BioSync: Offline-Synchronization of time-series data using bio-inspired semantic synchronization strategies

Abstract

In modern data-centric production, multiple sensors, machines, equipment, and systems are connected providing high variety and amount of data to enable insights to ongoing production. By adding more of those data sources to production, the Time Synchronization Problem becomes more intense when aggregating the data streams for analysis afterwards (offline synchronization). This synchronization is crucial for the quality of the whole dataset used for analytics and services like machine learning applications. A similar effect is existing in the human brain and the parietal cortex when a human is performing a multisensory fusion. The human brain uses information about the environment and the understanding of cause-effect relationships to present synchronized sensor information to the conscious human to act upon. In this paper, we show how this concept can be adapted to the time-series synchronization of production data. By using the information of the production system and the insights on cause-effect relationships on the components and inside the production process, probabilities of data points being connected by physical events in the process. The application and integration strategies for using this bio-inspired synchronization are presented in addition to the requirements for such applications in the production domain. By this, the bio-inspired semantic synchronization enables a completely new way of tackling the Time Synchronization Problem, especially for offline data sets.