Artificial intelligence software

managementmonitoringquality

Overview
GE Aerospace has built one of the aviation industry’s largest AI patent portfolios through years of investment in supercomputing and digital technologies. Today, AI is applied to accelerate Safety, Quality, Delivery and Cost (in that order) to support customers at scale. The company deploys AI across design, manufacturing and services to shorten design cycles, improve inspection consistency, predict demand and reduce turnaround time.

Design

• Generative AI Design — accelerates preliminary engine and propulsion design to reduce design times and produce hundreds of design iterations rapidly.
• Supercomputing — large-scale use of exascale-class supercomputers to accelerate breakthrough engine designs (examples cited: Open Fan, hypersonic ramjet studies).
• AI for Materials — collaborating with research partners to discover and demonstrate advanced materials for hypersonic vehicles.

Manufacturing

• AI Engineering Assistant — AI trained on 30+ years of part data to inspect new parts and standardize nonconforming-hardware evaluations, reducing thousands of hours in evaluation and improving traceability and quality.
• Agentic AI for Production Readiness — multi-year partnership to predict demand and identify production constraints earlier, enabling more reliable delivery planning.

Services

• AI Material Assistant — predicts parts needed during engine shop visits months ahead to cut turnaround times by an estimated 5–7 days.
• AI-Enabled Blade Inspection Tool — guides turbine blade image review to improve inspection consistency and reduce process time by about half.
• AI-Guided White Light Robot Inspection — provides a second set of eyes for accurate, consistent inspections to help technicians make better decisions.

AI Impact (selected metrics)

• 24x7 AI-powered engine safety and health monitoring.
• ~60% faster preventative maintenance identification with AI.
• ~50% faster on‑wing blade inspection time versus past approaches.
• Investment in AI in 2026 targeted at ~2x the prior year.

People & Use Cases

• Employee case examples describe technicians and engineers using AI-guided robot inspection, AI engineering and quality assistants, and generative AI design apps to shorten design and inspection cycles.

Guiding principles for responsible AI use

• Trust — use trusted, reliable data and a methodical approach to data selection for model training.
• Transparent — require system transparency and repeatability so teams understand and have confidence in AI outputs.
• Human — keep a human in the loop: AI enables faster workflows but human experts make final decisions.

Caractéristiques / spécifications techniques

• Largest AI patent portfolio in aviation (company-level claim).
• Use of exascale-class supercomputing resources to accelerate design exploration.
• AI Engineering Assistant trained on 30+ years of part and nonconformance data for standardized part evaluation.
• Predictive capabilities for shop visit parts demand (reduces turnaround by 5–7 days).
• AI-enabled inspection tools reduce blade inspection time by ~50% and improve consistency.
• 24x7 AI monitoring for engine safety and health.
• Targeted AI investment increase (approx. 2x in 2026 vs prior year).