Scholarlink

<p>Accurate forecasting of blast furnace gas (BFG) production is an essential prerequisite for reasonable energy scheduling and management to reduce carbon emissions. Coupling forecasting between BFG generation and consumption dynamics was taken as the research object. A multi-task learning (MTL) method for BFG forecasting was proposed, which integrated a coupling correlation coefficient (CCC) and an inverted transformer structure. The CCC method could enhance key information extraction by establishing relationships between multiple prediction targets and relevant factors, while MTL effectively captured the inherent correlations between BFG generation and consumption. Finally, a real-world case study was conducted to compare the proposed model with four benchmark models. Results indicated significant reductions in average mean absolute percentage error by 33.37%, achieving 1.92%, with a computational time of 76&#xa0;s. The sensitivity analysis of hyperparameters such as learning rate, batch size, and units of the long short-term memory layer highlights the importance of hyperparameter tuning.</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 multi-task learning method for blast furnace gas forecasting based on coupling correlation analysis and inverted transformer

  • 期刊论文

  • 发表日期：

    2025年9月30日

查看全文
  • Sheng Xie,
  • Jing-shu Zhang,
  • Da-tao Shi,
  • Yang Guo,
  • Qi Zhang

摘要

Accurate forecasting of blast furnace gas (BFG) production is an essential prerequisite for reasonable energy scheduling and management to reduce carbon emissions. Coupling forecasting between BFG generation and consumption dynamics was taken as the research object. A multi-task learning (MTL) method for BFG forecasting was proposed, which integrated a coupling correlation coefficient (CCC) and an inverted transformer structure. The CCC method could enhance key information extraction by establishing relationships between multiple prediction targets and relevant factors, while MTL effectively captured the inherent correlations between BFG generation and consumption. Finally, a real-world case study was conducted to compare the proposed model with four benchmark models. Results indicated significant reductions in average mean absolute percentage error by 33.37%, achieving 1.92%, with a computational time of 76 s. The sensitivity analysis of hyperparameters such as learning rate, batch size, and units of the long short-term memory layer highlights the importance of hyperparameter tuning.