The development of a process charge expert system for a Basic Oxygen Steelmaking plant.

In an integrated steelworks the Basic Oxygen Steelmaking (BOS) process is required for the refining of molten iron from a blast furnace to produce steel. The development of an expert diagnostic system is considered in the context of the initial phase of BOS operation, the loading and operation of the BOS vessel. In this part of the steelmaking process the BOS vessel is charged with the molten iron, scrap metal and fluxes which are there to facilitate the capture of impurities by forming slag. The nature of the elements added requires knowledge of the steelmaking process, the actual state of the contents of the vessel and the available process management options. The expert system produced to oversee this process exhibits the capability of dealing with both continuous and batch data, combining the two together to aid effective decision making and management. Fuzzy inference is used in the main diagnostic system due to the large rule base required to diagnose faults and infer a process state. The operation of the system and its use by the process operators and the application of this approach into other areas of the steelworks is considered in this paper.