High-Speed Rail AI/ML Patent Snapshot 2026
The High-Speed Rail AI/ML patent space is small and academically dominated, with 25 patent families on record and Chinese institutions holding 24 of the 25 filing jurisdictions. Annual volume has eased from a 2020 peak, and the field is fragmented at the top — no single applicant commands more than two patent records.
Chinese universities and rail research institutes lead a fragmented field
East. China Jiaotong University, China Academy of Railway Sciences Corporation Limited, Beihang University, and. China State Railway Group Co., Ltd. share the top rank, each holding 2 patent records — a clear sign that no single entity has established a commanding position in High-Speed Rail AI/ML.
The top five filers together account for 18% of the ranked applicants visible in this query’ combined total, indicating a highly distributed visible assignee structure with a shallow tier gap between leader and follower. The field invites entry, but also reflects limited consolidated R&D investment so far.
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 1 | East China Jiaotong University | 2 | |
| 2 | China Academy of Railway Sciences Corporation Limited | 2 | |
| 3 | Beihang University | 2 | |
| 4 | China State Railway Group Co., Ltd. | 2 | |
| 5 | Dr. M. M. Prasada Reddy | 1 | |
| 6 | Northeastern University China | 1 | |
| 7 | CHINA RAILWAY SIYUAN SURVEY & DESIGN GRP CO LTD | 1 | |
| 8 | Beijing Ruichi Guotie Intelligent Transport Systems Engineering Technology Co., Ltd. | 1 | |
| 9 | A. Thriveni, Mother Theresa Institute of Engineering & Technology | 1 | |
| 10 | Dr. S. J. Subhashini | 1 |
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 11 | Xi’an Jiaotong University | 1 | |
| 12 | A Ravindra Kumar, Kuppam Engineering College | 1 | |
| 13 | CHINA NAT SOFTWARE & SERVICE | 1 | |
| 14 | V. Gangadhar, Mother Theresa Institute of Engineering & Technology | 1 | |
| 15 | Southwest Jiaotong University | 1 | |
| 16 | Beijing Hua-Tie Information Technology Co., Ltd. | 1 | |
| 17 | China Electronics Corporation 6th Research Institute | 1 | |
| 18 | D. Selvapandian | 1 | |
| 19 | GUANGDONG POLYTECHNIC OF IND & COMMERCE | 1 | |
| 20 | ZHENGZHOU RAILWAY VOCATIONAL & TECH COLLEGE | 1 |
The leading positions held by universities and the national rail science academy suggest that foundational and applied research — rather than product commercialization — is still the primary driver of IP activity. Industrial players are present but have not yet pulled decisively ahead.
Filing data for the most recent 18–24 months is subject to publication lag and likely understates current activity; the apparent low counts for 2024–2026 should be interpreted with caution. Longer-window growth, applicant concentration, and technology-route coverage are therefore more reliable signals than the latest-year bar alone.
Activity peaked in 2020; AI computing models dominate the technology mix
The filing trend and IPC composition together show a field that has grown unevenly since 2018 and is technically concentrated in AI model computing, with several adjacent hardware and control branches still lightly covered.
Annual filing trend
Filings grew from 1 record in 2018 to a peak of 4 in 2020, then softened through 2021–2023. The spike to 11 records in 2025 should be read cautiously given publication lag; the underlying trend from verified years points to a field that has eased from its 2020 peak rather than sustained growth.
↗ Hover for values · click a bar to ask EurekaTechnology composition
G06N (Computing based on AI models) is overwhelmingly visible, appearing in 24 of the patent records. G06F (Electric digital data processing) and G01M (Testing machine and structure balance) are secondary clusters. Operational branches such as B61L (Railway traffic control) and G05B (Control and regulating systems) are sparsely populated, pointing to a gap between algorithmic research and deployed control-system applications.
↗ 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.
High-speed train speed predictive control using an…
HIGH-SPEED TRAIN SPEED PREDICTIVE CONTROL USING ANFIS MODELING AND MACHINE LEARNING, DEEP LEARNING ABSTRACT My Invention is “HIGH-SPEED TRAIN SPEED PREDICTIVE CONTROL USING ANFIS MODELING AND MACHINE LEARNING, DEEP LEARNING ”A generalized predictive control method of high-speed train, the method is based ANFIS model and Machine learning (ML) train operation… (excerpt from the patent abstract)
Open this patent in Eureka →| # | Patent | Citations |
|---|---|---|
| 1 | 一种基于车载和云端的列车故障诊断系统及方法 | 57 |
| 2 | 高铁行车设备故障诊断方法及装置 | 25 |
| 3 | 基于混合深度学习的高铁道岔故障诊断方法 | 19 |
| 4 | 基于BP神经网络的动车组客室空调故障识别与预警方法 | 16 |
| 5 | 高铁动车智能运维管理系统 | 15 |
| 6 | 基于嵌入区分性的条件对抗域自适应的轴承故障诊断方法 | 14 |
| 7 | High-speed train speed predictive control using an… | 13 |
| 8 | High-speed train speed predictive control using an… | 7 |
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.
Assignee snapshot from the current evidence set
The applicants below are visible in this query result. Because the evidence set is relatively small, read this section as a directional snapshot rather than a full competitive ranking.
East China Jiaotong University
Holding 2 patent records, East China Jiaotong University focuses on G06N (AI model computing), G01M (testing and structure balance), and G06F (digital data processing) — a profile oriented toward fault detection and predictive diagnostics for rail systems. No applicant momentum data is available for trend trajectory. As a specialist rail-sector university, its research pipeline likely feeds directly into China’s national railway operators.
patent records: 2Beihang University
Also holding 2 patent records, Beihang University is differentiated by its concentration in G01H (vibration and sound measurement), G01M (structure testing), and G06K (data recognition) — making it the most sensor- and signal-processing-oriented applicant among the leaders. This positions Beihang as the applicant closest to physical measurement and condition monitoring, complementary to the algorithm-heavy focus of other top filers. No momentum trend data is available.
patent records: 2Frequently asked questions
The corpus in scope contains 25 patent families. This is a small body of IP, reflecting that the intersection of high-speed rail operations and AI/ML methods is still an emerging research area rather than a mature commercial technology domain.
Four organizations are tied at the top with 2 patent records each: East China Jiaotong University, China Academy of Railway Sciences Corporation Limited, Beihang University, and China State Railway Group Co., Ltd. No single entity has established a visible portfolio.
Annual filings grew from 1 record in 2018 to a peak of 4 in 2020, then eased through 2021–2023. A spike of 11 records is recorded for 2025, but this figure is likely undercounted due to publication lag and should not be treated as a confirmed peak.
G06N (Computing based on AI models) is the visible branch, appearing in 24 patent records. G06F (Electric digital data processing) and G01M (Testing machine and structure balance) are secondary. Operational rail branches such as B61L (Railway traffic control) and G05B (Control and regulating systems) are sparsely covered.
China accounts for 24 of the 25 jurisdiction-level filing records. India is the only other jurisdiction with recorded filings, contributing 3 records. No protection has been sought in the US, EU, Japan, or Korea based on the current evidence.
The most-cited work in the corpus focuses on train fault diagnosis systems combining onboard and cloud-based AI, with citation counts of 57 and 25 respectively. Additional highly cited patents address railway switch fault diagnosis using deep learning and air-conditioning fault detection via BP neural networks on high-speed trains.
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.