GE Aerospace’s Flight Path to the Future: How AI is Powering the Next Era of Aviation

In an exclusive conversation with Express Computer, Jayanth Sekar, AI Leader – Digital Technology, GE Aerospace, opens up about how the company is transforming the aviation world with world-class artificial intelligence. From reducing inspection times and emissions to improving maintenance accuracy and engine reliability, AI is at the center of GE Aerospace’s strategies. He explains how their Lean + Digital approach fuels rapid innovation, the growing application of generative AI in their internal operations, and the manner in which the company’s R&D centre in Bengaluru is creating predictive maintenance technologies for a global fleet of over 45,000 jet engines.

GE Aerospace has been a pioneer in the application of AI in aviation. Can you walk us through some of the recent AI-powered innovations or solutions that have made a tangible impact across your operations?

AI is not new to us. We are leveraging AI to increase speed, quality, and productivity across our operations for well over a decade now. As one of the industry’s top AI patent holders, we have been at the forefront of integrating AI across our operations, delivering tangible improvements in engine maintenance, inspection, and operational efficiency.

Few of the recent notable advancements include the AI-enabled Blade Inspection Tool (BIT), which uses deep learning algorithms to analyse turbine blade images, reducing inspection time by 50% and improving detection rates by 34%. 

AI is also driving sustainability through tools like Fuel Insight, which analyses flight data to optimise fuel efficiency, reducing emissions and fuel burn for airlines. Generative AI is transforming workflows too, with AI Wingmate, developed in collaboration with Microsoft, processing ~3 million employee queries, enhancing productivity and collaboration across the organisation.

You’ve mentioned GE Aerospace’s focus on a Lean + Digital approach. How does this methodology shape your data science initiatives and help scale AI solutions across the organisation efficiently?
Our Lean + Digital approach ensures that AI solutions are developed with precision, scalability, and measurable impact. Lean principles help identify high-value problem areas, while digital tools enable rapid prototyping and enterprise-level deployment. FLIGHT DECK, our lean proprietary operating model, is a systematic approach to running the business to deliver exceptional customer value.

By embedding Lean principles into AI development, we ensure that every model delivers operational excellence, whether it’s fleet health diagnostics, supply chain optimisation, or component inspection. This methodology has been instrumental in scaling solutions like Digital Twins and Analytics-Based Maintenance (ABM), which helps predict and optimise engine maintenance schedules and reduce unscheduled removals.

With over 45,000 jet engines in your commercial fleet, engine maintenance becomes a critical area. How is AI being deployed to optimise inspection, repair cycles, and turnaround times in real-time?

AI is revolutionizing engine maintenance through 24×7 monitoring systems of our 45,000 commercial engines powered by advanced machine learning models. These systems detect anomalies and predict maintenance needs with greater accuracy, enabling earlier preventative measures and reducing false alerts by 50%. Predictive analytics has also improved detection rates by 45%, optimising repair cycles and significantly reducing turnaround times. Specifically, the use of AI has enabled to expand the number of conditions that can be monitored with greater accuracy and anticipate needed maintenance measures ahead of services.

Digital Twin technology mirrors real-time engine performance, enabling predictive maintenance and optimising repair cycles. The AI-enabled BIT further enhances turnaround times by halving inspection durations while improving accuracy. Together, these tools shift maintenance from reactive to predictive, reducing costs and improving reliability.

Can you share some insights on the AI-enabled Blade Inspection system used in the GEnx engine’s turbine blade analysis? How has computer vision enhanced accuracy and speed in the maintenance process?

The AI-enabled BIT leverages computer vision and deep learning to guide technicians in selecting high-quality images of turbine blades during borescope inspections, ensuring consistent records and measurements. It has helped improve the accuracy of inspections and cut the processing time in half from 3 hours to 1.5 hours compared to standard Borescope inspections. Recently, GE Aerospace commercially deployed an AI-enabled BIT for the *CFM LEAP in the narrowbody engine segment, which is patterned after one developed for the GEnx widebody engine that has been in the field for a few years now. GE Aerospace engineers are currently developing an AI-enabled BIT for the GE9X to have ready when it enters service. 

The expanded application of the AI-enabled BIT to other commercial jet engine platforms is all part of our commitment to further enhance fleet management and operational efficiency. 

By standardising image selection and enhancing visual consistency, BIT ensures faster turnaround times and more reliable engine performance, making it a critical innovation for MRO operations.

*The CFM LEAP engine is produced through a 50/50 joint venture between GE Aerospace and Safran. 

GE Aerospace’s R&D Centre in Bangalore plays a pivotal role in global innovation. How is the team there contributing to the advancement of AI and ML technologies, particularly in predictive and analytics-based maintenance?

Our Bangalore research and engineering centre, with 1000+ technology patents has been moving innovation forward for over 25 years with data-led intervention in many parts of the engine lifecycle. Data scientists here are at the forefront of advancing AI and ML technologies that are redefining predictive maintenance and fleet management globally.

Our data science teams in Bengaluru are playing a critical role in developing Digital Twin models that are virtual replicas of aircraft engines that simulate real-world field performance. These models help reduce unnecessary work in Maintenance, Repair, and Overhaul (MRO) shops, prevent unscheduled engine removals, and improve forecast accuracy​.

The team is also driving innovations in Aircraft Engine Health Analytics, where raw engine data is transformed into intelligent insights through anomaly detection, deep learning, and predictive analytics. These insights are integrated into our Analytics-Based Maintenance (ABM) tool, enabling condition-based maintenance schedules that extend engine time-on-wing and reduce operational disruptions.

The Bengaluru centre has also contributed to the development of next-generation inspection technologies, using AI to analyse engine images and videos. The Analytics Based Maintenance tool analyses the images and videos, enhancing the accuracy and speed of component inspections and optimising engine maintenance schedules​. 

Predictive maintenance powered by analytics and physics-based models is a key area of innovation. How is GE Aerospace using data science to proactively detect and prevent potential engine failures before they occur?

We employ data science techniques to convert raw engine data into actionable insights. Predictive maintenance systems use these insights to detect and predict failures in engine components well ahead of service needs, reducing unplanned maintenance events and enabling proactive resource planning. This approach has reduced unscheduled engine removals by one-third, significantly improving operational efficiency.

GE Aerospace’s predictive maintenance strategy combines data science, advanced analytics, and physics-based models to anticipate engine issues before they occur. Digital Twin technology enables real-time simulation of engine performance, improving maintenance schedules and reducing unscheduled removals.
AI-powered tools forecast work scopes and parts requirements months in advance, streamlining repair cycles and ensuring quicker return-to-service times. By integrating data from thousands of engines into the ABM ecosystem, we convert telemetry into actionable insights and improving fleet availability.

AI is increasingly becoming a differentiator in terms of quality, productivity, and speed. How are you ensuring that AI systems meet high operational standards while remaining adaptable across varied aerospace challenges?

We ensure high operational standards by focusing on trusted data, transparency, and human involvement in AI processes. The interpretability and transparency of AI models are prioritised to meet regulatory compliance and ethical considerations. Additionally, the FLIGHT DECK operating model guides AI initiatives to achieve better outcomes for operations, customers, and employees. This approach ensures that AI models are robust, transparent, and aligned with regulatory compliance and ethical considerations.

By blending domain expertise with physics-based models and machine learning, we maintain adaptability across diverse aerospace applications, whether it’s improving inspection accuracy, enhancing MRO workflows, or optimising supply chain productivity.