Fastest
Eureka on the web
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →https://www.patsnap.com/resources/blog/rd-blog/blast-furnace-process-modelling-patent-landscape/ · Patsnap · data cut-off 2026-07-31 · downloaded from the live page
Patent Landscape · Ironmaking & Process ControlBlast Furnace Process Modelling Patents: A Small, Concentrated Field
- 23 records total, all of them attributed to just four ranked assignees — the entire ranked field, not a top-50 cut.
- Filing peaked at 10 in 2021, then fell to zero by 2024 — a -100% swing the evidence confirms, not a slowdown still in progress.
- Every record carries a G05B control class, and nearly half also carry G06N — this is a control-and-AI field, not a metallurgy-claims field.
23
Published Records
-100%
Filing Growth 2021→2024
EP
Leading Jurisdiction
2021
Peak Filing Year
Filing growth compares 2021 (10 records) with 2024 (0) — a three-year span. 2024 is the most recent year we treat as complete: publication lags filing by roughly 18 months, so 2025 onwards are still filling in and any growth rate that ends there would understate the field.
Published byPatsnap Research··7 min readSourced from Patsnap Eureka
Field Overview
What this patent set actually covers
Blast furnace process modelling patents in this dataset cluster around thermal state prediction, operating-instruction generation and heat balance calculation rather than furnace hardware itself. The search string pulls together model calibration, hot metal temperature, silicon content prediction and cohesive zone shape work — all software-adjacent claims sitting on top of an otherwise mechanical process. Every one of the 23 records in scope carries a G05B control-systems classification, which tells you where the claim language actually lives: control loops and inferred plant state, not the furnace shell.
The filing history is short and already past its peak. Activity built to 10 records in 2021 and has since fallen to zero by 2024, the last year the dataset can treat as complete — publication lag means 2025 and 2026 figures are still filling in and should not be read as a continued decline.
Filing activity by year, 2017-2026
Source: Patsnap Eureka. Assignee ranking and totals. Derived from a Patsnap search on Blast Furnace Process Modelling covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Let an AI agent run this analysis on your own technology
Pick a task. Every answer cites the patents behind it.
10,000 free credits to start
The Numbers
Filing trend and technology composition
Two views of the same 23 records: how filing activity moved year over year, and which IPC subclasses the claims actually sit in.
A sharp rise and an equally sharp drop
Filings rose to a peak of 10 in 2021 and dropped to 0 by 2024, a -100% move over that three-year span. With only 23 records total, a handful of filings from one or two assignees is enough to move the whole curve — treat this as a thin, event-driven history rather than a stable multi-year trend.
Control systems dominate, AI models are close behind
G05B (control and regulating systems) appears in 100.0% of the 23 records in scope — every filing here is, at some level, a control-systems claim. G06N (AI-based computing) follows at 47.8%, confirming that machine-learning components are now central to how thermal state and burden behaviour are claimed, well ahead of the classic C21B iron-production class at 13.0%.
Shares are the percentage of the 23 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Source: Patsnap Eureka. Filing trend and technology composition. Derived from a Patsnap search on Blast Furnace Process Modelling covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.
Go deeper on Blast Furnace Process Modelling with Eureka
This page is one run against one query. Ask Eureka your own question about blast furnace process modelling and every answer comes back with the patent numbers behind it.
Try EurekaKey Patents
The most-cited filings in this set
Representative Filing
Computer system and method providing operating instructions for thermal control of a blast furnace
PAUL WURTH S.A.
A computer system and method for training a reinforcement learning model to generate thermal-control operating instructions for a blast furnace. A domain adaptation model builds a domain-invariant dataset from historical multivariate time series across multiple furnaces; a transient model of a generic blast furnace process generates artificial operating data for a given thermal control action, and a generative deep learning network is used alongside it to produce control guidance.Filed by Paul Wurth S.A., published 2026-01-27 — the most recent grant in this set and the anchor for the most-cited family.
Highest-cited records
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | WO2022069498A1 | Computer system and method providing operating instructions for thermal control of a blast furnace | 30 |
| 2 | EA202390995A1 | КОМПЬЮТЕРНАЯ СИСТЕМА И СПОСОБ ОБЕСПЕЧЕНИЯ РАБОЧИХ ИНСТРУКЦИЙ ДЛЯ ТЕРМОРЕГУЛИРОВАНИЯ ДОМЕННОЙ ПЕЧИ | 9 |
| 3 | US20230130462A1 | Method and system for ironmaking plant optimization | 5 |
| 4 | IN202121047962A | Method and system for ironmaking plant optimization | 2 |
| 5 | LU102103B1 | Computer System and Method Providing Operating Instructions for Thermal Control of a Blast Furnace | 2 |
| 6 | EP4170441A1 | Method and system for ironmaking plant optimization | 1 |
| 7 | EP4222562A1 | Computer system and method providing operating instructions for thermal control of a blast furnace | 1 |
Citation counts here favour earlier-filed records within this small, recent corpus — read them as a signal of influence inside the set, not as a ranking of current technical importance.
Publication numbers are shown where the record carries one (7 of 7 rows); clicking a row searches Eureka by that number.
Source: Patsnap Eureka. Citation counts and representative records. Derived from a Patsnap search on Blast Furnace Process Modelling covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Run it yourself
Put your own technology through the same analysis
Where to run it
For builders
MCP server & REST API
When it has to run inside your own pipeline.
Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.
Browse MCP servers →Insights
What the numbers mean for a filing decision
The dataset is small enough that individual filings move the picture — read the following as directional signals, not statistical certainty.
Concentration
100.0% of 23 records
held by 4 ranked assignees
The entire ranked field sits with four companies
There is no long tail here: the top four ranked assignees account for all 23 records in scope. A new entrant is not competing against dozens of incumbents but against a small number of dense filing programmes, mostly built around thermal-control and operating-instruction claims.
Assignee ranking, 23 records
Filing momentum
-100% (2021→2024)
peak to last complete year
Activity has already cooled from its 2021 peak
Ten filings landed in 2021 alone; by 2024, the last year this dataset can treat as complete, that had fallen to zero. Because publication lags filing by around 18 months, 2025-2026 counts are still incomplete and should not be read as an ongoing collapse — but the 2021 spike itself was not sustained.
Filing trend, 2017-2026
Claim shape
G05B in 100.0% of records
of 23 records in scope
Control-systems language, not metallurgy language, dominates claims
Every record in this set carries a G05B classification, and 47.8% also carry G06N for AI-based computing. Classic ironmaking classification C21B appears in only 13.0% of records — the claim space here has moved toward software and inference layers sitting on top of the furnace, not the furnace process itself.
IPC composition, 23 records
Eureka AI Agent
Looking for what nobody has claimed yet?
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to blast furnace process modelling, with the prior art for and against each one.
Source: Patsnap Eureka. Co-assignee relationships and derived observations. Derived from a Patsnap search on Blast Furnace Process Modelling covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Who's Filing
The ranked assignees and where they are not filing
Four assignees make up the entire ranked field for this topic. None show filing activity in the latest year, consistent with the broader cooldown from the 2021 peak.
Leader
12 records
of 23 in scope
One assignee holds roughly half the field
The leading assignee accounts for 12 of the 23 records in this set, built substantially around the thermal-control and operating-instruction filings that also carry the highest citation counts. That concentration means a freedom-to-operate check in this space should start with this one portfolio before looking anywhere else.
Assignee ranking
Momentum
0 in latest year
across all 4 ranked assignees
No ranked assignee has an active filing in the most recent year
Every one of the four ranked assignees shows zero filings in the latest year tracked. Combined with the fall from the 2021 peak, this points to a field where the founding claims are largely staked out and current activity has paused, at least in what has published so far.
Recent-year momentum by assignee
Receiving offices
EPO leads with 6
of the tracked receiving offices
Filing is European- and India-weighted, not US-first
Europe (EPO) received the most filings (6), followed by India (4) and the United States (3), with smaller counts through Chile, Germany and the Eurasian Patent Office. A company planning where to file defensively should note that EPO and India carry more weight here than is typical for a control-software patent set.
Receiving office counts
Recent-year filing momentum by assignee
| Assignee | Recent year | YoY |
|---|---|---|
| Paul Wurth S.A. | 0 | — |
| Tata Consultancy Services Limited | 0 | — |
| JFE Steel Corporation | 0 | — |
| Kawasaki Steel Corporation | 0 | — |
Source: Patsnap Eureka. Assignee-level momentum. Derived from a Patsnap search on Blast Furnace Process Modelling covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
What's Next
Where to take this analysis
This landscape shows shape and concentration; deciding whether to file, license or design around a specific claim needs a closer look at individual documents.
Check freedom-to-operate against the leading portfolio
With one assignee holding 12 of 23 records, any new thermal-control or operating-instruction filing should be checked claim-by-claim against that portfolio first.
Run a claim comparison in Eureka →Watch for the 2025-2026 filing lag to resolve
The apparent drop to zero by 2024 is real in this dataset, but 2025-2026 counts are still incomplete due to publication lag and may revise upward.
Track new publications in Eureka →Scope drafting around the under-claimed branches
Cohesive zone shape, silicon content prediction and soft-sensor calibration show low classification counts relative to the search terms that surface them — worth a deeper prior-art check before drafting there.
Explore white space in Eureka →Source: Patsnap Eureka. Forward-looking reading of the same dataset. Derived from a Patsnap search on Blast Furnace Process Modelling covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
FAQ
Common questions about this patent set
Within this dataset, one assignee holds 12 of the 23 records in scope, roughly half the entire ranked field. Only four assignees appear in the ranking at all, and together they account for all 23 records — there is no long tail of smaller filers to track separately. Anyone assessing competitive position in this niche should treat that single leading portfolio as the primary reference point.
Filing peaked at 10 records in 2021 and had fallen to zero by 2024, the most recent year the dataset can treat as complete, which the evidence records as a -100% move over that span. Because patent publication typically lags filing by about 18 months, the 2025-2026 figures are still incomplete and should not be read as proof the field has gone quiet permanently. Based on what has published so far, though, the 2021 surge was not sustained into the following years.
Despite the ironmaking subject matter, every one of the 23 records carries a G05B control-and-regulating-systems classification, and 47.8% also carry a G06N AI-computing classification. Classic iron-production classification (C21B) appears in only 13.0% of records. In practice this means the claims are mostly about control loops, thermal-state inference and machine-learning models layered on furnace data, not the furnace process itself.
The European Patent Office received the most filings in this set at 6, followed by India at 4 and the United States at 3, with smaller counts through Chile, Germany and the Eurasian Patent Office. That distribution is more Europe- and India-weighted than is typical for control-software patenting, which usually skews toward the US and China, and is worth factoring into any regional filing strategy.
US12535782B2, assigned to Paul Wurth S.A. and published 2026-01-27, covers a computer system and method that trains a reinforcement learning model to generate thermal-control operating instructions for a blast furnace, using domain adaptation and a transient process model to generate synthetic training data across multiple furnaces. It is the most recent grant in this set and sits within the family behind the most-cited record, WO2022069498A1 (cited 30 times). Anyone building a reinforcement-learning or domain-adaptation approach to blast furnace thermal control should review its claims closely before finalising an architecture.
Answers are grounded in the same dataset. Derived from a Patsnap search on Blast Furnace Process Modelling covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Research Blast Furnace Process Modelling in depth with Eureka
Go past this page: query the whole blast furnace process modelling corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
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.
Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company's registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.