Scholarlink

<p>Refractory materials are essential for high-temperature industrial processes, including steel and cement production as well as waste incineration. Due to the extreme operating conditions, refractory linings require regular replacement, generating significant amounts of spent refractory (SR) materials. These materials possess a&#xa0;high potential as secondary raw materials. Currently, SR recycling predominantly relies on manual sorting based on visual criteria, with economic constraints limiting the maximum particle size considered. A&#xa0;comprehensive, automated sorting system capable of classifying the wide variety of refractory materials independent of grain size has not yet been established. Recent advancements in research and technology have facilitated the development of more efficient and automated recycling solutions. One such innovation is the mobile sorting unit developed within the EU-funded ReSoURCE project (Refractory Sorting Using Revolutionizing Classification Equipment). The system integrates hyperspectral imaging (HSI) and laser-induced breakdown spectroscopy (LIBS) with artificial intelligence to achieve precise classification. To enhance sorting accuracy, an extensive database is being compiled, incorporating sensor measurements and analytical data of primary and secondary refractory materials with varying compositions and grain sizes. This contribution highlights the critical role of comprehensive material characterisation for sensor training and presents initial test results demonstrating a&#xa0;promising differentiation of refractory materials. Future work will focus on expanding the database and defining distinct chemical and mineralogical sorting classes to optimise automated classification.</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

Materialcharakterisierung gebrauchter Feuerfeststeine als Schlüssel für das effektive Training von Sensoren

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月22日

查看全文
  • Florian Feucht,
  • Simone Neuhold,
  • Alexander Leitner,
  • Cord Fricke-Begemann,
  • Julio Hernandez,
  • Volker Mörkens,
  • Klaus Philipp Sedlazeck

摘要

Refractory materials are essential for high-temperature industrial processes, including steel and cement production as well as waste incineration. Due to the extreme operating conditions, refractory linings require regular replacement, generating significant amounts of spent refractory (SR) materials. These materials possess a high potential as secondary raw materials. Currently, SR recycling predominantly relies on manual sorting based on visual criteria, with economic constraints limiting the maximum particle size considered. A comprehensive, automated sorting system capable of classifying the wide variety of refractory materials independent of grain size has not yet been established. Recent advancements in research and technology have facilitated the development of more efficient and automated recycling solutions. One such innovation is the mobile sorting unit developed within the EU-funded ReSoURCE project (Refractory Sorting Using Revolutionizing Classification Equipment). The system integrates hyperspectral imaging (HSI) and laser-induced breakdown spectroscopy (LIBS) with artificial intelligence to achieve precise classification. To enhance sorting accuracy, an extensive database is being compiled, incorporating sensor measurements and analytical data of primary and secondary refractory materials with varying compositions and grain sizes. This contribution highlights the critical role of comprehensive material characterisation for sensor training and presents initial test results demonstrating a promising differentiation of refractory materials. Future work will focus on expanding the database and defining distinct chemical and mineralogical sorting classes to optimise automated classification.