Digital twin-driven human-machine collaborative maintenance services for continuous slab caster
本文研究了数字孪生技术如何驱动连铸机的人机协同维护服务，通过构建数字孪生模型和多层知识库，实现性能评估、故障预测和服务推荐，并在钢厂应用中降低了维护成本、提高了效率。
Continuous slab caster is an important piece of metallurgical equipment in the iron and steel industry. The present maintenance service for complex metallurgical equipment is often inseparable from the experience knowledge of the maintenance professionals. Digital twin (DT) offers new approaches to intelligent maintenance for slab casters, as they are able to reflect the operational process of the physical equipment in a virtual space, including the cyber model, operation history, and real time sensor update. This paper mainly explores DT-driven human-machine collaborative maintenance services for the continuous slab caster. Firstly, DT model is constructed by digitally correlating the equipment operation process, enabling performance evaluation and failure prediction. Then, by integrating human expert knowledge, a multi-layer knowledge base of the domain maintenance is created to facilitate the service recommendation based on digital maps. This forms an intelligent maintenance mechanism bridging human and machine collaboration. Finally, the effect of the DT-driven maintenance scheme on slab caster engineering was verified by its application to a steel plant. Preliminary statistical results shown that this approach reduced maintenance costs and improved maintenance efficiency under the harsh metallurgical environments, and maintenance intelligence was improved through the DT-driven human-machine collaboration scheme.