Sintered Ore FeO Prediction for Real-Time Blending Ratio Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting the FeO content of sintered ore are inaccurate and require time-consuming sampling tests, leading to delayed corrective actions, which affect the quality and operation of blast furnaces.
Innovation Solution
A sintered ore production device and method using a machine learning model to predict the FeO content of sintered ore in real-time, incorporating operational data from a sintered ore production facility to calculate and adjust the agglomerating material blending ratio, ensuring the FeO content remains within a target range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional chemical analysis is used to measure FeO content, then measurement accuracy is achieved, but measurement time becomes too long causing delayed corrective actions
Solution Approach 1:
The patent replaces the conventional chemical analysis system with a machine learning-based prediction system that uses operational data (exhaust gas composition, temperature, material blending ratios) to predict FeO content. This substitution eliminates the need for time-consuming chemical laboratory analysis while providing timely predictions for process control.
Solution Approach 2:
The machine learning model predicts FeO content in advance based on current operational parameters before the actual sintering process completes. This preliminary prediction enables operators to take corrective actions proactively rather than waiting for post-process chemical analysis results.
2Manufacturing precision
If FeO content is controlled within target range, then sintered ore quality is improved, but operational complexity increases due to continuous monitoring and adjustment requirements
Solution Approach 1:
The patent implements a feedback control system where the machine learning model continuously predicts FeO content based on real-time operational data, and the system automatically adjusts the agglomerating material blending ratio to maintain FeO content within the target range. This closed-loop feedback mechanism ensures consistent sintered ore quality while automating the control process.
Solution Approach 2:
The machine learning model serves as an automated decision-support system that independently analyzes operational data and recommends or automatically implements control adjustments. This self-service capability reduces the need for manual intervention and complex operational procedures while maintaining high manufacturing precision.
3Productivity
If machine learning model is implemented for real-time prediction, then productivity is improved through faster decision-making, but device complexity increases due to data processing requirements
Solution Approach 1:
The machine learning model serves multiple functions: it predicts FeO content, identifies optimal agglomerating material blending ratios, and provides process optimization recommendations. By consolidating these multiple functions into a single integrated system, the patent improves productivity without proportionally increasing device complexity.
Solution Approach 2:
The patent uses existing operational data (exhaust gas composition, temperature, material ratios) as intermediary inputs for the machine learning model. These readily available data serve as mediators that bridge the gap between process control systems and quality prediction, enabling real-time decision-making without requiring complex additional sensing or measurement infrastructure.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A sintered ore production device (10) includes an acquisition interface (12) configured to acquire data on operational conditions in a sintered ore production facility as input data, an FeO content of sintered ore predictor (13) configured to predict an FeO content of sintered ore after a predetermined time based on the acquired input data, a control amount calculator (14) configured to calculate a control amount of an agglomerating material blending ratio based on the predicted FeO content of sintered ore and a predetermined target range of the FeO content of sintered ore, and an output interface (15) configured to output the calculated control amount to another production facility or present the calculated control amount as a guidance control amount.