Process Knowledge Graph Reasoning Based on Graph Neural Network

In intelligent manufacturing, the process knowledge graph serves as a vital tool for managing and reasoning about complex process knowledge. Despite its effectiveness, traditional reasoning methods for knowledge graphs struggle with incomplete data and intricate relationships. Graph Neural Networks (GNNs), with their powerful representation learning capabilities, offer a promising solution for process knowledge graph reasoning. This study proposes a knowledge graph reasoning framework based on GNN, which enables efficient process knowledge reasoning under conditions of incomplete data. By integrating practical needs from manufacturing scenarios, we have designed a specialized knowledge graph schema layer and validated its performance on process dataset. The findings indicate that this approach surpasses conventional methods in terms of accuracy, generalization, and practical utility, offering fresh perspectives and technical advancements for knowledge graph reasoning in intelligent manufacturing.