ST-HCSS: Deep Spatio-Temporal Hypergraph Convolutional Neural Network for Soft Sensing

2025-01-02

AI Summary

Industrial soft sensing faces challenges in modeling high-order nonlinear dynamics of sensor time-series data and lacks prior knowledge of multi-sensor structural dependencies. Method: This paper proposes the first end-to-end deep Spatio-Temporal Hypergraph Convolutional Network (ST-HGCN). It pioneers hypergraph learning in soft sensing by introducing learnable hyperedges for adaptive, structure-agnostic high-order relational modeling. A gated temporal convolution coupled with hypergraph convolution enables joint spatio-temporal feature propagation, unifying dynamic evolution and high-order multi-sensor dependencies. Contributions/Results: ST-HGCN achieves significant improvements over state-of-the-art methods on multiple industrial soft sensor benchmarks. The learned hypergraph topology exhibits strong consistency with underlying physical interconnections. The implementation is publicly available.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

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

Problem

• Soft Sensing
• Time-Space Information Processing
• Advanced Computational Networks

Innovation

• ST-HCSS Network
• Soft Sensing
• Temporal and Spatial Optimization