Study on Sintered Ore Production Process Modeling and Dynamic Optimization Driven by Multi-Algorithm Integration

Kanghao Li; Jia Wang; Chenbo Wang; Jiayu Li; Puxuan Zhao; Yifan Li

doi:10.54097/czns3967

Authors

Kanghao Li
Jia Wang
Chenbo Wang
Jiayu Li
Puxuan Zhao
Yifan Li

DOI:

https://doi.org/10.54097/czns3967

Keywords:

Sintered Ore Process, XGBoost, t-SNE Dimensionality Reduction, KNN-TOPSIS, Intelligent Optimization

Abstract

To address the challenges of complex coupling of process parameters and limited accuracy of traditional predictive models in sintered ore production, this study proposes an intelligent optimization system framework integrating multiple algorithms. First, through data governance and feature engineering, the XGBoost gradient boosting tree algorithm is used to extract key process features and establish a nonlinear correlation model. Second, t-SNE high-dimensional data dimensionality reduction technology is introduced to enable visual diagnosis and anomaly detection of the sintering process patterns. Finally, the KNN clustering algorithm is innovatively integrated with the TOPSIS multi-objective evaluation model to construct a dynamic grading and preferential decision-making framework for process plans. Experimental analysis shows that this system can significantly enhance the stability and energy efficiency of the production process, providing technical support for the intelligent transformation of the steel industry.

Downloads

Download data is not yet available.

References

[1] Xiang, X. P., Liu, W. Y., Zhu, M. F., et al. (2021). Research on sintering process optimization based on quality improvement and consumption reduction. Sintering and Pelletizing, 46(05), 35-40. DOI: 10.13403/j.sjqt.2021.05.067.

[2] Chen, F. S., Yuan, Y. Q., Kang, H. Y., et al. (2024). Development status and prospect of flue gas circulation sintering process under the current situation. China Metallurgy, 1-17.

[3] Cheng, Z. M., Ning, W. X., Pan, W., et al. (2019). Research and application of ultra-thick layer homogeneous sintering technology. Sintering and Pelletizing, 44(04), 7-12.

[4] Li, L. F., Zhang, S. H., Lyu, Q., et al. (2013). Research status and prospect of sintering ore blending. Journal of Iron and Steel Research, 25(09), 1-5. DOI:10.13228/j.boyuan.issn1001-0963. 2013. 09.009.

[5] Shan, C. D., Zhang, J. L., Liu, Z. J., et al. (2022). Research progress on assimilation of iron ore powder for sintering. China Metallurgy, 32(12), 1-6, 24.

[6] Yang, S. P., Sun, H. X., Zhang, T. T., et al. (2023). Study on high temperature basic characteristics and optimization of sintering blending for low silica iron ore. Journal of Iron and Steel Research, 35(06), 659-670.

[7] Wang, Y. S., Tan, S. Y., Liu, W. J., et al. (2025). Prediction of dust pollutant concentration based on variable weight combination. Journal of Arid Land Resources and Environment, 39 (03),152-162.DOI:10.13448/j. cnki. jalre. 2025. 052.

[8] Li, Z. S., & Liu, Z. G. (2019). Feature selection algorithm based on XGBoost. Journal on Communications, 40(10), 101-108.

[9] Chen, Z. Y., Liu, J. B., Li, C., et al. (2020). Ultra-short-term power load forecasting based on combined LSTM and XGBoost model. Power System Technology, 44(02), 614-620. DOI:10. 13335/j.1000-3673.pst.2019.1566.

[10] Wang, K. J., Xiang, Z. W., Tian, S. C., et al. (2024). Risk evaluation model of coal mine safety based on t-SNE data dimensionality reduction. Energy Technology and Management, 49(02), 146-149.

[11] MAY, ZHANGJ, LIQ, etal.Intelligent recommendation framework for iron ore matching based on SA2PSO and machine learning to reduce CO2 emissions[J]. Journal of Mate- rials, 2024, 76(1): 120.

[12] DANIELF,RAMONM,INIGOR,etal.Optimization of sinter plant operating conditions using advanced multivariate statistics: intelligent data processing[J].JOM, 2016,68 (8): 2089.

[13] KUMARV,SAIRAMS,KUMARS ,etal.Prediction of iron ore sinter properties using statistical technique[J].Trans- actions of the Indian Institute of Metals,2017,70(6):1661.

[14] HUANGX,FANX,CHENX,etal.A novel blending principle and optimization model for low-carbon and low-cost sintering in ironmaking process[J].Powder Technology,2019, 355: 629.

[15] LIUY,LIX,GAOD.The optimization of parameters for controlling iron ore sintering process based on maximum satis- faction[J].Journal of Physics:Conference Series,2019,1345 (2):32 .

[16] LIUS,ZHAOY,LIX,etal.An online sintering batching system based on machine learning and intelligent algorithm[J].ISIJ International,2021,61(8):2237.

[17] CHANGJ,SUB ,ZHANGJ ,etal.Application of simulated annealing algorithm in sintering burdening optimization[J]. Advances in Metallurgical and Mining Engineering, 2021, 402(1):116.