Graph-Based Variation Propagation Network for Modeling and Prediction of Hybrid Multi-Stage Manufacturing Systems

Multistage Manufacturing Systems (MMS) are common in industries involving complex processes with multiple stages, each impacting the final product quality. Traditional product quality modeling approaches struggle with the intricate interdependencies and variable structures within these systems, further complicated by the extensive sensor-generated data. In this paper, we introduce Graph-based Variation Propagation Network (GVPNet), an innovative approach for end-to-end learning of product quality representations and their propagation through MMS stages. GVPNet utilizes a heterogeneous Graph Attention Network (hGAT) architecture that uses a graph representation specifically tailored for MMS, facilitating the effective application of graph neural networks (GNN) in this context. The network’s ability to aggregate information and learn node embeddings enables it to predict quality variables several stages ahead, thus offering a proactive tool for quality control. GVPNet was applied in two real world case studies and demonstrated its superiority in predictive accuracy and robustness over benchmarks. Note to Practitioners—This paper introduces the Graph-based Variation Propagation Network (GVPNet), designed to enhance quality prediction in Multistage Manufacturing Systems (MMS) where traditional models fall short. Integrating a tailored graph representation with the Graph Attention Network (hGAT), GVPNet excels in capturing the complex dynamics of MMS, including inter-stage dependencies. This approach enables more accurate and proactive quality control in various manufacturing contexts, providing a significant tool for practitioners to optimize processes and improve product quality, even in data-rich environments.