Semantic Association Rule Learning from Time Series Data and Knowledge Graphs

TL;DR

This paper introduces a pipeline for learning semantic association rules from time series data and knowledge graphs in Digital Twins, demonstrating its effectiveness in industrial water network scenarios and laying groundwork for future industrial applications.

Contribution

It proposes a novel pipeline and new criterion for semantic association rule learning in Digital Twins using knowledge graphs and time series data.

Findings

High number of semantic association rules learned

Rules are more generalizable

Effective in industrial water network scenario

Abstract

Digital Twins (DT) are a promising concept in cyber-physical systems research due to their advanced features including monitoring and automated reasoning. Semantic technologies such as Knowledge Graphs (KG) are recently being utilized in DTs especially for information modelling. Building on this move, this paper proposes a pipeline for semantic association rule learning in DTs using KGs and time series data. In addition to this initial pipeline, we also propose new semantic association rule criterion. The approach is evaluated on an industrial water network scenario. Initial evaluation shows that the proposed approach is able to learn a high number of association rules with semantic information which are more generalizable. The paper aims to set a foundation for further work on using semantic association rule learning especially in the context of industrial applications.