quality leads ask in the first meeting.

Only within an explicit tool allow-list with per-tool rate and magnitude limits, inside the approved control-plan envelope, and only at the autonomy level your plant has set. Design partners start in shadow mode, where Railira writes nothing. Heat-input and weld-sequence changes, schedule release and car release stay with a named approver.

Get started

Talk to the people who wrote this

Start with one carbody, bogie, coating, fit-out or sequencing process and one measurable baseline. A paid pilot on weld and geometry, torque assurance, livery defects or line sequencing shows the number before you commit further.

Book a line review See pricing