Prediction of blast furnace gas utilization rate based on genetic algorithm-optimized GA-ARIMA model.

The utilization rate of blast furnace gas is the core index to measure the efficiency of blast furnace smelting and the level of energy consumption. Accurately predicting this utilization rate is of great significance for furnace condition adjustment. Aiming at the problem that the parameter selection of the traditional Autoregressive Integrated Moving Average (ARIMA) model depends on experience and is prone to falling into local optima, this paper proposes a GA-ARIMA prediction model based on the Genetic Algorithm (GA). Firstly, the production data of a 3200 m³ blast furnace in China was constructed through data cleaning, outlier handling and normalization. Secondly, the genetic algorithm was used to globally optimize the order parameters (p, d, q) of the ARIMA model. Finally, the utilization rate of blast furnace gas was predicted and the performance of each model was compared. The results show that compared with the traditional ARIMA model, the mean square error and root mean square error of the GA-ARIMA model were reduced by 31.1% and 16.9% respectively, significantly improving the prediction accuracy and stability. This model can provide more reliable decision-making support for the real-time monitoring and production control of blast furnace gas utilization. [ABSTRACT FROM AUTHOR]