Digital Twin (DT) is a promising technology that offers versatile services to enhance manufacturing intelligence. However, the agility, reliability and analysis capabilities of existing DT services are severely challenged when applied and deployed at large-scale production lines. To address the aforementioned issues, a microservice-based DT system with redundant architecture is proposed. First, a scalable microservice-based DT system compatible with standard and tailored plug-and-play DT services is constructed for DT protocol adaptation, stream processing, information and model management. Concurrently, a generic information model is proposed to represent the entire production lifecycle from design, operation, and maintenance in a structured manner. Second, an industrial multi-task DT model is introduced, leveraging the aforementioned architecture, to effectively achieve parallel monitoring of surface roughness and tool wear. Finally, industrial manufacturing cases are introduced to verify the feasibility and effectiveness of the proposed system. The results show that heterogeneous DT data are transferred and managed reliably, with a mean absolute percentage error of 1.28% for surface roughness prediction, and 85.71% accuracy in tool wear diagnosis.

中文翻译：

---

基于微服务的数字孪生系统迈向智能制造


数字孪生 (DT) 是一项很有前景的技术，可提供多种服务来增强制造智能。然而，现有DT服务的敏捷性、可靠性和分析能力在大规模生产线应用和部署时受到严峻挑战。针对上述问题，提出了一种基于微服务的冗余架构DT系统。首先，构建一个可扩展的、基于微服务的DT系统，兼容标准和定制的即插即用DT服务，用于DT协议适配、流处理、信息和模型管理。同时，提出了一个通用信息模型，以结构化方式表示从设计、操作和维护的整个生产生命周期。其次，引入工业多任务DT模型，利用上述架构，有效实现表面粗糙度和刀具磨损的并行监测。最后通过工业制造案例来验证该系统的可行性和有效性。结果表明，异构DT数据传输和管理可靠，表面粗糙度预测的平均绝对百分比误差为1.28%，刀具磨损诊断的准确率为85.71%。