Active monitoring of production status in discrete manufacturing workshops driven by digital twins

Traditional manufacturing workshop processes are challenging to change, and passive monitoring methods, such as quality traceability and completion rate monitoring, pose challenges for discrete workshops in achieving real-time and accurate production control. Therefore, combined with the digital twin system, a multi-level production status monitoring model is established to monitor discrete manufacturing workshops actively. This article focuses on discrete manufacturing workshops’ modeling and self-evolution production processes. It also proposes an active monitoring architecture for production status in discrete workshops using digital twin technology. A full-information model is constructed for a discrete manufacturing workshop. Then, a multi-node interaction logic is established for the discrete manufacturing workshop. Finally, based on the fuzzy C-means clustering algorithm, production anomalies are monitored, and real-time monitoring of disturbances caused by various production factors, including material status, equipment status, and work-in-progress status, is performed to assess their impact on production. Based on deep Bayesian network learning algorithms, we can monitor production performance and analyze workshop capacity, equipment utilization, bottleneck rhythm, etc. This allows us to actively monitor production performance through the self-evolution of digital twin models. This article aims to proactively predict changes in workshop production status and provide support for further plan completion rate improvement, capacity prediction, and capacity optimization.