Scholarlink

<p>Accurately predicting the gas utilization rate (GUR), a crucial metric reflecting the operational status and energy consumption of a blast furnace (BF), is essential for optimizing production processes. In this study, we develop a hybrid prediction model for GUR by integrating a least squares support vector machine (LSSVM) and an artificial neural network (ANN), with the fuzzy C-means (FCM) algorithm employed to classify BF conditions. The results demonstrate that the FCM algorithm achieves remarkable precision in distinguishing stable and unstable operating states of the BF, attaining an impressive accuracy rate of 94.59 pct. Furthermore, the hybrid prediction model exhibits high accuracy in GUR predictions, yielding a mean absolute deviation (MAD) of 0.22, a mean squared error (MSE) of 0.18, a root mean square error (RMSE) of 0.43 and a correlation coefficient (<i>R</i><sup>2</sup>) value of 93.88 pct. These results underscore the accuracy and effectiveness of the proposed hybrid model in predicting GUR, highlighting its potential to enhance the operational efficiency and reliability of BF.</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

A Hybrid Prediction Model for Gas Utilization Rate Based on Blast Furnace Operating Conditions

  • 期刊论文

  • 发表日期：

    2025年3月14日

查看全文
  • Zhi-Heng Yu,
  • Xiao-Ming Li,
  • Bao-Rong Wang,
  • Yi-Ze Ren,
  • Xu-Hui Lin,
  • Xiang-Dong Xing

摘要

Accurately predicting the gas utilization rate (GUR), a crucial metric reflecting the operational status and energy consumption of a blast furnace (BF), is essential for optimizing production processes. In this study, we develop a hybrid prediction model for GUR by integrating a least squares support vector machine (LSSVM) and an artificial neural network (ANN), with the fuzzy C-means (FCM) algorithm employed to classify BF conditions. The results demonstrate that the FCM algorithm achieves remarkable precision in distinguishing stable and unstable operating states of the BF, attaining an impressive accuracy rate of 94.59 pct. Furthermore, the hybrid prediction model exhibits high accuracy in GUR predictions, yielding a mean absolute deviation (MAD) of 0.22, a mean squared error (MSE) of 0.18, a root mean square error (RMSE) of 0.43 and a correlation coefficient (R2) value of 93.88 pct. These results underscore the accuracy and effectiveness of the proposed hybrid model in predicting GUR, highlighting its potential to enhance the operational efficiency and reliability of BF.