Ladle intelligent re-scheduling method in steelmaking–refining–continuous casting production process based on BP neural network working condition estimation

Frequent delays will be experienced in the start-up of molten steel on converter equipment during steelmaking–continuous casting (SCC) production process due to untimely supply iron or scrap, which may cause conflicts between adjacent heat same casting. The machine is cut off, resulting failure static scheduling plan. SCC ladle re-scheduling based premise that path remains unchanged, operation and refining furnace does not conflict, within continuous. steelmaking continuous aims at continuously many charges with cast avoiding machine. This mechanism proposes a method steelmaking–refining–continuous casting, divided into two parts: plan optimisation scheduling. Firstly, model built. minimising waiting time all charges. strategy proposed by interval processing expert experience. composed charge decision decision. Then, first-order rule learning used select target establish optimal model. matching rules are extracted basis reasoning minimum general generalisation. consists selection preparation proposed. Ladle adopts rule-based decarburised after choosing dephosphorised ladle. preparation, multi-priority heuristic method, designed decide from Finally, this was actually verified large-scale data company Shanghai, China. Results showed efficiency steelmaking-refining-continuous improved.