Scholarlink

<p>Steel is a&#xa0;durable material and is 100% recyclable from all stages of a&#xa0;product’s life. When steel scrap is properly processed, it retains most of its properties. With the transformation of the industry towards low-carbon steel production, the adoption of new technological innovations, also regarding the utilisation of scrap, including post-consumer scrap, is of great importance. An accurate chemical analysis of the scrap composition enables tramp- or alloying elements to be used as resources instead of being considered impurities. This work presents a&#xa0;concept to integrate an optical-spectroscopic sensor chain for scrap characterisation into an existing scrap preparation process. X‑Ray Fluorescence (XRF) and laser-induced breakdown spectroscopy (LIBS) are used for chemical analysis and are coupled with optical sensors, RGB‑D camera and Light Detection and Ranging (LiDAR), to simultaneously determine the material volume and mass and asses the presence of some tramp elements. A&#xa0;concept for transferring, synchronising and merging large amounts of data is outlined to develop a&#xa0;machine learning model to support scrap characterisation. First results demonstrate the potential of AI to advance digitalisation in sustainable steelmaking. In order to successfully implement these technologies in companies and to ensure acceptance among employees, their skills must be further developed. The workforce accordingly needs to be prepared and ready to embrace new challenges and learning opportunities. From a&#xa0;socio-technical perspective, such technology can only be introduced optimally through the joint optimisation of people, technology and organisation.</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

Kombination multimodaler Sensordaten für eine verbesserte Nutzung von Schrott in der Stahlproduktion

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月21日

查看全文
  • Melanie Leitner,
  • Valentina Colla,
  • Alice Petrucciani,
  • Marco Vannucci,
  • Anton Koval,
  • Nilesh Kulkarni,
  • Rucha Sawlekar,
  • George Nikolakopoulos,
  • Adrian Götting,
  • Tobias Wienzek,
  • Mauro Meneghin

摘要

Steel is a durable material and is 100% recyclable from all stages of a product’s life. When steel scrap is properly processed, it retains most of its properties. With the transformation of the industry towards low-carbon steel production, the adoption of new technological innovations, also regarding the utilisation of scrap, including post-consumer scrap, is of great importance. An accurate chemical analysis of the scrap composition enables tramp- or alloying elements to be used as resources instead of being considered impurities. This work presents a concept to integrate an optical-spectroscopic sensor chain for scrap characterisation into an existing scrap preparation process. X‑Ray Fluorescence (XRF) and laser-induced breakdown spectroscopy (LIBS) are used for chemical analysis and are coupled with optical sensors, RGB‑D camera and Light Detection and Ranging (LiDAR), to simultaneously determine the material volume and mass and asses the presence of some tramp elements. A concept for transferring, synchronising and merging large amounts of data is outlined to develop a machine learning model to support scrap characterisation. First results demonstrate the potential of AI to advance digitalisation in sustainable steelmaking. In order to successfully implement these technologies in companies and to ensure acceptance among employees, their skills must be further developed. The workforce accordingly needs to be prepared and ready to embrace new challenges and learning opportunities. From a socio-technical perspective, such technology can only be introduced optimally through the joint optimisation of people, technology and organisation.