数字孪生系统及其在药玻检测设备运维中的应用  

Digital twin system and its application in the operation and maintenance of drug glass testing equipment

作　　者：武存宇 程煜[2] 任亚恒[2] 康尧星 吴立龙[2] 代明 张云佐 WU Cunyu;CHENG Yu;REN Yaheng;KANG Raoxing;WU Lilong;DAI Ming;ZHANG Yunzuo(School of Information Science and Technology,Shijiazhuang Tiedao University,Shijiazhuang 050043,China;Institute of Applied Mathematics,Hebei Academy of Sciences,Shijiazhuang 050081,China)

机构地区：[1]石家庄铁道大学信息科学与技术学院,河北石家庄050043 [2]河北省科学院应用数学研究所,河北石家庄050081

出　　处：《电子设计工程》2025年第1期80-85,共6页Electronic Design Engineering

基　　金：国家自然科学基金(61702347);河北省科学院科技计划项目(23A01);中央引导地方科技发展资金项目(226Z0501G)。

摘　　要：针对药用玻璃生产设备维保困难大、成本高、周期长等问题,该文文引入数字孪生技术,构建了用于药玻检测设备故障诊断的数字孪生运维系统,以实现对药玻生产线运行过程中的虚拟监控、关键部件的状态预测及联动决策。根据药玻设备的特点构建药玻检测线设备的数字孪生模型。针对实体物理设备因模块协议不统一导致的数据感知异常,基于OPC UA构建了一套针对药玻检测设备的标准化通信协议。采用虚实数据融合的架构模式,结合虚实相似度映射融合规则对多元异构数据进行融合处理,并对融合后的数据进行后期数据分析和处理。将特征输入HSMM预测模型,并结合模糊专家系统对药玻设备故障进行识别分析,给出最终的设备维护建议。仿真实验表明,所设计的系统可真实反映物理设备的运行状态,并通过大量数据样本对设备状态进行评估。In response to the challenges of maintenance difficulty,high costs,and long cycles in pharmaceutical glassware production equipment,this paper introduces digital twin technology to construct a digital twin operation and maintenance system for fault diagnosis of pharmaceutical glassware inspection equipment.This system aims to achieve virtual monitoring of the pharmaceutical glassware production line,prediction of key component status,and coordinated decision⁃making.Digital twin models for pharmaceutical glassware inspection equipment are built based on the characteristics of the equipment.To address data perception anomalies resulting from inconsistent module protocols in physical devices,a standardized communication protocol for pharmaceutical glassware inspection equipment is established using OPC UA.Subsequently,employing an architecture pattern that combines virtual and real data fusion,heterogeneous data from multiple sources are fused using similarity mapping fusion rules,followed by subsequent data analysis and processing.Features are input into the HSMM prediction model,and combined with a fuzzy expert system for fault identification analysis of pharmaceutical glassware equipment,providing final equipment maintenance recommendations.Simulation experiments demonstrate that the designed system accurately reflects the operational status of physical equipment and evaluates equipment status using a large number of data samples.

关 键 词：数字孪生 故障诊断 OPC UA 数据融合 专家系统 

分 类 号：TN-9[电子电信]