How RTX is using AI and data to transform aircraft maintenance
RTX companies are deploying AI and data analytics to modernize aircraft maintenance, reducing inspection time and improving predictive accuracy across engines and nacelles.
RTX’s Pratt & Whitney has integrated Aiir Innovations’ AI-powered borescope tool, which automates blade counting, surface pattern tracking, and report generation during engine inspections. The software, trained on a decade of real-world inspection data, flags potential issues without distracting inspectors, reducing manual clerical work from hours to minutes. Technicians retain final decision-making authority while benefiting from AI’s second-set-of-eyes precision. The tool is already in use on V2500 engines and has completed pilots on GTF and F135 engines, with broader deployment planned.
At the Goodrich Aerostructures Service Center Asia (GASCA) in Singapore, a robotic machine-vision system called "Spot" automates the verification of quick engine change kits, cutting manual workload by about 70%. Digital mapping tools and laser-guided ply-installation systems further enhance nacelle repair accuracy by reducing rework and improving material positioning. These systems rely on real-time data to streamline inspections and maintenance processes.
Collins Aerospace’s Ascentia platform analyzes thousands of flight parameters per second, blending them with maintenance records to predict repair needs before physical signs appear or alerts trigger. Early adopters initially tested the system’s recommendations, but after confirming its accuracy in identifying degradation, airlines now expect predictive insights as standard in maintenance agreements. The platform helps operators plan replacements during scheduled downtime, turning unexpected issues into manageable routine tasks.
Across RTX’s operations, AI-driven predictive maintenance systems—such as those used by Pratt & Whitney and Collins Aerospace—enable early detection of potential issues and precise repair planning. By leveraging detailed operational and maintenance data, these tools reduce unscheduled component removals, minimize equipment list write-ups, and prevent hours of operational disruption. The result is a clearer, data-backed view of fleet health and maintenance needs months in advance.