Monitoring self-organizing industrial systems using sub-trajectory dictionaries

Abstract

In this work, we present a monitoring system for Self-Organizing Industrial Systems (SOIS). It is based on an anomaly detection approach which evaluates the movement of objects within a factory by putting them together from sub-trajectories. By introducing two metrics — relative user frequency and pathlet occurence per user — the existing method is extended so that not only anomalous trajectories and omitted production stations can be detected, but also loops, shifts in the load distribution and novel valid paths. For this purpose, suitable visualization techniques are presented: For loop detection the pathlet occurence per user is monitored and evaluated using box plots. Shifts in the load distribution and novel valid paths are detected using heat maps. The work-flow of the monitoring system is illustrated based on data which is generated by a simplified simulation model.