Li-Ion Battery AI/ML Patent Snapshot 2026
The application of AI and machine learning to lithium-ion batteries is an early-stage, fragmented field dominated by academic and research institutions, with no single commercial player holding a commanding position. Activity has grown sharply since 2021, with India and the United States as the principal filing jurisdictions and battery-state estimation as the clear technical focus.
Fragmented field led by academic institutions, with Hong Kong Metropolitan University at the top
Hong Kong Metropolitan University leads the ranking with 3 patent records, followed by a cluster of seven organizations — Carnegie Mellon University, Beijing Institute of Technology, Chang Gung University, Vellore Institute of Technology, SciBot Technology LLC, Michigan Technological University, and Mahindra & Mahindra — each with 2 patent records. The ranking is populated almost entirely by universities and research foundations.
The top five filers account for 27% of the ranked applicants visible in this query’ combined total, indicating a notably low concentration: no single entity has established a visible position, and the gap between the leader and the second tier is minimal.
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 1 | Hong Kong Metropolitan University | 3 | |
| 2 | Carnegie Mellon University | 2 | |
| 3 | Beijing Institute of Technology | 2 | |
| 4 | Chang Gung University | 2 | |
| 5 | Vellore Institute of Technology | 2 | |
| 6 | SciBot Technology LLC | 2 | |
| 7 | Michigan Technological University | 2 | |
| 8 | MAHINDRA & MAHINDRA LTD | 2 | |
| 9 | Koneru Lakshmaiah Education Foundation | 1 | |
| 10 | Smartkosh Tech Pte Ltd | 1 |
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 11 | Sadhu Renuka (AITS EEE Dept.) | 1 | |
| 12 | Purdue Research Foundation | 1 | |
| 13 | Kalinga Institute of Industrial Technology (KIIT Deemed University) | 1 | |
| 14 | University of South Carolina | 1 | |
| 15 | Dr. K. Sudarsan (PVKK Institute of Technology EEE Dept.) | 1 | |
| 16 | Emuron Tech Pvt Ltd | 1 | |
| 17 | Bingimalla N. Prasad (AITS EEE Dept.) | 1 | |
| 18 | National Institute of Technology | 1 | |
| 19 | Mondragon Goi Eskola Politeknikoa Jose Maria Arizmendiarrieta | 1 | |
| 20 | RMD Engineering College | 1 |
The academic dominance of the leaderboard suggests the technology is still in a pre-commercialization phase. Industrial entrants such as Mahindra & Mahindra and SciBot Technology LLC represent early commercial interest, but the overall roster signals that foundational research, not product-driven IP accumulation, is the primary activity.
The most recent 18–24 months of filing data are subject to publication lag and likely undercount actual activity; the true pace of growth is therefore higher than the visible record suggests. Longer-window growth, applicant concentration, and technology-route coverage are therefore more reliable signals than the latest-year bar alone.
Sharp growth since 2021, with battery measurement and AI computing as the dominant technology branches
The annual filing trend reveals a field that was essentially inactive before 2021 and has since entered a growth phase. The technology composition chart shows that measurement and diagnostics applications of AI/ML predominate, with direct battery-cell and EV-propulsion coverage as secondary branches.
Annual filing trend
Filings were zero from 2017 through 2020, then jumped in 2021 and have remained elevated. The recent-window growth rate of 183% confirms a genuine expansion phase. Data for 2025 and 2026 are incomplete due to publication lag and should be read as floors, not totals.
↗ Hover for values · click a bar to ask EurekaTechnology composition
G01R (electric and magnetic measurement) is the visible branch, reflecting the field’s concentration on battery-state estimation and diagnostics. G06N (AI model computing) and H01M (batteries and cells) form the next tier. Branches such as B60L (EV propulsion), H02J (power supply and grid), and G05B (control systems) each account for a small share, marking them as adjacent areas with limited current coverage.
↗ 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.
Artificial intelligence (AI)-based charging curve …
An artificial intelligence (AI)-based charging curve reconstruction and state estimation method for a lithium-ion battery is provided to estimate various states of a battery. In the method, a complete charging curve is reconstructed through deep learning with charging data segments as input. Then, a plurality of states of the battery can be extracted from… (excerpt from the patent abstract)
| # | Patent | Citations |
|---|---|---|
| 1 | System and method for estimation of battery state … | 42 |
| 2 | Simulating battery dynamics with equivalent circui… | 8 |
| 3 | 基于人工智能的锂离子电池充电曲线重构及状态估计方法 | 6 |
| 4 | Method for estimation of state of charge and state… | 4 |
| 5 | Lebesgue sampling-based deep belief network for li… | 4 |
| 6 | Self-adaptive lithium-ion battery method using kno… | 3 |
| 7 | Artificial intelligence (AI)-based charging curve … | 2 |
| 8 | An advanced and efficent system to manage lithium-… | 1 |
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.
Hong Kong Metropolitan University
The current record-count leader with 3 patent records, all filed as a new entrant in the recent window. Its technical focus spans G01R 31 (electric and magnetic measurement) and G06N 3 (neural-network AI models), covering the core battery-state estimation problem. As a new entrant with the top position, its trajectory is upward but its base remains small.
patent records: 3Michigan Technological University & SciBot Technology LLC
Michigan Technological University (2 patent records) and SciBot Technology LLC (2 patent records) are new entrants who have co-filed, making them the only confirmed university–industry collaboration in the dataset. Both focus on G05B 13 (control and regulating systems) and G06N 3 (AI models), differentiating them from the measurement-focused majority. This pairing represents the most direct route from academic research to commercial application currently visible in the landscape.
patent records: 2 eachFrequently asked questions
The current corpus contains 31 patent families. The field only began generating filings in 2021, so the body of prior art is still small relative to more established battery-technology domains.
Hong Kong Metropolitan University leads with 3 patent records. Seven other organizations — including Carnegie Mellon University, Beijing Institute of Technology, Michigan Technological University, and Mahindra & Mahindra — are tied at 2 patent records each.
India accounts for the largest number of patent records, followed by the United States. Australia, Taiwan, WIPO (PCT), and South Korea each have a smaller number of records. The geographic footprint is currently narrow, suggesting most applicants have not pursued broad international protection.
G01R (electric and magnetic measurement) is the leading IPC branch, reflecting a concentration on AI/ML-based battery-state estimation — including state of charge, state of health, and remaining useful life. G06N (AI computing models) and H01M (batteries and cells) are the next most common branches.
Yes. Michigan Technological University and SciBot Technology LLC have co-filed 2 patent records together, making them the only confirmed co-filing pair in the dataset. Their shared focus is on G05B (control and regulating systems) and G06N (AI models), which is distinct from the measurement-focused majority.
The most-cited work in the corpus is a patent on system and method for battery state estimation, with 42 citations. The second and third most-cited works address equivalent-circuit battery simulation (8 citations) and an AI-based lithium-ion battery charging curve reconstruction and state estimation method (6 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.