Fuel Ratio Reduction, Intelligent Blast Furnace Ironmaking, Big Data, Deep Learning, Energy Conservation and Emission Reduction
Abstract
Blast furnace ironmaking a crucial segment within modern steel production, a paradigmatic “black box” model. The optimization of perception and decision-making throughout this process holds paramount significance in enhancing ironmaking efficiency. This research delves into issues such as the incapability of achieving the anticipated fuel ratio in blast furnace ironmaking, the dearth of timely feedback information during the process, and high pollution and energy consumption levels. The research findings imply that by implementing intelligent blast furnace ironmaking, preprocessing blast furnace data, optimizing sinter burden formulation, and leveraging machine learning techniques based on big data to handle the “black box” conundrum, the perception capabilities regarding the blast furnace operating status can be substantially enhanced. Consequently, this leads to optimizing the decision-making procedures, reducing energy consumption, and elevating molten iron quality. Moreover, the intelligent decision-making system grounded in artificial intelligence can effectively mitigate human intervention and augment the overall production stability under complex ironmaking operating conditions. This research proffers novel insights for the intelligent development of the blast furnace ironmaking process and is crucial for propelling the sustainable development of the steel industry.
