Real-time vision-based estimation of sinter particle-size distribution for blast furnace burden control
- 20 November 2026
- journal article
- Published by SAGE Publications in Ironmaking & Steelmaking: Processes, Products and Applications
Abstract
Accurate measurement of particle-size distribution (PSD) in dense granular materials is challenging in industrial environments because particles are irregular, partially overlapping, and often observed under non-uniform illumination. Conventional laboratory methods, such as sieve analysis, provide reliable PSD measurements but are time-consuming and unsuitable for continuous monitoring in operating plants. This study presents a vision-based framework for the real-time estimation of sinter particle size distribution during blast furnace operation. Sinter PSD strongly influences burden permeability, gas flow, and overall furnace performance, making reliable monitoring essential for stable operation. The proposed approach employs high-resolution imaging with controlled multi-directional illumination to capture particle images under industrial conditions. Image-derived particle features are segmented and mapped to weight-based size distributions using a calibrated regression model, enabling non-intrusive, high-frequency PSD estimation. System performance is evaluated against laboratory sieve analysis as the reference method. Industrial validation demonstrates a mean absolute measurement error of ∼ 1.7%, with a maximum deviation of < 6% for particles larger than 5 mm. Continuous monitoring further revealed that increases in the fine particle fraction were detected prior to measurable changes in furnace performance, indicating the potential of the method for early identification of adverse granulometric trends. The results demonstrate that the proposed framework provides stable and repeatable PSD estimates under harsh industrial conditions and offers a practical approach for online granulometry of bulk particulate materials.This publication has 27 references indexed in Scilit:
- Vision based process monitoring in wire arc additive manufacturing (WAAM)Journal of Intelligent Manufacturing, 2024
- Online measurement method of FeO content in sinter based on infrared machine vision and convolutional neural networkMeasurement, 2022
- Machine learning and deep learning based predictive quality in manufacturing: a systematic reviewJournal of Intelligent Manufacturing, 2022
- Efficient image segmentation based on deep learning for mineral image classificationAdvanced Powder Technology, 2021
- Image-based size analysis of agglomerated and partially sintered particles via convolutional neural networksPowder Technology, 2020
- Real-time monitoring of particle size distribution in a continuous granulation and drying process by near infrared spectroscopyEuropean Journal of Pharmaceutics and Biopharmaceutics, 2019
- An image-based method for online measurement of the size distribution of iron green pellets using dual morphological reconstruction and circle-scanPowder Technology, 2019
- An industrial image processing-based approach for estimation of iron ore green pellet size distributionPowder Technology, 2016
- Estimation of particle size distribution on an industrial conveyor belt using image analysis and neural networksPowder Technology, 2014
- Influence of the material properties of iron ore sinter feed on granulation effectivenessPowder Technology, 1988