In this research, we propose a system architecture of the server-edge dualized closed-loop data analytics system for cyber-physical system (CPS) application. We define six essential components for the data analytics system for CPS application: (1) the cyber model, (2) the data analytics module, (3) the data analysis model execution module, (4) the decision making module, (5) the system control module, and (6) the visualization module. We then propose an architecture of dualized closed-loop data analytics with server and edge-computing devices. The proposed dualized architecture of the data analytics system has advantages in handling the three issues of applying data analytics systems to the manufacturing context: (1) the system overload issue of the data analytics module due to large volumes of data, (2) the automation issue in the sequences of data analysis model generation, data analysis module execution, and system control, and (3) the real-time issue of data analysis model execution. In particular, a PMML-based data analysis model information parsing structure is proposed to deal with the automation issue. A case study that applies the proposed server-edge dualized closed-loop data analytics system for CPS application to the die-casting factory in Korea is introduced.

在这项研究中，我们提出了一种用于计算机物理系统（CPS）应用程序的服务器边缘双重化闭环数据分析系统的系统架构。我们为CPS应用程序的数据分析系统定义了六个基本组件：（1）网络模型，（2）数据分析模块，（3）数据分析模型执行模块，（4）决策模块，（5）系统控制模块，以及（6）可视化模块。然后，我们提出了使用服务器和边缘计算设备进行双重化闭环数据分析的体系结构。拟议的数据分析系统的双重体系结构在处理将数据分析系统应用于制造环境的三个问题方面具有优势：（1）由于数据量大，数据分析模块的系统过载问题；（2）数据分析模型生成，数据分析模块执行和系统控制顺序中的自动化问题，以及（3）数据分析模型执行的实时问题。特别地，提出了一种基于PMML的数据分析模型信息解析结构来解决自动化问题。介绍了一个案例研究，该案例将拟议的服务器边缘双重闭环数据分析系统用于CPS应用程序应用于韩国的压铸工厂。