Koopman-Constrained Hierarchical Deep State Space Model for Industrial Quality Prediction via Cloud-Edge Collaborative Framework
针对工业制造中工况波动和数据噪声影响质量预测的问题，提出一种Koopman约束的层次化深度状态空间模型，并嵌入云边协同框架，通过模型失配检测和简化策略提升预测精度与实时性，在仿真和实际工业过程中验证了有效性。
In cloud manufacturing of industrial processes, the accurate online prediction of product quality is the basis for realizing decision-making and control of the manufacturing process. However, frequent fluctuations in working conditions and data noise restrict the application of data-driven methods in industrial sites. In addition, the constrained resources on edge devices limit their ability to automatically update or deploy complex models. To address these issues, this study proposes a Koopman-constrained hierarchical deep state-space model (KHSSM) and incorporates it into the innovative cloud-edge collaboration framework for industrial quality prediction. First, KHSSM integrates a state-space model, leveraging its advantage in modeling noisy dynamic data. Second, the Koopman operator is introduced to constrain the latent variables in the measurement space, enabling it to interpretably reflect the evolution dynamics of the system. In addition, novel strategies for model mismatch detection and model simplification are designed and deployed to improve the predictive accuracy and real-time efficiency of the cloud-edge collaboration framework. Finally, the effectiveness of the proposed method is verified by extensive experiments in a numerical simulation and a real-world industrial process.