Whale Optimization End-point Control Model for 260 tons BOF Steelmaking

The end-point control technology of basic oxygen furnace (BOF) steelmaking is a very important production process in the later stage smelting, and it has become research hotspot smelting industry. In this paper, carbon content temperature prediction models were established based on twin support vector regression (TSVR). order to ensure stability model, input variables model determined by using grey relational analysis (GRA) partial correlation (PCA). results demonstrate that hit rate error bound within 0.005 wt% 90%, 10°C 94%, respectively. Moreover, double reached 84%. By comparing with back propagation (BP) neural network rates proposed are higher than those BP model. Based models, whale optimization was for calculations auxiliary materials blowing volume. simulation illustrate mean absolute 9.3114 tons scrap weight, 2.5791 lime 0.7919 dolomite weight 537.8215 Nm3 volume, which better other two aspects calculation accuracy.