AI, robotics, and 3D printing set to streamline UAE aerospace operations
Sanad, Strata Manufacturing PJSC, and Sindan have signed a new Memorandum of Understanding at the Dubai Airshow 2025. The focus: apply artificial intelligence, robotics, and additive manufacturing across maintenance, repair and overhaul (MRO) and production.
The agreement was formalized by Mansoor Janahi, Managing Director and Group CEO of Sanad; Sara Abdulla AlMemari, Acting CEO of Strata; and Heyuan Huang, Managing Director and CEO of Sindan. They were joined by Ismail Ali Abdullah, Executive Director of UAE Clusters at Mubadala Investment Company, and Amer Siddiqui, Group Chairman of Sanad.
Janahi noted the deal brings together Sanad's MRO experience, Strata's manufacturing strength, and Sindan's AI-driven systems to advance the UAE as a center of excellence in aerospace engineering-focused on speed, precision, and sustainability.
AlMemari added that the collaboration enables practical rollout of smart production and maintenance technologies in Abu Dhabi, improving precision, productivity, and environmental performance.
What's changing on the shop floor
The partnership targets AI-enabled automation across Sanad's MRO lines and Strata's production cells. Sindan will deploy robotic inspection, automated material handling, humanoid technologies for warehouse tasks, and automated racking systems to sharpen inventory accuracy and throughput. It will also design and 3D print jigs and fixtures to shorten tooling lead times and improve manufacturing precision.
- Robotic inspection: Reduce touch time and human error while capturing structured data for closed-loop quality and faster release.
- Automated material handling: Stabilize takt, cut non-value-added movement, and improve safety in high-mix environments.
- Warehouse automation: Use humanoid assistance and automated racking to raise pick accuracy, improve slotting, and increase inventory turns.
- 3D-printed tooling: Compress tooling development cycles, enable lightweight fixtures, and tune tolerances for complex geometries.
Operationally, expect tighter turn times, fewer reworks, better part flow, and lower scrap and energy use-supporting Abu Dhabi's position as an aviation innovation hub.
Implementation playbook for operations leaders
- Start with a pilot: Pick one asset family or cell with measurable pain (e.g., high rework or long setup). Timebox 12-16 weeks.
- Map the data backbone: Define integrations from robots, vision systems, and AM machines into MES, ERP, and QMS. Standardize IDs and traceability.
- Quality and certification: Align with AS9100, special-process control, and full genealogy for AM parts. Lock audit trails and parameter sets.
- Workforce readiness: Cross-train technicians on robot HMI, AM job prep, and basic data diagnostics. Pair SMEs with automation engineers.
- Safety and cyber: Conduct machine guarding, CoBot risk assessments, and network segmentation. Define patching and access policies.
- Service model: Set SLAs for uptime, spare parts, and remote support. Track mean time to repair (MTTR) for automation assets.
- Facility fit: Validate floor loading, power, air, and heat extraction for AM. Plan material flow, cell layout, and point-of-use kitting.
- ROI discipline: Quantify baseline and deltas for TAT, FPY, scrap, labor hours, WIP, and energy per part. Target 12-24 month payback.
KPIs to watch from day one
- Turnaround time (TAT) and queue time by station
- First-pass yield (FPY), rework hours, and scrap rate
- OEE for automated cells (availability, performance, quality)
- Pick accuracy, pick rate, and cycle time in warehouse
- Inventory turns, WIP days, and stockout frequency
- Tooling lead time and calibration interval adherence
- Inspection false positives/negatives and NCR closure time
- Energy per part and CO₂ per part
- Safety incidents and near-miss rate post-automation
Signals from global programs
In Europe, GKN Aerospace has integrated Interspectral's AM Explorer software at its Engine Systems Centre of Excellence in Trollhättan, Sweden. Real-time build monitoring and AI-based anomaly detection consolidate defect reports, helping lower material waste and accelerate delivery of certified aero-engine components.
In the UK, the government is backing a £14.1 million initiative-Project STRATA-led by Honeywell to advance certified aerospace parts via additive manufacturing. The work, centered at Honeywell's Yeovil facility with partners including 3T Additive Manufacturing, BeyondMath, Qdot Technology, and the Oxford Thermofluids Institute, supports supply chain resilience and lower CO₂ across the sector. For broader context, see the Aerospace Technology Institute programme.
Practical next steps
- Run a 6-8 week discovery: value stream map one MRO line and one production cell; capture loss tree and automation candidates.
- Stand up a digital thread pilot: connect AM machine data, inspection images, and ERP/QMS records for one serialized part number.
- Set a quarterly automation council: operations, quality, IT/OT security, and finance to prioritize use cases and funding gates.
- Bake outcomes into contracts: tie vendor performance to FPY, uptime, and time-to-recover metrics, not just installation milestones.
If your team is building capability around AI-driven operations and automation, this curated list of courses can help accelerate adoption: AI courses by job role.
Your membership also unlocks:
