Knowledge graph-driven decision support for manufacturing process: A graph neural network-based knowledge reasoning approach

In modern manufacturing, effectively reusing and sharing knowledge is essential due to the vast amounts of data and resources available. This research introduces a three-layer cognitive manufacturing paradigm that integrates data, knowledge, and decision-making. Our model uses a manufacturing knowledge graph to organize various data sources and applies a dual-driven knowledge reasoning strategy for smooth data-to-knowledge transitions. We developed an automated framework to construct knowledge graphs specifically for machining product knowledge and implemented an RGAT-PRotatE method for regular knowledge updates. The RGAT encoder effectively captures complex relational dynamics using attention mechanisms to focus on key interactions within mechanical processes. Meanwhile, the PRotatE decoder predicts and fills in missing information in the graph. We also introduce a knowledge-centric decision support system that utilizes the knowledge graph's reasoning capabilities. An empirical study on the fabrication of aero-engine casings demonstrates the practicality and effectiveness of our framework, contributing to advancements in cognitive manufacturing and decision-making.