How IAG’s Home-Grown AI Could Save Airlines Millions

In an industry where operational efficiency is measured in minutes and margins, the potential of artificial intelligence to streamline airline maintenance logistics is more than an optimization exercise, it’s a necessity. That’s why the International Airlines Group (IAG) developed its new AI-powered Engine Optimisation System. Designed in-house and now implemented with Aer Lingus, the system is poised to roll out across IAG’s other airlines British Airways, Iberia, Vueling, and LEVEL by year’s end.

Turning a Complex Problem into an AI Challenge

The system, built within IAG’s London and Barcelona-based AI Labs, is engineered to solve a particularly complex problem: how to schedule engine maintenance in a way that simultaneously satisfies regulatory mandates, part availability, labor constraints, and operational continuity.

Every commercial jet engine must meet strict regulatory intervals while also fitting around flight schedules, parts inventory and shop capacity. Planners juggle thousands of variables, yet one late part or an unexpected route change can unwind months of work.

By running millions of “what-if” scenarios every day, IAG’s new system re-plans in minutes instead of weeks, helping the airline avoid Aircraft On Ground emergencies serious enough to ground the airplane until it’s fixed and maintenance-related passenger delays. The system is designed to update maintenance schedules dynamically, adapting in real time as new data flows in.

“By applying advanced algorithms, we’re making our engine maintenance programme more efficient. We are avoiding unnecessary maintenance delays to ensure that our fleet is available and in service,” explains Ben Dias, IAG’s chief AI scientist. “The system gives our people the data and tools they need for smarter planning and better teamwork.”

An In-House Approach to AI System Development

Many organizations license predictive-maintenance dashboards from OEMs or software vendors. IAG chose a different path: keep the data, keep the code and tune the algorithms to its own mixed fleet. Dias’ team started with the workhorse CFM56 engine, a common type in narrow-body aircraft, to prove the concept before moving to other engine families.

Owning the intellectual property matters for two reasons. First, IAG can refine the model as its network, fleet mix and shop capacity change. Second, the group avoids vendor lock-in, critical when an engine swap between BA and Iberia can hinge on data portability.

AI Making an Increasing Impact in the Airline Industry

IAG’s efforts align with similar changes happening in aviation. Lufthansa Technik uses its Aviatar platform for predictive diagnostics that spots repetitive fault codes and suggests fixes, part of a suite used by 100-plus airlines. Delta Air Lines’ APEX engine-health system crunches real-time sensor data; the carrier claims parts-demand accuracy has jumped from 60% to 90%. Air France-KLM is working with Google Cloud to layer generative-AI tools onto its existing “Prognos” analytics stack for both maintenance and network planning.

Where IAG differs is its focus on prescriptive optimization. The model does not simply predict when an engine might need service, it chooses the slot that minimises ground time across a 700-aircraft portfolio.

Taking a broader look, the financial upside becomes clear. With the industry set to spend over $100 billion annually on maintenance, repair and overhaul (MRO) by 2030 according to Strategic Market Research’s Aircraft MRO Market Size & Forecast report, even single-digit gains have massive implications. McKinsey estimates AI-driven maintenance could cut costs by 20% and eliminate up to half of unscheduled repairs.

There’s also a sustainability edge. By reducing last-minute swaps and repositioning flights, the system can lower emissions, helping airlines meet environmental targets while saving money. A smoother shop schedule reduces repositioning flights and last-minute charters, lowering fuel burn and CO₂.

Obstacles on the AI Taxiway

Still, there are bumps ahead. AI relies on clean, consistent data, and aviation data can be messy. Airlines still wrestle with inconsistent logbook entries, paper-based records and parts tagged under multiple naming conventions. IAG spent months cleaning historical files and standardizing schemas before training the model. Integrating these systems with existing workflows, especially under strict safety regulations, adds another layer of complexity.

Change management is equally tough. Engineers used to white-board plans may bristle at a probabilistic recommendation engine. That is why the system presents its schedule, along with the factors that drove each choice, for human sign-off. Trust builds when planners can challenge the AI, tweak a variable and watch the plan update in seconds.

Getting the data right, and earning trust from frontline teams, will be key to long-term success.

Where the Airline Industry Is Heading

AI developments in the industry could push things even further. Technicians could share anonymized model insights across member airlines in a federated-learning loop. This would allow datasets from different airlines and locations to improve each other without exposing commercially sensitive details. Longer term, this could feed the optimization layer with live flight-ops and crew-roster data so that disruption management and maintenance planning draw from a single source of truth.

If that sounds ambitious, keep in mind that pilots once lugged over 30 pounds of binders to the cockpit in large black roll-aboard suitcases. The electronic flight bag (EFB), a tablet-class device that stores charts, manuals and performance calculators in digital form, changed that. Today they are table stakes. A decade from now, an AI-based scheduler that treats engines, slots and spares as a living puzzle may feel just as ordinary, and IAG will have gained a multi-year head start.