Turbofan Engine Health Management AI/ML Patent Landscape
The turbofan engine health management AI/ML patent space is highly concentrated, with RTX Corp alone accounting for the plurality of activity among the top filers. The field is in a Growth life-cycle stage, expanding on a multi-year basis, though annual volume has eased from its 2023 peak and recent years remain understated by publication lag.
RTX Corp leads a tightly held field dominated by aerospace OEMs
RTX Corp holds the top position among ranked applicants with 46 patent records, followed by General Electric Co with 22 and Rolls-Royce PLC with 20. The top five filers together account for 71% of the combined total across the hundred largest filers, signaling a strongly consolidated competitive landscape.
The gap between the first-tier OEMs — RTX Corp, General Electric Co, and Rolls-Royce PLC — and the second tier is substantial. Honeywell International Inc and Rolls-Royce North American Technologies Inc hold 8 and 7 patent records respectively, less than half the volume of the third-ranked player.
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 1 | RTX Corporation | 46 | |
| 2 | General Electric Company | 22 | |
| 3 | Rolls-Royce PLC | 20 | |
| 4 | United Technologies Corporation | 16 | |
| 5 | Honeywell International Inc. | 8 | |
| 6 | Rolls-Royce North American Technologies Inc. | 7 | |
| 7 | Meggitt SA | 4 | |
| 8 | University of Southern California | 3 | |
| 9 | Oliver Crispin Robotics Limited | 3 | |
| 10 | NANJING UNIV OF AERONAUTICS & ASTRONAUTICS | 3 |
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 11 | PRATT & WHITNEY CANADA CORP | 3 | |
| 12 | Rolls-Royce Corporation | 2 | |
| 13 | Inha University | 2 | |
| 14 | Harbin Institute of Technology | 2 | |
| 15 | Dr. B. Ramesh | 1 | |
| 16 | Dr. A. Madhan Kumar | 1 | |
| 17 | Mr. S. R. Kasthuri Raj | 1 | |
| 18 | Siemens Corporation | 1 | |
| 19 | Mr. R. Sunilkumar | 1 | |
| 20 | Dr. A. Samuel Raja | 1 |
This concentration implies that the three leading OEMs have erected substantial prior-art barriers in core health-monitoring architectures. Challengers and new entrants will need to identify differentiated technical approaches or adjacent application domains to avoid direct collision with established portfolios.
Filings from 2024 onward are subject to publication lag and will be understated in current counts; the apparent slowdown in 2024–2026 should not be interpreted as a real decline in activity. Longer-window growth, applicant concentration, and technology-route coverage are therefore more reliable signals than the latest-year bar alone.
Growth-stage field with a broad turbine-centric technology base and emerging AI coding
The filing trend reflects multi-year growth consistent with the field’s Growth life-cycle stage, while the technology composition reveals a dominant mechanical-control core increasingly overlaid with AI and data-processing classes.
Annual filing trend
Filings climbed from 12 in 2017 to a peak of 20 in 2023, confirming multi-year expansion. The dip to 12 in 2024 and 4 in 2025 reflects publication lag, not a genuine contraction; treat those figures as provisional floors rather than trend reversals.
↗ Hover for values · click a bar to ask EurekaTechnology composition
F01D (Turbines and non-positive engines) dominates with 93 patent records, anchoring the portfolio in core turbine mechanics. G05B (Control and regulating systems, 61 records) and F02C (Gas-turbine plants, 48 records) form a strong control-systems layer. G06N (Computing based on AI models, 34 records) and G01M (Testing machine and structure balance, 31 records) confirm that machine-learning inference and structural testing are becoming integral rather than peripheral to the field.
↗ Hover for values · click a bar to ask EurekaHighly cited patent families surfaced by the query
Citation-heavy patent families returned by the query. Use this section as citation context, not as a curated list of the most topic-specific patents.
COMPUTERIMPLEMENTIERTES VERFAHREN ZUR BESTIMMUNG D…
A computer-implemented method comprising: controlling input of data quantifying damage received by one or more components of a gas turbine engine into a first machine learning algorithm; receiving data quantifying a first operating parameter of the gas turbine engine as an output of the first machine learning algorithm; and determining operability of the… (excerpt from the patent abstract)
| # | Patent | Citations |
|---|---|---|
| 1 | Method and system for modeling the performance of … | 94 |
| 2 | 一种基于故障特征迁移的航空涡扇发动机剩余寿命预测方法 | 38 |
| 3 | MFCC and CELP to detect turbine engine faults | 37 |
| 4 | Machine learned aero-thermodynamic engine inlet co… | 34 |
| 5 | Reducing gas turbine performance tracking estimati… | 27 |
| 6 | Machine learning-aided model-based method for esti… | 24 |
| 7 | Methods and systems for turbine line replaceable u… | 22 |
| 8 | Systems and methods of servicing equipment | 21 |
Ranked by total forward citations. Citation counts favour older and broadly cited patent families, and broad or adjacent patents may appear when they match the search scope. Treat this section as citation context, not as a curated list of the most topic-specific patents. Some patent titles may be shown in their original, non-English language where an accurate translation could not be guaranteed.
What the competitive structure means for R&D investment decisions
The combination of high concentration, Growth-stage dynamics, and a deepening AI layer creates distinct strategic pressure points for incumbents and new entrants alike.
Growth stage, easing from 2023 peak
The field carries a Growth life-cycle label: the recent three-year filing window sits well above the prior three-year window, confirming genuine expansion. Annual volume, however, has eased from its 2023 peak of 20 filings. Teams entering now will find an active but not yet mature prior-art environment, with room to differentiate on AI model architecture and sensor-fusion approaches before the field consolidates further.
Growth · easing from 2023 peak71% share held by five filers; tier gap is large
The top five filers hold 71% of the combined total across the hundred largest filers, and the gap between the top three OEMs and the rest is pronounced. RTX Corp’s 46 patent records dwarf the second-ranked General Electric Co at 22 and Rolls-Royce PLC at 20. For new entrants, the practical implication is that direct competition in core turbine fault-detection architectures requires navigating a dense prior-art landscape controlled by three well-resourced incumbents.
Highly concentratedIndustry-academia and cross-OEM co-filings are emerging
The most active co-filing pairs are General Electric Co with Oliver Crispin Robotics (3 joint filings), Rolls-Royce North American Technologies Inc with Rolls-Royce Corp (2 filings), and the University of Southern California with Inha University (2 filings). The GE–Oliver Crispin pairing links inspection robotics with health-management data, suggesting that in-situ robotic inspection is being integrated into AI-driven maintenance workflows. The USC–Inha academic collaboration points to university-led algorithm research feeding into the broader ecosystem.
Cross-sector co-filingUS and EPO dominate; China presence is limited
The United States leads with 63 patent records, followed by Europe (EPO) with 55, reflecting the home jurisdictions of the dominant OEMs and their primary commercial aviation markets. China holds 8 records and WIPO (PCT) 4, indicating that Chinese applicants — including Nanjing University of Aeronautics and Astronautics and Harbin Institute of Technology — are present but at modest scale. Teams seeking freedom-to-operate in Asian markets will find a comparatively less crowded prior-art environment.
US + EPO coreGo beyond the landscape: Eureka’s TRIZ Solution agent breaks down an R&D problem and returns patented concept solutions, each with a technical approach and cited patent & literature evidence.
| Applicant | Collaborator | Co-filings |
|---|---|---|
| General Electric Company | Oliver Crispin Robotics Limited | 3 |
| Rolls-Royce North American Technologies Inc. | Rolls-Royce Corporation | 2 |
| University of Southern California | Inha University | 2 |
Co-filing pairs, ranked by the number of jointly-filed patent families.
RTX Corp and Rolls-Royce PLC differ sharply in trajectory and technical emphasis
The leading applicants share a common anchor in F01D turbine mechanics but diverge in their secondary technology focus — RTX Corp leans on control-systems depth, while Rolls-Royce PLC shows the strongest AI model commitment among the top filers.
RTX Corp
RTX Corp holds 46 patent records, the largest portfolio among ranked applicants, built primarily around F01D 21 (turbine fault detection, 20 records), G05B 23 (condition monitoring control systems, 8 records), and F01D 25 (turbine bearing and casing management, 7 records). Applicant momentum is marked as a new entrant in the recent measurement window, suggesting the RTX Corp entity consolidation has concentrated filings that previously appeared under United Technologies Corp. The portfolio’s breadth across mechanical and control-systems classes makes it the dominant prior-art reference point in this field.
patent records: 46Rolls-Royce PLC
Rolls-Royce PLC holds 20 patent records and carries the strongest AI model emphasis among the top three, with G06N 3 (neural-network-based AI models, 11 records) as its second-largest focus class after F01D 21 (18 records). This differentiates Rolls-Royce from RTX Corp and General Electric Co, whose secondary classes remain rooted in control systems and structural testing. However, applicant momentum shows a decline of 69% in recent filings, indicating a slowdown in new Rolls-Royce PLC activity that warrants monitoring — though publication lag may partially account for this.
patent records: 20| Applicant | Recent (3 yrs) | Trend |
|---|---|---|
| RTX Corporation | 23 | ▲ new entrant |
| General Electric Company | 8 | ▲ new entrant |
| Rolls-Royce PLC | 4 | ▼ -69% |
| Meggitt SA | 4 | ▲ new entrant |
| Pratt & Whitney Canada Corp. | 3 | ▲ new entrant |
Under-served adjacent branches worth monitoring for R&D positioning
Several IPC classes appear at comparatively low volumes relative to the dominant F01D and G05B core, representing areas where the prior-art density is lower and targeted entry may be feasible. These are observations of relative sparsity; technical and commercial validation would be needed before treating them as confirmed opportunities.
G01M · Structural and machine testing methodologies
G01M carries 31 patent records — meaningful volume, but its share relative to the dominant F01D class (93 records) suggests that formal structural and balance-testing frameworks are less thoroughly covered than fault-detection architectures. Turbofan health management increasingly requires physics-informed test protocols to validate AI model outputs; an applicant bridging G01M test methods with G06N inference models could occupy a differentiated position. The most direct entry path would be through sensor-array test-bench innovations linked to on-wing diagnostic algorithms.
Search this in Eureka →G01N · Material analysis and non-destructive testing
G01N holds only 12 patent records in this corpus, reflecting sparse coverage of material-level and non-destructive testing (NDT) methods applied to turbofan health management. As AI-enabled inspection — including robotic in-situ inspection as suggested by the GE–Oliver Crispin collaboration — becomes more prevalent, coupling NDT signal processing with ML classifiers is a plausible and technically grounded direction. Prior-art density is low enough that a focused filing program in AI-assisted NDT for hot-section components could establish a credible position without direct conflict with the dominant OEM portfolios.
Search this in Eureka →How leading applicants differ across technology routes
Route coverage across the main technology branches in the current evidence set.
| Player | F01D 21 · Turbines & non-positive engines | G05B 23 · Control & regulating systems | F02C 7 · Gas-turbine plants | G06N 3 · Computing based on AI models | G01M 15 · Testing machine & structure balance |
|---|---|---|---|---|---|
| United Technologies Corporation | Strong · 20 | Strong · 15 | Moderate · 8 | Moderate · 5 | Moderate · 7 |
| Rolls-Royce PLC | Strong · 18 | Strong · 10 | Moderate · 4 | Strong · 11 | Moderate · 7 |
| RTX Corporation | Strong · 20 | Moderate · 8 | Emerging · 3 | Moderate · 5 | Emerging · 4 |
| General Electric Company | Strong · 19 | Moderate · 5 | Moderate · 6 | Absent | Moderate · 7 |
| Honeywell International Inc. | Moderate · 4 | Moderate · 4 | Strong · 8 | Absent | Moderate · 4 |
| Rolls-Royce North American Technologies Inc. | Moderate · 2 | Strong · 7 | Moderate · 2 | Absent | Absent |
| Rolls-Royce Corporation | Strong · 2 | Strong · 2 | Strong · 2 | Absent | Absent |
Frequently asked questions
RTX Corp leads with 46 patent records among the ranked applicants, ahead of General Electric Co (22) and Rolls-Royce PLC (20). United Technologies Corp (16) and Honeywell International Inc (8) round out the top five.
The top five filers account for 71% of the combined total across the hundred largest filers, indicating a highly concentrated field controlled by a small number of major aerospace OEMs.
The field is classified as Growth stage. The recent three-year filing window is well above the prior three-year window (47% higher), confirming multi-year expansion, though annual volume has eased from its 2023 peak of 20 filings. The most recent years are further understated by publication lag.
The United States leads with 63 patent records, followed by Europe (EPO) with 55. China holds 8 records, WIPO (PCT) 4, and Canada and Germany 3 each. The US and EPO together reflect the primary commercial aviation markets of the dominant OEMs.
RTX Corp, General Electric Co, Meggitt SA, and Pratt & Whitney Canada Corp all show new-entrant momentum in the most recent filing window, meaning they had no prior-window filings in the measured period. Rolls-Royce PLC shows a decline of 69% in recent filings relative to its prior window.
The most-cited work is titled ‘Method and system for modeling the performance of…’ with 94 citations. Other highly cited documents include work on MFCC and CELP methods to detect turbine engine faults (37 citations), machine-learned aero-thermodynamic engine inlet conditions (34 citations), and a Chinese-language study on remaining-life prediction via fault-feature transfer learning (38 citations).
Built on Patsnap Open Platform
This report’s underlying patent dataset — filings, assignees, technology clusters — is open for developers via MCP and REST API. Free to start, 10,000 credits, no credit card required.
Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries inherent limitations: recent filings (typically the most recent 18–24 months) are under-counted due to standard publication lag; counts may be reported at either a patent-family or a patent-record basis and are not always directly comparable; classification, applicant-name, and citation data may contain errors, duplicates, or omissions; and the underlying search query defines and constrains the scope shown. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, or validity search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. Any patent, commercial, or strategic decision should be verified independently and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.