Metric Based Dynamic Control Charts for Edge Anomaly Detection in Factory Logistics

The optimization of transport logistics in production environments is a holistic task for the factory future. Autonomous guided vehicles that perform jobs factories are facing this challenge and have to detect, react prepare unforeseen changes anomalies system. Due data protection concerns, details like plans often not available an external transportation Hence anomaly detection has be based on self-collected observed system occurred needs or evolution internal metrics. In paper we infused with manufacturing process demonstrate observation overcome gab caused by restricted information. For extended classic control charts work expected values learned dynamic characteristics. sets tolerance field as narrow possible around dynamically determined values, resulting average precision 95% unusual number jobs.