Prediction of blast furnace gas utilization rate based on mechanism and data-driven approaches

As one of the key indicators in blast furnace production, the stability of the blast furnace gas utilization rate directly affects the economic benefits of ironmaking enterprises. To this end, this paper proposes a blast furnace gas utilization rate prediction method that integrates mechanism modeling with data-driven approaches. First, operational data from the blast furnace process were collected. Abnormal and missing data were preprocessed by combining big-data techniques with process theory. On this basis, mechanism-derived features were constructed from multiple mechanistic models to capture the time-lag effects and state-accumulation characteristics of blast furnace operation, including burden composition, regional ore-to-coke ratio, and state transitions. After fusing these mechanism-derived features with time-series features, light gradient boosting machine (LightGBM) combined with time-series cross-validation was employed to select 18 features most relevant to blast furnace gas utilization rate. These selected features were further analyzed in detail from the process perspective and were confirmed to be suitable as the inputs to the model. Finally, the blast furnace gas utilization rate prediction model was developed by integrating gradient boosting decision tree (GBDT), Mamba, and temporal convolutional network (TCN). By leveraging the respective strengths of these algorithms, the model better captures the time-lag effects, state-accumulation effects, and short-term fluctuations in blast furnace operation. In addition, the superiority of the proposed model and the effectiveness of the constructed features were verified through ablation experiments. The results show that the model achieves a prediction hit rate of approximately 92% within an error margin of ±0.3%. After industrial deployment, the model delivered an approximately 1 percentage point increase in blast furnace gas utilization rate, which translated into enhanced economic returns for the company.