Cyber-physical systems (CPS) offer immense optimization potential for manufacturing processes through the availability of multivariate time series data of actors and sensors. Based on automated analysis software, the deployment of adaptive and responsive measures is possible for time series data. Due to the complex and dynamic nature of modern manufacturing, analysis and modeling often cannot be entirely automated. Even machine- or deep learning approaches often depend on a priori expert knowledge and labelling. In this paper, an information-based data preprocessing approach is proposed. By applying statistical methods including variance and correlation analysis, an approximation of the sampling rate in event-based systems and the utilization of spectral analysis, knowledge about the underlying manufacturing processes can be gained prior to modeling. The paper presents, how statistical analysis enables the pruning of a dataset's least important features and how the sampling rate approximation approach sets the base for further data analysis and modeling. The data's underlying periodicity, originating from the cyclic nature of an automated manufacturing process, will be detected by utilizing the fast Fourier transform. This information-based preprocessing method will then be validated for process time series data of cyber-physical systems' programmable logic controllers (PLC).

翻译：信息物理系统（CPS）通过提供执行器和传感器的多变量时间序列数据，为制造过程带来了巨大的优化潜力。基于自动化分析软件，可对时间序列数据部署自适应和响应性措施。由于现代制造的复杂性和动态性，分析与建模往往无法完全自动化。即使机器学习和深度学习方法也常依赖于先验专家知识和标注。本文提出了一种基于信息的数据预处理方法。通过应用包括方差分析、相关性分析在内的统计方法，对事件驱动系统采样率的近似估算以及频谱分析的应用，可在建模前获取关于底层制造过程的知识。本文阐述了统计分析如何实现对数据集中最不重要特征的剪枝，以及采样率近似方法如何为后续数据分析和建模奠定基础。利用快速傅里叶变换，可检测到源自自动化制造过程周期特性的数据底层周期性。最后，针对信息物理系统的可编程逻辑控制器（PLC）过程时间序列数据，对该基于信息的预处理方法进行了验证。