Perception layer
Vision, in-process metrology, laser tracker and photogrammetry fuse into a single as-built state of the structure — hole, gap, fastener, surface and FOD.
38 ms p99 fusion
One loop, from the first hole to the final join
Rivetira closes the loop from perception to robot-and-line control. A shared sensing layer feeds seven agents and one as-built twin, all running on a factory edge runtime that never lets program geometry leave the building.
| Structure | Closed loop | Supervised | Advisory | Shadow | Total |
|---|---|---|---|---|---|
| Section join | 62% | 24% | 11% | 3% | 100% |
| Wing skin | 71% | 19% | 8% | 2% | 100% |
| Wing-body | 48% | 31% | 16% | 5% | 100% |
| Empennage | 74% | 18% | 6% | 2% | 100% |
| Systems | 33% | 34% | 22% | 11% | 100% |
| Final | 41% | 30% | 21% | 8% | 100% |
Four layers, one contract with the airframe
Perception is shared, agents are specialised, the twin is the arbiter and the runtime is the safety boundary. No agent actuates a machine without passing all four.
Agent layer
Seven specialised agents plan and control drilling, fastening, alignment, shimming, sealing, joining, line balance and handling.
240 Hz control
As-built twin
Simulates fit, gap, shim and structural conformance for the specific airframe in front of you, gating every action before it reaches a machine.
4.1 s per join sim
Edge runtime
Deterministic, fail-safe execution on factory hardware, with assurance-grade logging and air-gapped model management.
< 40 ms fail-safe stop
Perceive, plan, control, verify, learn
The same loop runs at every station, from a single drilling cell to a whole moving line. Nothing is actuated that has not first been simulated against the as-built twin.
-
01
Perceive
Vision, in-process metrology, laser tracker and photogrammetry fuse into a live as-built model of the structure, hole, gap and fastener state.
38 msFusion latency p99
-
02
Plan
Align, shim, drill, countersink, fasten, seal and join are sequenced against the predicted gap field and the program tolerance stack-up.
4.1 sTwin sim per join
-
03
Control
Feed and speed, interference, torque, bead geometry and crawler position are driven adaptively, with fail-safe stop at every actuator.
240 HzControl loop
-
04
Verify & learn
Hole, countersink, fastener, gap and FOD are sensed, conformance is logged immutably, and supervised corrections retrain the models.
1.4MTraced actions/day
What the platform senses, per hole
Nine measurements per hole, at station speed, on stacked metallic and composite structures. The distributions below are what the mechanic’s calipers can only sample.
| Characteristic | Resolution (mm) |
|---|---|
| Hole diameter | 0.008 mm |
| Hole roundness | 0.011 mm |
| Countersink depth | 0.009 mm |
| Countersink flushness | 0.008 mm |
| Fastener seating | 0.014 mm |
| Edge distance | 0.021 mm |
| Interlaminar gap | 0.019 mm |
| Stack-up material | Detection recall | Precision |
|---|---|---|
| Aluminium | 99.6% | 99.4% |
| Ti-6Al-4V | 99.2% | 99.0% |
| CFRP | 98.7% | 98.2% |
| CFRP/Ti | 98.1% | 97.6% |
| CFRP/Al | 98.9% | 98.4% |
| Steel | 99.4% | 99.1% |
The seven agents that run on the platform
Each agent owns one part of the structural build. They share one perception layer, one as-built twin and one conformance record, so a decision made at the drill is visible at the join.
Drill & Fasten
Adaptive control of drilling, countersinking and rivet/bolt installation.
Hole & Fastener Inspection
Vision + in-process metrology sensing of hole, countersink, fastener, gap and FOD.
Align & Shim
Metrology-assisted alignment and predictive shimming that removes hand-fit loops.
Seal & Join
Sealant application control and fuselage / wing-body join sequencing.
Line & Takt
Moving- and pulse-line station balancing, takt optimisation and travelled-work control.
Robot & Handling
Crawlers, AGVs, positioners and cranes moving and holding large structures.
Quality & Conformance
Right-first-time, non-conformance, rework and full airworthiness traceability.
Hit the fit before the join
Every airframe diverges from CAD the moment the first hole is drilled. The as-built twin models that divergence — fit, gap, shim, drilling and structural conformance — and simulates the join before a single fastener is installed.
- Simulates fit, gap field and shim geometry against the real as-built structure, not the as-designed model
- Gates every autonomy promotion: an agent only takes a step in the plant after it takes it in the twin
- Predicts tolerance stack-up across the whole join sequence, not point by point
- Replays any historical join for root-cause analysis and airworthiness investigation
| Structure | Twin prediction | Measured as-built |
|---|---|---|
| Section 41 | 0.31 mm | 0.34 mm |
| Section 43 | 0.44 mm | 0.41 mm |
| Section 44 | 0.28 mm | 0.30 mm |
| Wing box L | 0.52 mm | 0.55 mm |
| Wing box R | 0.49 mm | 0.47 mm |
| Empennage | 0.22 mm | 0.24 mm |
| Time of day | Edge inference p99 | Edge inference p50 |
|---|---|---|
| 00:00 | 36 ms | 11 ms |
| 03:00 | 34 ms | 10 ms |
| 06:00 | 41 ms | 13 ms |
| 09:00 | 44 ms | 14 ms |
| 12:00 | 39 ms | 12 ms |
| 15:00 | 42 ms | 13 ms |
| 18:00 | 38 ms | 12 ms |
| 21:00 | 35 ms | 11 ms |
Deterministic where it has to be, connected where it helps
Perception and control run on factory hardware next to the machines. The cloud control plane handles model management, fleet governance and analytics — and can be removed entirely for controlled programs.
- Hard real-time control path isolated from the analytics path
- Graceful degradation: loss of the control plane drops agents to advisory, never to an unsafe state
- Idempotent agent steps — a retried instruction never double-drills or double-fastens
- Signed, versioned model artefacts with rollback to any prior station configuration
- Air-gapped mode with offline model delivery for ITAR and classified programs
The as-built record is a first-class object
Everything the platform senses and does is addressable — by airframe, structure, station, join, hole and fastener. That record is what an airworthiness engineer exports for an audit.
<span class="tok-com"># Every hole on an airframe, with its measured state and disposition</span>
<span class="tok-key">from</span> rivetira <span class="tok-key">import</span> Client
client = <span class="tok-fn">Client</span>(site=<span class="tok-str">"everett-fa2"</span>)
holes = client.as_built.<span class="tok-fn">holes</span>(
airframe=<span class="tok-str">"MSN-4182"</span>,
structure=<span class="tok-str">"wing_box_lower_skin"</span>,
include=[<span class="tok-str">"diameter"</span>, <span class="tok-str">"roundness"</span>, <span class="tok-str">"countersink_depth"</span>,
<span class="tok-str">"flushness"</span>, <span class="tok-str">"fastener_state"</span>, <span class="tok-str">"edge_distance"</span>],
)
out_of_spec = [h <span class="tok-key">for</span> h <span class="tok-key">in</span> holes <span class="tok-key">if</span> <span class="tok-key">not</span> h.within_spec]
<span class="tok-fn">print</span>(<span class="tok-str">f"{len(holes):,} holes · {len(out_of_spec)} flagged"</span>)
<span class="tok-com"># 6,786 holes · 24 flagged</span></code><span class="term-prompt">$</span> rivetira conformance export --airframe MSN-4182 --format as9100
<span class="term-out">→ resolving as-built record ......... 1,412,884 traced actions</span>
<span class="term-out">→ hole & fastener conformance ...... 218,440 characteristics</span>
<span class="term-out">→ gap & shim record ................ 62 joins, 1 iteration each</span>
<span class="term-out">→ FOD sweeps ....................... 4,120 scans, 0 open events</span>
<span class="term-out">→ human overrides .................. 84, all signed</span>
<span class="term-out">→ signing bundle .................. sha256:9f2c…a417</span>
<span class="term-prompt">✓</span> export complete in 71s → MSN-4182-conformance.tar.zstEvery hole measured, not one in four
Hole diameter, countersink flushness, fastener seating, edge distance, gap and FOD are sensed in process — so a non-conformance is caught at the station that created it.
| Hole diameter (mm) | Holes | Within spec |
|---|---|---|
| 6.32 mm | 3 | No |
| 6.33 mm | 22 | Yes |
| 6.34 mm | 168 | Yes |
| 6.35 mm | 940 | Yes |
| 6.36 mm | 2410 | Yes |
| 6.37 mm | 2280 | Yes |
| 6.38 mm | 810 | Yes |
| 6.39 mm | 132 | Yes |
| 6.40 mm | 19 | Yes |
| 6.41 mm | 2 | No |
| Segment | Share |
|---|---|
| Hole quality / burr | 34.2% |
| Countersink flushness | 21.6% |
| Gap & shim fit | 18.4% |
| Fastener seating / torque | 13.1% |
| Sealant profile | 7.9% |
| FOD | 4.8% |
Where the line is losing its takt, four hours before it does
Station balancing is a continuous optimisation, not a quarterly study. Rivetira predicts the breach and proposes the resequencing that avoids it.
| Station | Shift A | Shift B | Shift C | Weekend |
|---|---|---|---|---|
| FA-01 Section join | 98.4% | 96.2% | 94.1% | 91.8% |
| FA-02 Wing-body | 97.1% | 95.4% | 93.2% | 90.4% |
| FA-03 Empennage | 99.2% | 98.1% | 96.4% | 94.2% |
| FA-04 Systems | 95.8% | 94.2% | 92.6% | 89.9% |
| FA-05 Final | 96.9% | 96.1% | 95.0% | 92.7% |
Reads and writes back to the machines you already own
Rivetira is not a rip-and-replace. It connects to the drilling machines, crawlers, trackers, shim cells, sealant robots and MES already on your floor over APIs and OT protocols.
Drilling & fastening
- Flex-track crawlers
- Gantry drilling machines
- C-frame riveters
- Automated fastening cells
- Hand-fed ADUs
Metrology
- Laser trackers
- Photogrammetry rigs
- Structured-light scanners
- iGPS / indoor GPS
- Articulated arm CMMs
Shimming & sealing
- 5-axis shim machining
- Liquid shim dispense
- Sealant robots
- Cure monitoring
- Bead inspection
Factory systems
- Assembly MES
- PLM / as-designed models
- ERP work orders
- Quality / NCR systems
- Historians & OPC UA
OPC UA, MTConnect, MQTT, ROS 2, REST and file-drop connectors. Read-only shadow mode first; write-back enabled only after twin validation.
Shadow first. Autonomy is earned, not switched on.
Every agent starts by watching. It is promoted only when its measured accuracy clears the mechanic-plus-metrology baseline and the twin agrees.
-
Weeks 1–4
Shadow
Agent observes the station, predicts every outcome, actuates nothing. Accuracy measured against what the mechanics actually do.
-
Weeks 4–10
Advisory
Agent recommends feed, shim geometry and sequence. A human accepts or rejects; every rejection becomes training data.
-
Weeks 10–20
Supervised
Agent actuates with a human in the loop and a live fail-safe stop. Airworthiness-critical dispositions still require sign-off.
-
Week 20+
Closed loop
Agent runs the step. Humans handle exceptions and the twin gates any change to the control policy.
| Week | Agent accuracy | Mechanic + metrology baseline |
|---|---|---|
| Wk 2 | 88.2% | 94.1% |
| Wk 4 | 91.4% | 94.0% |
| Wk 6 | 93.6% | 94.2% |
| Wk 8 | 95.2% | 94.1% |
| Wk 10 | 96.4% | 94.3% |
| Wk 12 | 97.1% | 94.2% |
| Wk 16 | 97.8% | 94.1% |
| Wk 20 | 98.3% | 94.2% |
| Wk 24 | 98.6% | 94.3% |
Every station, every structure, one record
Sort any column. The same table backs the audit export an airworthiness engineer hands to a regulator.
| FA-01 · Fuselage section join | Section 41/43 | 0.041 mm | 18 h | ||
|---|---|---|---|---|---|
| FA-02 · Wing-body join | Wing box | 0.062 mm | 31 h | ||
| FA-03 · Empennage attach | Vertical/horizontal | 0.028 mm | 9 h | ||
| FA-04 · Systems installation | Hydraulics/electrical | 0.055 mm | 12 h | ||
| FA-05 · Final assembly | Interiors/doors | 0.037 mm | 6 h | ||
| WG-11 · Wing skin-to-spar | Lower skin | 0.033 mm | 22 h | ||
| WG-12 · Wing skin-to-spar | Upper skin | 0.048 mm | 26 h | ||
| FS-21 · Fuselage panel | Barrel section | 0.030 mm | 11 h |
What the platform commits to
- Uptime target
- 99.9%
- Fail-safe stop
- < 40 ms
- Control loop rate
- 240 Hz
- Perception fusion p99
- 38 ms
- Twin join simulation
- 4.1 s
- Audit retention
- Program life + 7 y
- Conformance export
- < 90 s
- Model rollback
- Any prior version
- Tenant isolation
- Per program, cryptographic
- Encryption
- In transit + at rest
- Deployment
- Edge, on-prem, air-gapped
- Identity
- SSO / SAML, SCIM
- Access control
- RBAC to station level
- Compliance
- SOC 2 Type II, AS9100-mapped
- Export control
- ITAR / EAR aware
What changes on the floor
Plant directors, liaison engineers and airworthiness leads on what autonomy did to their numbers.
“We stopped arguing about whether the gap was 0.4 or 0.6 millimetres. The twin predicted it, the shim came off the machine right, and the join closed in one pass.”
−64% shim hours per join
“The rate ramp was going to cost us four more positions. Instead the line rebalanced itself every shift and we found the capacity inside the stations we already had.”
+38% delivered rate
“Every hole is now inspected, not one in four. My airworthiness record writes itself, and I can hand an auditor a complete trace in ninety seconds.”
100% inspection coverage
See the loop close on your line
A line assessment maps one station, quantifies the rework, shim and rate opportunity, and returns a modelled ROI in three weeks. No production disruption.