Scholarlink

<p>Predicting NO<sub><i>x</i></sub> in the sintering process of iron ore powder in advance was helpful to adjust the denitrification process in time. Taking NO<sub><i>x</i></sub> in the sintering process of iron ore powder as the object, the boxplot, empirical mode decomposition algorithm, Pearson correlation coefficient, maximum information coefficient and other methods were used to preprocess the sintering data and naive Bayes classification algorithm was used to identify the sintering conditions. The regression prediction model with high accuracy and good stability was selected as the sub-model for different sintering conditions, and the sub-models were combined into an integrated prediction model. Based on actual operational data, the approach proved the superiority and effectiveness of the developed model in predicting NO<sub><i>x</i></sub>, yielding an accuracy of 96.17% and an absolute error of 5.56, and thereby providing valuable foresight for on-site sintering operations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Identification of working conditions and prediction of NOx emissions in iron ore fines sintering process

  • 期刊论文

  • 发表日期：

    2025年5月24日

查看全文
  • Bao-rong Wang,
  • Xiao-ming Li,
  • Zhi-heng Yu,
  • Xu-hui Lin,
  • Yi-ze Ren,
  • Xiang-dong Xing

摘要

Predicting NOx in the sintering process of iron ore powder in advance was helpful to adjust the denitrification process in time. Taking NOx in the sintering process of iron ore powder as the object, the boxplot, empirical mode decomposition algorithm, Pearson correlation coefficient, maximum information coefficient and other methods were used to preprocess the sintering data and naive Bayes classification algorithm was used to identify the sintering conditions. The regression prediction model with high accuracy and good stability was selected as the sub-model for different sintering conditions, and the sub-models were combined into an integrated prediction model. Based on actual operational data, the approach proved the superiority and effectiveness of the developed model in predicting NOx, yielding an accuracy of 96.17% and an absolute error of 5.56, and thereby providing valuable foresight for on-site sintering operations.