用超图网络建模多传感器复杂关系，提升工业软传感精度
ST-HCSS: Deep Spatio-Temporal Hypergraph Convolutional Neural Network for Soft Sensing
- 构建时空超图，捕捉传感器间的高阶非线性交互
- 在多个真实数据集上优于现有最优软传感方法
- 适合工业过程监控、故障预测等需要高精度软传感的场景
现代工业环境中，高阶传感器网络通过允许多节点连接，比传统成对图边更能准确刻画传感时序数据的非线性动态。为此，我们提出一种用于软传感的深度时空超图卷积神经网络（ST-HCSS）。该框架无需先验结构知识，即可自动构建并利用高阶图（超图）来建模传感器节点间的复杂多向交互。为捕捉深层时空依赖关系，ST-HCSS采用堆叠的门控时序与超图卷积层，在时间和节点维度上高效聚合与更新超图信息。实验结果验证了ST-HCSS在多个基准数据集上优于现有最先进软传感器模型，且学习到的超图特征表示与传感器数据相关性高度一致。代码已开源：https://github.com/htew0001/ST-HCSS.git。
原文摘要 · Abstract (English)
Higher-order sensor networks are more accurate in characterizing the nonlinear dynamics of sensory time-series data in modern industrial settings by allowing multi-node connections beyond simple pairwise graph edges. In light of this, we propose a deep spatio-temporal hypergraph convolutional neural network for soft sensing (ST-HCSS). In particular, our proposed framework is able to construct and leverage a higher-order graph (hypergraph) to model the complex multi-interactions between sensor nodes in the absence of prior structural knowledge. To capture rich spatio-temporal relationships underlying sensor data, our proposed ST-HCSS incorporates stacked gated temporal and hypergraph convolution layers to effectively aggregate and update hypergraph information across time and nodes. Our results validate the superiority of ST-HCSS compared to existing state-of-the-art soft sensors, and demonstrates that the learned hypergraph feature representations aligns well with the sensor data correlations. The code is available at https://github.com/htew0001/ST-HCSS.git
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。