High-precision online correction of pellet size distribution under stacking conditions: An ARNN model enhanced by GAN-GVMD and attention mechanism

IF 5.5 2区工程技术 Q2 ENGINEERING, CHEMICAL

Powder Technology Pub Date : 2026-04-15 Epub Date: 2026-01-24 DOI:10.1016/j.powtec.2026.122170

Weiwen Lu , Shuang Lin , Shihua Shao , Kangkang Tan , Liangjun Chen , Hongming Long , Zhengwei Yu

{"title":"High-precision online correction of pellet size distribution under stacking conditions: An ARNN model enhanced by GAN-GVMD and attention mechanism","authors":"Weiwen Lu , Shuang Lin , Shihua Shao , Kangkang Tan , Liangjun Chen , Hongming Long , Zhengwei Yu","doi":"10.1016/j.powtec.2026.122170","DOIUrl":null,"url":null,"abstract":"<div><div>The pellet size distribution, as a critical factor affecting blast furnace permeability, reduction reaction kinetics, and hot metal quality. Its high-precision online identification is essential for optimizing pelletizing parameters, improving pellet quality, and sustaining the stable and efficient operation of the blast furnace. In practical applications, machine vision-based pellet size identification is vulnerable to particle segregation, material stacking, and imaging distortions, which cause substantial discrepancies between the surface and true bulk size distributions and ultimately hinder its engineering applicability and large-scale industrial adoption. To address these issues, this study proposes a fused GAN_GVMD_ARNN integrated neural network model to correct the pellet size distribution data obtained from machine vision. After correction, 88% of the samples exhibit a deviation within ±2% between the image-based size composition and the results of sieve analysis. The experimental results demonstrate that the proposed model can effectively enhance the accuracy of pellet size distribution detection and significantly reduce measurement errors, providing a new technical pathway for image-based granulometric analysis.</div></div>","PeriodicalId":407,"journal":{"name":"Powder Technology","volume":"473 ","pages":"Article 122170"},"PeriodicalIF":5.5000,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Powder Technology","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0032591026000586","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2026/1/24 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}

引用次数: 0

Abstract

The pellet size distribution, as a critical factor affecting blast furnace permeability, reduction reaction kinetics, and hot metal quality. Its high-precision online identification is essential for optimizing pelletizing parameters, improving pellet quality, and sustaining the stable and efficient operation of the blast furnace. In practical applications, machine vision-based pellet size identification is vulnerable to particle segregation, material stacking, and imaging distortions, which cause substantial discrepancies between the surface and true bulk size distributions and ultimately hinder its engineering applicability and large-scale industrial adoption. To address these issues, this study proposes a fused GAN_GVMD_ARNN integrated neural network model to correct the pellet size distribution data obtained from machine vision. After correction, 88% of the samples exhibit a deviation within ±2% between the image-based size composition and the results of sieve analysis. The experimental results demonstrate that the proposed model can effectively enhance the accuracy of pellet size distribution detection and significantly reduce measurement errors, providing a new technical pathway for image-based granulometric analysis.

Abstract Image

查看原文本刊更多论文

堆积条件下颗粒粒径分布的高精度在线校正：GAN-GVMD和注意机制增强的ARNN模型

球团粒度分布是影响高炉透气性、还原反应动力学和铁水质量的关键因素。它的高精度在线识别对于优化球团参数、提高球团质量、保持高炉稳定高效运行至关重要。在实际应用中，基于机器视觉的颗粒尺寸识别容易受到颗粒偏析、材料堆积和成像畸变的影响，这导致表面和真实颗粒尺寸分布之间存在重大差异，最终阻碍了其工程适用性和大规模工业应用。为了解决这些问题，本研究提出了一种融合GAN_GVMD_ARNN集成神经网络模型，对机器视觉获得的颗粒粒度分布数据进行校正。经过校正，88%的样品在图像粒度组成和筛析结果之间的偏差在±2%以内。实验结果表明，该模型能有效提高颗粒粒度分布检测的精度，显著降低测量误差，为基于图像的粒度分析提供了新的技术途径。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Powder Technology 工程技术-工程：化工

CiteScore

9.90

自引率

15.40%

发文量

1047

审稿时长

46 days

期刊介绍： Powder Technology is an International Journal on the Science and Technology of Wet and Dry Particulate Systems. Powder Technology publishes papers on all aspects of the formation of particles and their characterisation and on the study of systems containing particulate solids. No limitation is imposed on the size of the particles, which may range from nanometre scale, as in pigments or aerosols, to that of mined or quarried materials. The following list of topics is not intended to be comprehensive, but rather to indicate typical subjects which fall within the scope of the journal's interests: Formation and synthesis of particles by precipitation and other methods. Modification of particles by agglomeration, coating, comminution and attrition. Characterisation of the size, shape, surface area, pore structure and strength of particles and agglomerates (including the origins and effects of inter particle forces). Packing, failure, flow and permeability of assemblies of particles. Particle-particle interactions and suspension rheology. Handling and processing operations such as slurry flow, fluidization, pneumatic conveying. Interactions between particles and their environment, including delivery of particulate products to the body. Applications of particle technology in production of pharmaceuticals, chemicals, foods, pigments, structural, and functional materials and in environmental and energy related matters. For materials-oriented contributions we are looking for articles revealing the effect of particle/powder characteristics (size, morphology and composition, in that order) on material performance or functionality and, ideally, comparison to any industrial standard.