🤖 AI Summary
Spatial process mining for physical entities in digital twins remains challenging, particularly in complex manufacturing environments such as modular production lines, where manual domain expertise is often required for deviation diagnosis.
Method: This paper proposes an automated, domain-expert-free deviation attribution method. It employs overhead cameras for active perception to generate event logs and constructs a spatiotemporal partitioning model. An improved HITS-based event-node ranking mechanism is introduced to automatically localize root causes of deviations. Additionally, a novel Gantt-style process representation and visualization framework is proposed, specifically designed for spatial cells.
Contribution/Results: The approach enables bird’s-eye-view dynamic process monitoring, achieving high interpretability while significantly improving both the efficiency and accuracy of anomaly diagnosis. Experimental evaluation validates its effectiveness in real-world industrial settings.
📝 Abstract
We propose a new framework that focuses on on-site entities in the digital twin, a pairing of the real world and digital space. Characteristics include active sensing to generate event logs, spatial and temporal partitioning of complex processes, and visualization and analysis of processes that can be scaled in space and time. As a specific example, a cell production system is composed of connected manufacturing spaces called cells in a manufacturing process. A cell is sensed by ceiling cameras to generate a Gantt chart that provides a bird's-eye view of the process according to the cycle of events that occur in the cell. This Gantt chart is easy to understand for experienced operators, but we also propose a method for finding the focus of causes of deviations from the usual process without special experience or knowledge. This method captures the characteristics of the processes occurring in a cell by using our own event node ranking algorithm, a modification of HITS (Hypertext Induced Topic Selection), which scores web pages against a complex network generated from a process model.