A Hybrid Prediction Model for Gas Utilization Rate Based on Blast Furnace Operating Conditions

Accurately predicting the gas utilization rate (GUR), a crucial metric reflecting the operational status and energy consumption of a blast furnace (BF), is essential for optimizing production processes. In this study, we develop a hybrid prediction model for GUR by integrating a least squares support vector machine (LSSVM) and an artificial neural network (ANN), with the fuzzy C-means (FCM) algorithm employed to classify BF conditions. The results demonstrate that the FCM algorithm achieves remarkable precision in distinguishing stable and unstable operating states of the BF, attaining an impressive accuracy rate of 94.59 pct. Furthermore, the hybrid prediction model exhibits high accuracy in GUR predictions, yielding a mean absolute deviation (MAD) of 0.22, a mean squared error (MSE) of 0.18, a root mean square error (RMSE) of 0.43 and a correlation coefficient (R2) value of 93.88 pct. These results underscore the accuracy and effectiveness of the proposed hybrid model in predicting GUR, highlighting its potential to enhance the operational efficiency and reliability of BF.