基于GA-BP模型和李斯特操作线的铁直接还原度的预测研究

Study on Prediction of Iron Direct Reduction Degree Based on GA-BP Model and Rist Operation Line

摘要: 为实现“碳达峰、碳中和”目标和加快打造具有重要影响力的经济社会，着力推进工业绿色低碳转型和制造业高质量发展就必须从工业技术上改革。在高炉炼铁工艺过程中，铁的直接还原度在炼铁工艺中作为判断生产的重要指标系数，为决定生产强度起到关键作用。本文通过李斯特操作线模型计算铁的直接还原度，运用GA-BP算法建立了铁的直接还原度预测模型，并与支持向量机模型、随机森林模型进行预测结果对比。预测结果表明，GA-BP模型的MSE为0.012，MAE为0.08，R²达到0.92，预测性能明显优于另外两个预测模型，模型的拟合性更强。

Abstract: In order to achieve the goal of “carbon peak, carbon neutral” and accelerate the construction of a comprehensive green transformation zone with important influence on economic and social development, it is necessary to reform industrial technology to focus on promoting the green and low-carbon transformation of industry and high-quality development of manufacturing industry. In the process of blast furnace ironmaking, the direct reduction degree of iron plays a key role in determining the production intensity as an important production index coefficient in the ironmaking process. In this paper, the direct reduction degree of iron is calculated by the Rist operation line model, and the prediction results are compared with the support vector machine model and random forest model. The prediction results show that the MSE, MAE and R² of the GA-BP model are 0.012, 0.08 and 0.92, respectively. The prediction performance of the GA-BP model is obviously better than that of the other two prediction models, and the model has stronger fitting.