A flow-generator platform to assess a data-driven design of material handling and production systems

This study introduces a flow-generator platform designed to enable data-driven approaches, e.g., models, decision support systems, and digital twins, in production and storage systems. It aims to address the challenges of providing realistic operational data when actual data are unavailable as in greenfield scenarios. The platform simulates inbound and outbound material flows by capturing variability in production rates, shipping schedules, and storage processes. Users configure parameters such as production line capacity, items diversity, batch sizes, and material handling strategies through a visual dashboard, facilitating detailed analysis of operational production peaks, trends, and variabilities. By enhancing decision-making processes through robust and realistic data, the platform complements simulators, digital twins, and advanced modeling methods. A numerical example set in the food processing industry demonstrates its applicability, showcasing its ability to support robust performance modeling and optimization tailored to dynamic supply chain environments.