Blast Furnace State Classification for Faster Smelting Diagnosis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Evaluating process parameters in smelting plants, particularly in blast furnaces, is complex and time-consuming, often leading to late detection of undesirable behaviors and difficulty in determining their causes, necessitating significant effort and experience.

Innovation Solution

A method and system utilizing machine-learned models that categorize blast furnace operating states based on a limited number of process parameters, such as gas flow, cooling capacity, and reducing agent consumption, enabling timely detection and response to process deterioration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If numerous process parameters are monitored and evaluated manually, then the characterization of smelting processes becomes more comprehensive, but the complexity and time consumption of evaluation increases significantly

Engineering Contradiction:
Improvecharacterization accuracyVSAvoidevaluation complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

A machine-learned model is introduced as an intermediary between the numerous process parameters and the operator. The model automatically evaluates multiple parameters simultaneously and provides simplified operating state assessments, eliminating the need for manual analysis of individual parameters while maintaining comprehensive characterization.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The manual mechanical evaluation process is replaced with an automated information processing system. The machine-learned model processes parameter data automatically, substituting the human operator's manual analysis with algorithm-based evaluation that is both comprehensive and efficient.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If individual process parameters are examined separately, then the monitoring process becomes simpler, but the detection of undesirable process behaviors is delayed

Engineering Contradiction:
Improvemonitoring simplicityVSAvoiddetection time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The machine-learned model merges the evaluation of multiple individual process parameters into a unified assessment of the overall operating state. By combining parameter analysis, the system maintains monitoring simplicity while enabling simultaneous detection of complex process behaviors that would be missed by individual parameter examination.

Inventive Principle:
Principle #5Merging (Combining)

3Measurement precision

If a multitude of parameter values are considered for process evaluation, then the accuracy of identifying process issues improves, but the effort and experience required to determine causes increases

Engineering Contradiction:
Improveissue identification accuracyVSAvoidcause determination automation
Core Design Contradiction:
Measurement precisionVSExtent of automation

Solution Approach 1:

The machine-learned model performs self-service by automatically determining the causes of process issues based on the pattern recognition capabilities embedded during training. The system autonomously analyzes parameter relationships and identifies root causes without requiring extensive human experience or manual effort, while maintaining high accuracy in issue identification.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4600378A1Characterization of a smelting process
Publication Date: 2025.08.13 PRIMETALS TECH AUSTRIA GMBH
  • EP4600378A1 patent drawingFigure 1
  • EP4600378A1 patent drawingFigure 2~3
  • EP4600378A1 patent drawingFigure 4~5

AI summary

The present invention relates to a method (100) and a system (10) for characterizing a smelting process in a blast furnace (3), a smelting plant (1), and methods (200; 300) for machine-learning models (16; 24) that can be used in such a method (100) and system (10). Parameter values (A, B, C, D, E) of a predetermined number of different process parameters are determined (S1) for the smelting process currently taking place in the blast furnace (3). Preferably, at least one of the process parameters represents gas flow through the blast furnace (3). A machine-learned model (16) assigns a blast furnace operating state (30) defined by the parameter values (A, B, C, D, E) to an operating category (X, Y, Z) (S2) on the basis of the determined parameter values (A, B, C, D, E).