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

• Published in: Steel research international Vol. 93; no. 12
• Main Authors: Nenchev, Bogdan, Panwisawas, Chinnapat, Yang, Xiaoan, Fu, Jun, Dong, Zihui, Tao, Qing, Gebelin, Jean-Christophe, Dunsmore, Andrew, Dong, Hongbiao, Li, Ming, Tao, Biao, Li, Fucun, Ru, Jintong, Wang, Fang
• Format: Journal Article
• Language: English
• Published: Weinheim Wiley Subscription Services, Inc 01.12.2022
• Subjects: Artificial intelligence; Back propagation; Back propagation networks; Basic converters; basic oxygen furnace; Case studies; Complexity; Data links; Data mining; Data science; Data storage; Datasets; digitalization; Digitization; Industrial development; Iron and steel industry; Machine learning; metallurgical data; Neural networks; Optimization; Oxygen steel making; Process controls; Quality control; Steel industry; steelmaking
• ISSN: 1611-3683; 1869-344X
• DOI: 10.1002/srin.202100813

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