Cyber-physical internet spatial-temporal reasoning for production logistics resource recommendation in industry 4.0

Abstract

Production logistics (PL) focuses on planning, allocating, and controlling the material and information flows within production processes. In discrete manufacturing, PL is characterized by significant dynamics and uncertainty due to fluctuating resource demands and operational asynchrony. Reliable PL resource allocation is not only fundamental for improving production efficiency but also serves as a crucial prerequisite for orchestrating various resources to achieve zero inventory or even zero warehousing. Therefore, this paper proposes a recommendation-based PL resource allocation approach that considers the temporal and spatial characteristics of shop floors and production materials. To accurately represent the relationships of various entities and resource allocation history, we borrow the idea from the digital Internet, where the IP address and routing tables contribute to moving data packets, to design the Cyber-Physical Internet (CPI) addresses and routing tables, which represent location areas and resource flow directions, and thereby construct the resource spatial-temporal knowledge graph (RSTKG). Then, a spatial-temporal reasoning mechanism is proposed, which conducts connectivity, contextual, and collaborative reasoning on RSTKG to evaluate the cost-effectiveness between required nodes and available resources and generate the resource allocation recommendation plan. Finally, the allocation decisions will be updated to the related routing table of each node. When new resources arrive, table lookup can be conducted to understand the next transfer direction, reducing the risk of delay during the actual transportation of resources. To evaluate the effectiveness of the proposed approach, we first conduct a laboratory experiment and then conduct a case study on an air conditioning manufacturer. Compared to other resource allocation algorithms, our approach achieves a punctuality rate of over 90%, reduces the average traveling distance, and improves the efficiency of traceability analysis.