Typed, ordered, inspectable
A run is a goal, a plan and a graph of typed steps. Every step has an agent, a tool, a duration and a status, and the whole record is kept per block.
Hullira's features are the mechanics of a system that is allowed to touch production equipment: typed runs, a policy engine, named approvals, fused inspection, a twin, genealogy and an audit log. The list below is design scope, not a shipped feature list.
Illustrative scenario: Block B-214 · double-bottom block · panel line PL-2 · dock D1, one block, one approval gate
Each capability names what it does and where its limit sits.
A run is a goal, a plan and a graph of typed steps. Every step has an agent, a tool, a duration and a status, and the whole record is kept per block.
Tag allow-lists, per-tag rate and magnitude limits, the qualified WPS, coating, dimensional and schedule constraints, autonomy level, shift and interlock state are evaluated before any parameter moves.
Class-critical seam changes, lift plans, block release and class evidence wait for the approver the yard names. The request, the evidence and the decision are logged.
Weld-pool and seam frames, X-ray and UT files, point clouds and coating readings fused into one estimate of weld, dimensional and coating quality, localised to joint, area and block.
Candidate weld sequences, fairing moves, crane paths and erection orders ranked on distortion, fit, reach and takt before a parameter moves. Proven plans handed to the control agents.
Plates and heats, weld parameters per joint, scans, fairing moves, coating readings, approvals, NDT results and disposition, exportable for class and naval review.
Welding and accuracy-control engineers see recommendations with their evidence, approve or correct them, and those corrections train the models.
Every agent action with source evidence, the WPS, class or PSPC citation applied, confidence, predicted rework, dock-time and schedule impact, rollback path, approver and block scope.
Retrieval over WPS and PQR, ABS, DNV, LR and ClassNK rules, IMO PSPC, naval specs and the yard's procedures, tenant-isolated.
Per-yard weld-quality and accuracy history and per-welder and per-robot performance memory, versioned and scoped per tenant.
Rare weld defects, coating failures, distortion modes, occluded seams and misalignment cases generated to augment training and always validated against real NDT and scan distributions before promotion. Planned.
Model versions promoted by process area with canary rollout and automatic fallback; group policy with per-yard override on the Enterprise tier.
Every Hullira run is an ordered, inspectable sequence. This is run_4b7e19 on Block B-214 · double-bottom block · panel line PL-2 · dock D1. Scenario completes in 10 steps with one approval gate. Predicted distortion at the erection joint fell from 4.2 mm to 1.8 mm after a back-step sequence, one porosity precursor on seam S-31 was cleared inside the WPS envelope, the ballast-tank coat ran inside a 3.4 °C dew-point margin, and the block landed at 1.6 mm with its conformance record written.
Yard Orchestrator · Pulled the work package for B-214 from the yard MES: 46 plates, 212 seams under WPS-117, erection tolerance 2 mm at the D1 joint, PSPC-grade ballast-tank coating, erection slot on D1 in the dock plan. Locked the qualified WPS envelope and the class scope.
Ship Twin · Simulated 18 candidate weld sequences on the as-built twin with the weld-thermal surrogate, ranked on predicted distortion at the erection joint, crane reach on D1 and shift takt. Standing sequence predicts 4.2 mm; candidate #6 predicts 1.8 mm.
Cut-and-Profile · Released the nest for 46 plates on CL-1 with the fit-up gaps candidate #6 assumes. As-cut geometry logged per plate and handed to the panel line; material yield 91.4% against the nest plan.
Panel-and-Weld · Loaded the back-step sequence for the non-critical seams on PL-2 and set heat input and travel speed inside WPS-117. Weld-pool and seam cameras streaming on 12 channels.
Yard Orchestrator · Candidate #6 also re-orders two class-critical butt seams, S-31 and S-32. Sequence changes on class-critical seams stay with a human, so the step was held for the shift welding engineer and approved at 06:12:44.
Quality-and-Anomaly · Twelve weld cameras and the UT station fused at the yard edge. One porosity precursor on S-31 at 06:41 flagged and cleared by a 4% wire-feed trim inside the WPS-117 envelope; the joint was routed to UT and passed.
Fair-and-Form · Post-weld scan registered against the twin: 2.1 mm at the erection joint. Two line-heating passes planned on the inner bottom and executed by the fairing crew; re-scan read 1.8 mm, inside the 2 mm tolerance.
Blast-and-Coat · Ballast-tank blast and first coat scheduled to a window with steel temperature 3.4 °C above dew point. Dry-film thickness read 312 µm against a 280 µm minimum on the stripe coats; PSPC evidence assembled per area.
Schedule-and-Yard · Re-solved the D1 dock and crane plan with B-214 ready 6 hours early and a neighbouring block late: erection slot pulled forward one shift, crane G2 reassigned, no berth conflict. Planner approved the revised plan.
Erect-and-Align · Both blocks scanned on D1 and registered against the twin; fit predicted at 1.6 mm. Shimming guidance issued to the erection crew, block landed and welded out, final scan 1.6 mm. Conformance record written: welds, scans, coating readings, approvals and class evidence for B-214.
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 yard or the surveyor.
Plan, thought, action, observation, exactly as the orchestrator would record it.
Build and erect B-214 inside WPS-117, hold the erection joint within 2 mm, coat the ballast tank inside the PSPC window, and land it on D1 by the dock plan.
Simulate weld sequences on the twin first. Lead with the sequence because distortion is decided at the arc, then cut to the fit-up the sequence assumes, then weld and inspect continuously. Scan after welding and fair only what the scan shows. Hold any class-critical seam change for a human.
The standing sequence welds the inner bottom straight through and predicts 4.2 mm at the joint, which means fairing hours and a risk to the D1 slot. A back-step sequence with two class-critical seams re-ordered predicts 1.8 mm at a cost of 0.4 hours of takt.
twin.simulate(candidates=18) returns plan #6: back-step on the non-critical seams, S-31 and S-32 re-ordered, heat input held inside WPS-117.
Plan #6 predicts 1.8 mm at the joint and clear crane reach on D1. Three candidates scored lower on distortion but moved heat input outside the WPS envelope and were discarded.
Execute plan #6: eight bounded writes permitted on cutting, non-critical weld sequence, parameters inside WPS, coating windows and dock plan; the class-critical seam order routed to the shift welding engineer.
Porosity precursor on S-31 at 06:41:03. A 4% wire-feed trim inside WPS-117 cleared it in 15 s; the joint was routed to UT and passed. Post-weld scan 2.1 mm, two line-heating passes brought it to 1.8 mm.
Scenario complete. Block landed at 1.6 mm, ballast tank coated inside the window, conformance record written for class review.
Hullira is not a dashboard. Each agent closes a loop a yard already measures in rework, fairing hours, coating non-conformance and dock days. The tables show what each loop watches and what it is allowed to move.
Weld-pool, seam and bead cameras and the UT and X-ray streams are fused at the yard edge into a live estimate of defect risk per joint. Weldra trims parameters inside the qualified WPS envelope and routes the suspect joint to the right check before the block closes.
| Signal | Watches | Moves |
|---|---|---|
| Defect risk | Weld-pool and seam cameras, UT, X-ray | Wire feed, travel speed, heat input inside WPS |
| Seam sequence | Plan from the twin | Non-critical seams; class-critical seams under approval |
| Inspection routing | Risk score per joint | UT or X-ray queue, hold on the joint |
A weld-thermal FEA surrogate forecasts how each block moves for a given sequence, heat input, material and geometry. Fairix picks the sequence and back-step pattern before the arc strikes, and plans the line heating from the post-weld scan instead of from a shipwright's eye.
| Signal | Watches | Moves |
|---|---|---|
| Predicted distortion | FEA surrogate on the twin | Weld order, back-step pattern |
| As-built deviation | Laser scan and photogrammetry | Line-heating passes, under accuracy-control approval |
| Block tolerance | Per join from the erection plan | Hand-off to Aligna only inside tolerance |
Humidity, dew point and steel temperature are read continuously against the coating specification. Coatiq schedules blast and coat to an open window, pauses robotic cells when it drifts, reads dry-film thickness as it goes and assembles the PSPC evidence per area without a clipboard.
| Signal | Watches | Moves |
|---|---|---|
| Environmental window | Humidity, dew point, steel temperature | Blast and coat timing per area |
| Surface profile | Vision after blasting | Re-blast flag, cell pause |
| Film thickness | Dry-film gauge readings | Stripe coat and recoat inside the specification |
Both blocks are scanned and registered against the as-built twin before the crane moves. Aligna predicts the fit, issues shimming guidance, and Dockos re-solves the dock and crane plan as blocks run early or late, so a six-figure-a-day dock is not waiting on a block that will not fit.
| Signal | Watches | Moves |
|---|---|---|
| Fit at the joint | Point clouds of both blocks | Shimming and positioning guidance |
| Dock and crane plan | Block readiness, crane capacity, berths | Erection order and slots, under planner approval |
| Class evidence | Welds, scans, coating readings, approvals | Release or hold, written for sign-off |
A yard does not go from paper travelers to unattended welding in one step. Hullira makes the level explicit, auditable and reversible at any time. The first release runs shadow mode, then assist mode, then supervised control on low-risk actions. Class-critical seam changes, lift plans and block release stay with named people.
| Level | What the agent does | What the human does | Where it sits in a pilot |
|---|---|---|---|
| L1 · Shadow | Reads weld, scan, NDT, coating, robot, crane and MES signals; predicts and recommends; writes nothing | Runs the process as today; compares predictions to NDT and surveyor outcomes | Shadow mode; the baseline is measured from the yard's own records |
| L2 · Assist | Proposes weld, fairing, coating, routing and schedule moves with evidence, confidence, envelope and rollback path | Approves each action in the review console | Assist mode, the remainder of the pilot |
| L3 · Supervised control | Executes pre-approved low-risk actions: inspection routing, coating pauses when a window drifts, weld parameters inside the WPS envelope, robot path variants tested in simulation | Approves class-critical seam changes, lift plans and block release | Graduated autonomy, after audited accuracy and ROI |
| L4 · Bounded | Supervised work sequencing and weld adaptation for qualified block types, across processes and yards | Sets the envelope; reviews the shift record and the evaluation results | Planned; after class, yard and insurer acceptance is earned |
A weld pool is decided in milliseconds and a dock waits by the hour. Perception has to be local, deterministic and fast, so Hullira runs GPU inference at the yard edge and keeps training, simulation and optimisation in the cloud or on-prem.
6 to 24 cameras per process area plus UT, X-ray, thermal, laser-scan, photogrammetry, robot and coating-instrument streams fused at the yard edge. Sub-50 ms weld alerts and sub-150 ms coating or scan prompts are the design targets. Jetson Thor is planned for higher camera density.
Weld-defect, distortion-risk, coating-risk, point-cloud and schedule-risk models behind one orchestrator at the yard edge, versioned with rollback, routed by latency, tenant, sensitivity and cost.
Weld-defect vision, UT and X-ray classification, NeMo class-rule reasoning and weld-thermal FEA surrogates fine-tuned per tenant: 100 to 500 GPU-hours per yard during onboarding, then monthly retraining from engineer corrections and class outcomes. Dedicated training capacity is planned.
Block erection, weld sequence, robot reach, crane paths and yard layout simulated before the shift, as-built against as-designed. GPU weld-thermal and structural FEA is the workload; physics-informed surrogates rank plans at shift cadence.
Rare weld defects, coating failures, distortion modes, occluded seams and erection misalignment cases generated and validated against real NDT and scan distributions before promotion. 50k to 250k variants per vessel class is the target. Planned.
Dock, crane and berth schedules, work-package sequencing, yard logistics and erection order, re-solved as progress changes.
Robotic weld, blast, coat and inspection cells and crawler or drone hull inspection, with paths validated in simulation before they run next to a hull.
Telemetry ETL across weld parameters, scans, NDT results, coating readings, non-conformance and schedule history, for retraining, drift detection and rework, dock-time and schedule benchmarks.
WPS and PQR, class-rule, PSPC, cyber and human-approval policies enforced before any action writes back to robots, MES, QA or work packages; retrieval with citations and tenant isolation.
Hullira writes to production equipment. Every capability is scoped, every write is policy-checked against the qualified WPS, class and PSPC constraints, and every action is written to an append-only audit log the yard owns.
| Item | Scope | Status |
|---|---|---|
| SOC 2 Type I | Cloud control plane | QUEUED Planned, first 6 months, with a defense and ITAR-aware review |
| 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 |
| Class-society and defense assurance packages | Disposition and genealogy evidence | QUEUED Planned, 6 to 12 months; not a class approval or certification claim |
| Cited reasoning | WPS and PQR, ABS, DNV, LR, ClassNK, IMO PSPC, naval specs | RUNNING In the design, every answer cites its source |
| Per-tenant and IP isolation | Drawings, WPS, naval data, models, memory | RUNNING In the design from day one |
| On-prem and yard-edge deployment | Naval and regulated yards | RUNNING Design option |
The questions production directors, welding engineers and class-compliance leads ask in the first meeting.
Yes, but only within an explicit tag allow-list with per-tag rate and magnitude limits, inside the qualified WPS, coating, dimensional and schedule constraints, and only at the autonomy level your yard has set. Design partners start in shadow mode, where Hullira writes nothing. Class-critical seam changes, lift plans and block release stay with named people.
Control returns to the robot controller, PLC or planner's last known-good state. Hullira is a supervisory layer on top of the controllers and interlocks you already run, never a replacement for them, so an outage degrades the process to its current way of running, not to a stop.
Advisory recommendations start from the physics-based twin, the WPS and the block drawings in the first weeks. Defect, distortion and coating prediction improve as block history and labelled NDT and surveyor outcomes accumulate. Onboarding is sized at 100 to 500 GPU-hours per yard and 50,000 to 250,000 synthetic variants per vessel class, both design targets.
Only if you choose cloud training. Drawings, WPS and PQR, naval data, process models and quality records are isolated per tenant and never used to train another customer's models. Security is defense and ITAR-aware, a fully on-prem deployment at the yard edge is available for naval and regulated yards, and federated learning across yards is planned and waits on data-rights agreements.
You are, the same as with any procedure change, 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 evidence, the WPS or class citation applied and the human decision.
A paid pilot on one process, scoped to a single wedge with a success metric written into the order form: weld rework, fairing hours, coating non-conformance, dock days or class-approval cycle time. Shadow mode comes first and the baseline is measured from your own records. We do not publish a pilot length because we have not run one.
Start with one welding, fairing, coating or erection process and one measurable baseline. A paid pilot on weld inspection, distortion control or coating assurance shows the number before you commit further.
↑↓ navigate↵ openesc close