Research on Converter Steelmaking Expert System Based on Knowledge Graph

Converter steelmaking process usually involves many complex processes and technical specifications, and the knowledge in the field of iron and steel smelting exists in the form of documents and databases, which lacks integration and sharing. In order to assist the real-time decision-making of converter steelmaking, this paper investigates the knowledge graph-based expert system for converter steelmaking. In the design of converter steelmaking knowledge graph, a top-down construction method is adopted, in which the ontology level is constructed first, and then the entities and relations are extracted. Where each entity as well as attribute contains the category to which it belongs, the ternary of the conceptual hierarchy (entity category, relation, entity category) can be used to filter the high-quality negative samples as well as the final answer, thus improving the accuracy of the system. In order to improve the interactive capability of the converter steelmaking expert system, this paper adopts the client-server architecture model so as to provide real-time decision support to the operators.