Cite this article as:

Zhen Zhang, Jue Tang, Quan Shi, Mansheng Chu, Wang Mingyu, and Zhifeng Zhang, Comprehensive status evaluation and prediction of blast furnace based on cascade system and combined model, Int. J. Miner. Metall. Mater.,(2025). https://dx.doi.org/10.1007/s12613-025-3179-6
Zhen Zhang, Jue Tang, Quan Shi, Mansheng Chu, Wang Mingyu, and Zhifeng Zhang, Comprehensive status evaluation and prediction of blast furnace based on cascade system and combined model, Int. J. Miner. Metall. Mater.,(2025). https://dx.doi.org/10.1007/s12613-025-3179-6
引用本文 PDF XML SpringerLink

Comprehensive status evaluation and prediction of blast furnace based on cascade system and combined model

Abstract: The comprehensive status of the blast furnace was one of the most important factors affecting economy, quality, and longevity. The blast furnace comprehensive status had the nature of "black box", and it was "unpredictable." In this study, a blast furnace comprehensive status score and prediction method based on a cascade system and combined model was proposed to solve this issue. Based on the blast furnace parameter characteristics, a dual cascade evaluation system of AHP-CV-EWM-ICG was constructed by integrating subjective and objective assignment methods. The categorized status (raw material, gas flow, furnace body, furnace cylinder, and Iron-slag) was realized. Based on the 5 categories of status data, the second cascade was applied to upgrade the quantitative evaluation of the comprehensive status. The weights of the different categories were 0.22, 0.15, 0.22, 0.21, and 0.20, respectively. According to the data analysis, the result of the comprehensive status score closely matched the on-site production logs. Based on the blast furnace smelting period, the MIC method was applied to the 100 parameters most relevant to the comprehensive status. A combined prediction model for the comprehensive status score was designed by applying BiLSTM and CatBoost. The test results indicated that the combined model reduced the MAE by an average of 0.275 and increased the hit rate by an average of 5.65% compared to BiLSTM or CatBoost alone. When the error range was ±2.5, the combined model predicted a hit rate of 91.66% for the next hour's comprehensive status score, and its high accuracy was deemed satisfactory for the field. SHAP and regression fitting were applied to analyze the linear quantitative relationship between the key variables and comprehensive status score. When the furnace bottom center temperature increased by 10°C, the comprehensive status score increased by 0.44. This method contributed to more precise management and control of the blast furnace's comprehensive status on-site.

 

/

返回文章
返回