Scholarlink

<p>One of the world’s most energy-intensive businesses, the steel sector consumes much energy during its production operations. This research examines energy use trends in the steel industry with an emphasis on the main phases of steel manufacture, such as iron ore extraction, coke production, blast furnace operation, and electric arc furnace operation. Natural gas, coal, and electricity are all significant energy sources; the blast furnace consumes the most energy. It uses four different models to analyse how much energy the steel sector uses. Its purpose is to determine which model is more efficient given the diverse features in the energy dataset. In order to improve energy efficiency, the research also examines technical advancements such as waste heat recovery, hydrogen-based steel, and the use of renewable energy sources. Energy use must be decreased in order to lower carbon emissions and enhance the sustainability of steel manufacturing. The results highlight the necessity of industry investments in green technologies, policy interventions, and the adoption of best practices to lower the total energy footprint of the steel manufacturing sector. For analyzing energy use in steel manufacturing, machine learning (ML) methods such as Naive Bayes (NB), Logistic Regression (LR), Gradient Boosting (GB), and Extra Trees (ET) were employed. After assessing the models’ efficacy, ET is the most suitable option for this task.</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

The Importance of Energy Consumption and the Need for Efficiency in the Steel Industry Using Machine Learning

  • 期刊论文

  • 发表日期：

    2025年8月4日

查看全文
  • Xiaoling Zhang,
  • Lanqin Yang,
  • Deming Ma

摘要

One of the world’s most energy-intensive businesses, the steel sector consumes much energy during its production operations. This research examines energy use trends in the steel industry with an emphasis on the main phases of steel manufacture, such as iron ore extraction, coke production, blast furnace operation, and electric arc furnace operation. Natural gas, coal, and electricity are all significant energy sources; the blast furnace consumes the most energy. It uses four different models to analyse how much energy the steel sector uses. Its purpose is to determine which model is more efficient given the diverse features in the energy dataset. In order to improve energy efficiency, the research also examines technical advancements such as waste heat recovery, hydrogen-based steel, and the use of renewable energy sources. Energy use must be decreased in order to lower carbon emissions and enhance the sustainability of steel manufacturing. The results highlight the necessity of industry investments in green technologies, policy interventions, and the adoption of best practices to lower the total energy footprint of the steel manufacturing sector. For analyzing energy use in steel manufacturing, machine learning (ML) methods such as Naive Bayes (NB), Logistic Regression (LR), Gradient Boosting (GB), and Extra Trees (ET) were employed. After assessing the models’ efficacy, ET is the most suitable option for this task.