Institute of Databases and Information Systems, University of Ulm, 89081 Ulm, Germany.
Institute of Clinical Epidemiology and Biometry, University of Würzburg, 97080 Würzburg, Germany.
Sensors (Basel). 2020 Sep 14;20(18):5245. doi: 10.3390/s20185245.
For machine manufacturing companies, besides the production of high quality and reliable machines, requirements have emerged to maintain machine-related aspects through digital services. The development of such services in the field of the Industrial Internet of Things (IIoT) is dealing with solutions such as effective condition monitoring and predictive maintenance. However, appropriate data sources are needed on which digital services can be technically based. As many powerful and cheap sensors have been introduced over the last years, their integration into complex machines is promising for developing digital services for various scenarios. It is apparent that for components handling recorded data of these sensors they must usually deal with large amounts of data. In particular, the labeling of raw sensor data must be furthered by a technical solution. To deal with these data handling challenges in a generic way, a sensor processing pipeline (SPP) was developed, which provides effective methods to capture, process, store, and visualize raw sensor data based on a processing chain. Based on the example of a machine manufacturing company, the SPP approach is presented in this work. For the company involved, the approach has revealed promising results.
对于机械制造企业来说，除了生产高质量、可靠的机器外，还需要通过数字服务来维护与机器相关的方面。工业物联网 (IIoT) 领域此类服务的发展正在处理有效状态监测和预测性维护等解决方案。然而，需要适当的数据来源，数字服务才能在此基础上实现技术支撑。由于近年来引入了许多强大且廉价的传感器，因此将它们集成到复杂的机器中对于开发各种场景的数字服务来说具有广阔的前景。显然，对于处理这些传感器记录数据的组件来说，它们通常必须处理大量的数据。特别是，原始传感器数据的标记必须通过技术解决方案进一步完善。为了以通用的方式处理这些数据处理挑战，开发了一种传感器处理管道 (SPP)，它提供了基于处理链捕获、处理、存储和可视化原始传感器数据的有效方法。基于一家机械制造公司的示例，本文介绍了 SPP 方法。对于所涉及的公司，该方法已经显示出了有前景的结果。
