Rolling Bearing Digital Twin Patent Landscape 2026
The rolling bearing digital twin space is a fast-growing but nascent field, still highly fragmented with no single dominant commercial actor — Siemens AG leads with 4 patent families, while the remaining activity is distributed across a broad set of Chinese universities and industrial players. Filing volume has expanded substantially on a multi-year basis, with China accounting for the overwhelming share of protected inventions, leaving meaningful geographic white space in other jurisdictions.
Fragmented field led by Siemens, with Chinese academia driving most activity
Siemens AG holds the top position with 4 patent families, making it the sole industrial incumbent with a measurable portfolio. The next tier consists entirely of Chinese universities, each holding 2 patent families, illustrating that academic institutions rather than industrial manufacturers currently set the pace of invention.
The top five filers account for 22% of the combined output of the hundred largest filers — an unusually low concentration figure that signals a fragmented, open competitive field. No single player has established a commanding position, and the gap between the leader and the pack is narrow.
| # | Applicant | Patent families | Share |
|---|---|---|---|
| 1 | Siemens AG | 4 | |
| 2 | Tianjin Polytechnic University | 2 | |
| 3 | Shandong Jianzhu University | 2 | |
| 4 | Suzhou University OF SCI & TECH | 2 | |
| 5 | Wuxi Xinjie Electrical Co., Ltd. | 2 | |
| 6 | HARBIN UNIV OF SCI & TECH | 2 | |
| 7 | HENAN UNIV OF SCI & TECH | 2 | |
| 8 | Xinjiang University | 2 | |
| 9 | SHANDONG UNIV OF SCI & TECH | 2 | |
| 10 | Chongqing University | 2 |
| # | Applicant | Patent families | Share |
|---|---|---|---|
| 11 | TECH & ENG CENT FOR SPACE UTILIZATION CHINESE ACAD… | 1 | |
| 12 | Qingdao Sino-German Institute of Intelligent Technology | 1 | |
| 13 | Nanjing Tech University | 1 | |
| 14 | Huaneng Power International Inc. Shanghai Shidongkou Power Plant | 1 | |
| 15 | Suzhou University | 1 | |
| 16 | Xi’an Jiaotong University | 1 | |
| 17 | Lanzhou University of Technology | 1 | |
| 18 | Chongqing Jiaotong University | 1 | |
| 19 | NANJING UNIV OF AERONAUTICS & ASTRONAUTICS | 1 | |
| 20 | Changshu Institute of Technology | 1 |
Siemens AG’s lead, though modest in absolute size, is notable because it is the only non-academic entity in the top tier. This positions Siemens as the primary commercial reference point for licensing or freedom-to-operate analysis, while the depth of academic activity suggests a rich prior-art base in AI-driven modeling and diagnostics.
The most recent 18–24 months of filing data are subject to publication lag and should be treated as an undercount; actual recent activity is likely higher than the visible figures suggest. Longer-window growth, applicant concentration, and technology-route coverage are therefore more reliable signals than the latest-year bar alone.
Multi-year growth is real, with AI and data-processing methods dominating the technology mix
Two structural features define this field: a clear upward trajectory in annual filings over the past several years, and a technology composition dominated by software and AI classification rather than mechanical bearing design.
Annual filing trend
Filings were negligible through 2019, then accelerated from 2020 onward, reaching a visible peak in 2023 before easing slightly. The 2025 and 2026 figures are understated due to publication lag and should not be read as a real decline — the field remains on a multi-year growth trajectory with a 150% increase in recent-period filings versus the prior comparable window.
↗ Hover for values · click a bar to ask EurekaTechnology composition
Electric digital data processing (G06F) and AI model computing (G06N) together account for the largest share of IPC classifications, followed closely by machine and structure testing (G01M) — confirming that digital twin research in this space is primarily concerned with predictive modeling and fault diagnosis rather than physical bearing design. The native mechanical class F16C (shafts, bearings, and couplings) appears in only 1 record, marking it as a clear gap relative to the dominant software branches.
↗ 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.
Method And Device For Predicting Service Life Of R…
Various embodiments of the teachings herein include a method for predicting service life of a rolling bearing. An example includes: acquiring a first vibration signal of a rolling bearing; extracting a time-domain feature of the first vibration signal, wherein the time-domain feature represents a degradation state of the rolling bearing; entering the… (excerpt from the patent abstract)
| # | Patent | Citations |
|---|---|---|
| 1 | 基于EEMD-MCNN-GRU的滚动轴承剩余使用寿命预测方法 | 69 |
| 2 | 一种基于动力学的滚动轴承数字孪生建模方法 | 58 |
| 3 | 基于隐马尔科夫模型和迁移学习的轴承寿命预测方法 | 54 |
| 4 | 一种基于数字孪生的滚动轴承建模与模型更新方法及系统 | 53 |
| 5 | 一种基于振动信号实时采集的滚动轴承工况量化分析方法 | 16 |
| 6 | 一种基于改进残差网络和WGAN的轴承剩余寿命预测方法 | 16 |
| 7 | 一种混合注意力机制下改进TCN的轴承寿命预测方法 | 15 |
| 8 | 一种滚动轴承剩余寿命预测方法及装置 | 14 |
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 low concentration, academic dominance, and geographic skew toward. China creates both risk and opportunity for industrial R&D teams evaluating entry or expansion in this space.
Early Growth — field is expanding but not yet crowded
The lifecycle stage is classified as Growth, driven by a 150% increase in recent three-year filings versus the prior three-year window. Annual volume has eased from its 2023 peak, but this reflects normal publication-lag distortion rather than a reversal. Teams entering now can still establish meaningful portfolio positions before consolidation occurs.
Growth stageLow concentration leaves room for new entrants
The top five filers hold only 22% of the combined output of the hundred largest filers, and the leader’s margin is just 2 patent families over the next tier. This means no single entity controls a blocking position. Industrial players and specialized startups have a realistic window to build differentiated portfolios in specific sub-domains such as real-time model updating or physics-informed twin architectures.
FragmentedMinimal co-filing; Siemens and Siemens China the only recorded pair
The only co-applicant relationship in evidence is between Siemens AG’s entities — specifically between the parent company and Siemens (China) Co. Ltd, with 1 co-filed family. No university-industry or cross-institution collaboration pairs are recorded. This absence of collaborative filings suggests the ecosystem has not yet matured into the kind of consortium activity typical of later-stage industrial AI fields.
Low collaborationChina-centric filings; Europe and US are largely uncovered
China accounts for 46 of the patent records, with Europe (EPO), WIPO (PCT), India, and the United States each holding only 1–2 records. This concentration means most inventions currently lack protection in major Western markets, creating both freedom-to-operate space and a first-mover opportunity for non-Chinese applicants seeking US, EP, or PCT coverage.
China-dominantGo 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 |
|---|---|---|
| Siemens AG | Siemens (China) Co., Ltd. | 1 |
Co-filing pairs, ranked by the number of jointly-filed patent families.
Siemens leads on diagnostics testing; Chinese universities anchor AI modeling routes
Siemens AG is the only industrial incumbent in the top tier and concentrates its portfolio on physical testing and machine-balance diagnostics. Chinese universities dominate the AI modeling and data-processing routes, each with modest but focused portfolios.
Siemens AG
Siemens AG holds 4 patent families — the largest single portfolio in this space — with technology focus concentrated entirely on G01M 13 (machine and structure testing), indicating a diagnostics-first approach to bearing digital twins. Applicant momentum is classified as a new entrant, meaning this portfolio was built recently, signaling a deliberate strategic move into the space rather than legacy accumulation.
patent families: 4Chongqing University
Chongqing University holds 2 patent families with a multi-branch technology focus spanning electric digital data processing (G06F 30 and G06F 119) and AI model computing (G06N 3), positioning it as a broad-spectrum academic contributor to twin modeling methodology. Like Siemens, it is classified as a new entrant by momentum, reflecting recent filing activity from a standing start.
patent families: 2| Applicant | Recent (3 yrs) | Trend |
|---|---|---|
| Siemens AG | 4 | ▲ new entrant |
| Chongqing University | 2 | ▲ new entrant |
| Suzhou University of Science and Technology | 2 | ▲ new entrant |
| Tianjin Polytechnic University | 1 | ▲ new entrant |
| Harbin University of Science and Technology | 1 | ▲ new entrant |
Under-served branches in data recognition, control systems, and native bearing mechanics
Four IPC branches show notably low patent record counts relative to the dominant AI and testing classes, suggesting areas where the prior-art base is sparse. These are observations of relative sparsity; technical and commercial value must be assessed independently.
F16C · Shafts, Bearings & Couplings — native mechanical design
Only 1 patent record falls under F16C, the class that directly covers bearing geometry, materials, and mechanical design. Given that a credible digital twin requires a high-fidelity physical model of the bearing itself, the near-absence of filings in this class is a structural gap. Teams combining physics-based bearing models with data-driven twin architectures could occupy largely unclaimed ground here.
Search this in Eureka →G05B · Control & Regulating Systems — closed-loop twin feedback
G05B, covering control and regulating systems, holds only 1 patent record, suggesting that work on using bearing digital twins to drive real-time closed-loop control (rather than purely diagnostic or predictive outputs) is almost entirely absent from the patent literature. This is technically adjacent and commercially relevant for autonomous machinery and smart manufacturing applications, representing a plausible entry path for control-systems specialists.
Search this in Eureka →How leaders differ by technology route across IPC branches
Route coverage across the main technology branches in the current evidence set.
| Player | G06N 3 · Computing based on AI models | G01M 13 · Testing machine & structure balance | G06F 30 · Electric digital data processing | G06F 119 · Electric digital data processing | G06F 18 · Electric digital data processing |
|---|---|---|---|---|---|
| Shandong Jianzhu University | Strong · 2 | Absent | Strong · 2 | Strong · 2 | Strong · 2 |
| Harbin University of Science and Technology | Strong · 2 | Absent | Moderate · 1 | Moderate · 1 | Strong · 2 |
| Chongqing University | Strong · 2 | Absent | Strong · 2 | Strong · 2 | Absent |
| Henan University of Science and Technology | Absent | Strong · 2 | Strong · 2 | Strong · 2 | Absent |
| Xinjiang University | Strong · 2 | Absent | Strong · 2 | Absent | Absent |
| CRRC Yongji Electric Co., Ltd. | Strong · 1 | Absent | Strong · 1 | Strong · 1 | Strong · 1 |
| Siemens AG | Absent | Strong · 4 | Absent | Absent | Absent |
Frequently asked questions
The evidence covers 51 patent families in scope across the rolling bearing digital twin field.
Siemens AG is the top filer with 4 patent families, making it the only industrial incumbent in the top tier. The next tier consists of Chinese universities each holding 2 patent families.
Yes. The field is in a Growth lifecycle stage, with a 150% increase in filings in the recent three-year window versus the prior comparable period. Annual volume has eased from its 2023 peak, but this is partly attributable to publication lag in the most recent years.
China dominates with 46 patent records. Europe (EPO) and WIPO (PCT) each hold 2 records, and India and the United States each hold 1 record, indicating the field is heavily skewed toward Chinese jurisdiction coverage.
Electric digital data processing (G06F) and AI model computing (G06N) are the most represented branches, followed by machine and structure testing (G01M). The native mechanical bearing class F16C appears in only 1 record, marking a clear technology gap.
Recorded co-filing activity is minimal. The only identified co-applicant pair is Siemens AG’s parent and Siemens (China) Co. Ltd, with 1 co-filed family. No cross-institution or university-industry collaborations are recorded in the evidence.
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.