In a significant breakthrough for the steelmaking industry, researchers have introduced a functional digital twin model aimed at enhancing the control of end-point carbon in converter steelmaking. This innovative approach addresses a critical challenge faced by steel manufacturers: the need for smarter, more efficient production processes that align with the goals of “China Manufacturing 2025.” The study, led by Xu Gang, highlights the potential for this model to revolutionize how steel is produced, ultimately benefiting the construction sector that heavily relies on high-quality steel.
Converter steelmaking is the predominant method of steel production globally, yet it grapples with complex thermodynamic and dynamic reactions that often hinder accurate predictions of carbon content. Traditional methods, such as sublance control and flue-gas analysis, have proven insufficient, leading to inefficiencies and increased production costs. The new functional digital twin model leverages real-time flue gas analysis to monitor the carbon and oxygen reactions in molten steel, enabling a more precise prediction of the end-point carbon levels.
“The greatest advantage of our method is its ability to automatically adjust according to real-time data,” Xu Gang explained. “This self-learning capability allows for accurate predictions throughout the smelting process, including critical stages like decarburization and carbon drawing during secondary scraping slag.”
The implications of this research extend far beyond the steelmaking process itself. By accurately predicting the carbon content, manufacturers can optimize the final blowing point, effectively preventing costly overblowing or underblowing incidents. This precision not only enhances product quality but also significantly reduces production costs—an attractive proposition for construction companies that depend on reliable steel supplies.
An industrial experiment conducted on a 260-ton converter validated the model’s robustness, demonstrating its self-adaptive abilities even in abnormal smelting states. The results show that the model can maintain a carbon content prediction accuracy of 95% at ± 0.02%. This level of precision could eliminate the need for the traditional blown-off sampling step, streamlining operations and further driving down costs.
As the construction industry continues to evolve, the demand for high-quality steel at competitive prices will only increase. The introduction of such advanced technologies in steelmaking could lead to a new era of construction efficiency, enabling projects to be completed faster and with better materials.
The findings are published in ‘工程科学学报,’ which translates to ‘Journal of Engineering Science.’ This research not only underscores the pivotal role of technology in modern manufacturing but also sets the stage for future developments in the field of steel production. The potential for such innovations to reshape the construction landscape is immense, prompting industry stakeholders to consider how they can leverage these advancements for competitive advantage.
For more information about Xu Gang and his research team, you can visit their affiliation at lead_author_affiliation.
