The amount of alloy added during the LF refining process affects the hit rate of steel composition control. Therefore, improving the accuracy of the alloy addition amount can help improve efficiency and reduce production costs. To address the existing problem of inaccurate alloy addition in the refining process, the group established an alloy addition prediction model based on an improved whale swarm optimization algorithm and stochastic configuration network (LWOA-SCN) with the historical smelting data of a steel mill. The model can effectively improve the prediction accuracy and convergence speed of the model. The research results show that the model is more advantageous in improving the hit rate of alloy addition, which provides theoretical guidance for practical production.
