Metallurgical Data Science for Steel Industry: A Case Study on Basic Oxygen Furnace

The steel industry has developed sensorization to generate data, monitoring systems, and steelmaking process control. remaining challenges are data storage issues, lack of cross-production links, erroneous datasets, which significantly increase the quality control complexity. development a data-driven approach through artificial intelligence (AI) techniques enables machine learning big datasets aiming provide process–property optimization identify gaps in data. Recently, computational capabilities algorithmic developments have grown power complexity, accelerating optimization. Addressing large-scale industrial strategies involve numerous influencing possessing factors but limited As one largest production chains world, faces an ever-increasing demand for larger components, high levels functionality, final product. Herein, integrated case study is built with aim predicting optimizing product composition quality. Machine used collaboratively fundamental knowledge, first-principal calculation, feedback into backpropagation neural network (NN) model. Integrating mining generates reasonable predictions addresses efficiencies within furnaces. ultimate goal enhance digitalization industry.