Voidra
See every void — porosity, wrinkles, and FOD, sensed and certified.
Edge AI that predicts porosity, wrinkles, FOD, misalignment and dry spots before the cure — then fuses ultrasonic and thermographic NDT after the cure to certify internal integrity, tracing every indication to its cause.
Why this step condemns parts
A speck of porosity, a subsurface wrinkle, a trapped void or a dry spot can silently halve a flight-critical laminate’s strength — and today they are hunted after cure by slow ultrasonic and thermographic NDT, often condemning a part that already carries tens of thousands of dollars of carbon fiber and autoclave energy. Inspection is manual, operator-dependent, and disconnected from the layup and cure history that caused the defect.
See every void — porosity, wrinkles, and FOD, sensed and certified.— Voidra, part of the Curelum autonomy platform
A closed perceive → decide → act loop
No open-loop hoping. Voidra senses, reasons against the qualified envelope, acts within bounds, and logs every action.
Predict pre-cure
In-process vision and profilometry predict porosity, wrinkles, FOD, misalignment and dry spots before the part ever enters the autoclave.
Fuse post-cure NDT
Robotic ultrasonic C-scan and thermographic evidence are fused into a single internal-integrity map.
Auto-disposition
Indications are classified and dispositioned against acceptance criteria, with engineer review where required.
Trace to cause
Every indication links back to the exact ply, machine action and cure trajectory that produced it — closing the loop with Plyoq and Curevo.
What Voidra does on the line
Pre-cure defect prediction
Porosity, wrinkle, FOD, dry-spot and misalignment risk sensed in-process, before cure.
Ultrasonic + thermographic fusion
C-scan and thermography combined into one certified integrity map.
Automated disposition
Accept / reject / review against NADCAP acceptance criteria with full evidence.
Defect-to-cause traceback
Connects every indication to ply, action and cure history for root-cause.
Operator-independent
Consistent detection across shifts, parts and inspectors.
Evidence packages
Assurance-grade inspection records for airworthiness and audit.
Instrumented, not guessed
Every Voidra readout maps to a real measurement on the floor — tow geometry, cure trajectory, C-scan integrity, or predicted strength. The interface is precision test equipment: numbers you can certify, not a dashboard of vanity charts.
- Grounded, auditable outputs on every action
- Bounded control envelopes from the Strandix twin
- Human-in-the-loop on flight-critical decisions
- Immutable audit trail for AS9100 / NADCAP
Built for the composites floor
Voidra deploys on the factory edge and integrates with the systems you already run, under your security and export controls.
| Pre-cure sensing | Vision, laser profilometry, thermal |
|---|---|
| Post-cure NDT | Ultrasonic C-scan, thermography, robotic scanning |
| Defect classes | Porosity, wrinkle, FOD, dry spot, misalignment |
| Disposition | Automated with human-in-the-loop review |
| Traceability | Indication → ply → action → cure trajectory |
| Standards | AS9100 / NADCAP-ready evidence packages |
Fits your stack, under your controls
AFP / ATL controllers
Autoclave / OOA
Ultrasonic & thermographic NDT
MES / ERP
OPC-UA / OT
Historian & PLM
Trust before autonomy
Voidra runs in shadow, then assist, then bounded autonomy — grounded, auditable, and human-supervised at every airworthiness-critical checkpoint.
Stronger together across the loop
Questions engineers ask
Does Voidra replace our NDT technicians?
It augments them: Voidra automates detection, fusion and first-pass disposition, and frees inspectors to adjudicate exceptions with full evidence and traceability.
Can it work pre-cure only?
Yes. Many customers land on pre-cure prediction to stop defects before autoclave energy is spent, then add post-cure NDT fusion.
How does traceback work?
Voidra shares a part timeline with Plyoq and Curevo, so each indication is linked to the machine action and cure trajectory that caused it.
Put Voidra on your line
Start with one cell, a hard success metric, and a paid pilot. Prove ROI, then expand across the loop.