Scholarlink

<p>To address the challenge of identifying the primary causes of energy consumption fluctuations and accurately assessing the influence of various factors in the converter unit of an iron and steel plant, the focus is placed on the critical components of material and heat balance. Through a thorough analysis of the interactions between various components and energy consumptions, six pivotal factors have been identified—raw material composition, steel type, steel temperature, slag temperature, recycling practices, and operational parameters. Utilizing a framework based on an equivalent energy consumption model, an integrated intelligent diagnostic model has been developed that encapsulates these factors, providing a comprehensive assessment tool for converter energy consumption. Employing the K-means clustering algorithm, historical operational data from the converter have been meticulously analyzed to determine baseline values for essential variables such as energy consumption and recovery rates. Building upon this data-driven foundation, an innovative online system for the intelligent diagnosis of converter energy consumption has been crafted and implemented, enhancing the precision and efficiency of energy management. Upon implementation with energy consumption data at a steel plant in 2023, the diagnostic analysis performed by the system exposed significant variations in energy usage across different converter units. The analysis revealed that the most significant factor influencing the variation in energy consumption for both furnaces was the steel grade, with contributions of −0.550 and 0.379.</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

Multifactor diagnostic model of converter energy consumption based on K-means algorithm and its application

  • 期刊论文

  • 发表日期：

    2025年5月24日

查看全文
  • Fei-xiang Dai,
  • Guang Chen,
  • Xiang-jun Bao,
  • Gong-guo Liu,
  • Lu Zhang,
  • Xiao-jing Yang

摘要

To address the challenge of identifying the primary causes of energy consumption fluctuations and accurately assessing the influence of various factors in the converter unit of an iron and steel plant, the focus is placed on the critical components of material and heat balance. Through a thorough analysis of the interactions between various components and energy consumptions, six pivotal factors have been identified—raw material composition, steel type, steel temperature, slag temperature, recycling practices, and operational parameters. Utilizing a framework based on an equivalent energy consumption model, an integrated intelligent diagnostic model has been developed that encapsulates these factors, providing a comprehensive assessment tool for converter energy consumption. Employing the K-means clustering algorithm, historical operational data from the converter have been meticulously analyzed to determine baseline values for essential variables such as energy consumption and recovery rates. Building upon this data-driven foundation, an innovative online system for the intelligent diagnosis of converter energy consumption has been crafted and implemented, enhancing the precision and efficiency of energy management. Upon implementation with energy consumption data at a steel plant in 2023, the diagnostic analysis performed by the system exposed significant variations in energy usage across different converter units. The analysis revealed that the most significant factor influencing the variation in energy consumption for both furnaces was the steel grade, with contributions of −0.550 and 0.379.