A Novel Method of Digital Twin-Based Manufacturing Process State Modeling and Incremental Anomaly Detection

In the manufacturing process, digital twin technology can provide real-time mapping, prediction, and optimization of physical process in information world. order to realize complete expression accurate identification changes state a framework incremental learning driven by stream data is proposed. Additionally, novel method data-driven equipment operation modeling anomaly detection proposed based on twin. Firstly, hierarchical finite machine (HFSM) for was completely express state. Secondly, used detect job data, so as change status real time. Furthermore, F1 value time consumption algorithm were compared analyzed using general dataset. Finally, applied practical case development welding manufacturer’s system. The flexibility model calculated quantitative method. results show that help system mapping quickly, effectively, flexibly.