Temporal and Heterogeneous Graph Neural Network for Remaining Useful Life Prediction

2024-05-07

IEEE Transactions on Neural Networks and Learning Systems

AI Summary

Industrial systems generate highly dynamic and heterogeneous multi-source sensor data, yet existing graph neural networks (GNNs) based on discrete snapshots fail to capture fine-grained temporal evolution and neglect sensor-type heterogeneity, limiting remaining useful life (RUL) prediction accuracy. To address this, we propose the Temporal Heterogeneous Graph Neural Network (THGNN), the first framework integrating fine-grained temporal graph modeling with sensor-type-aware Feature-wise Linear Modulation (FiLM) for joint characterization of dynamic spatiotemporal dependencies and sensor heterogeneity. THGNN further incorporates a neighborhood historical aggregation module and a dynamic spatial relation learning module to enhance evolutionary pattern modeling. Evaluated on the N-CMAPSS dataset, THGNN reduces RUL prediction error by 19.2% and 31.6% compared to state-of-the-art methods, demonstrating its effectiveness and superiority.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Predicting remaining useful life (RUL) plays a crucial role in the prognostics and health management of industrial systems that involve a variety of interrelated sensors. Given a constant stream of time-series sensory data from such systems, deep learning (DL) models have risen to prominence at identifying complex, nonlinear temporal dependencies in these data. In addition to the temporal dependencies of individual sensors, spatial dependencies emerge as important correlations among these sensors, which can be naturally modeled by a temporal graph that describes time-varying spatial relationships. However, the majority of existing studies have relied on capturing discrete snapshots of this temporal graph, a coarse-grained approach that leads to a loss of temporal information. Moreover, given the variety of heterogeneous sensors, it becomes vital that such inherent heterogeneity is leveraged for RUL prediction in temporal sensor graphs. To capture the nuances of the temporal and spatial relationships and heterogeneous characteristics in an interconnected graph of sensors, we introduce a novel model named temporal and heterogeneous graph neural networks (THGNNs). Specifically, THGNN aggregates historical data from neighboring nodes to accurately capture the temporal dynamics and spatial correlations within the stream of sensor data in a fine-grained manner. Moreover, the model leverages feature-wise linear modulation (FiLM) to address the diversity of sensor types, significantly improving the model's capacity to learn the heterogeneity in the data sources. Finally, we have validated the effectiveness of our approach through comprehensive experiments. Our empirical findings demonstrate significant advancements on the N-CMAPSS dataset, achieving improvements of up to 19.2% and 31.6% in terms of two different evaluation metrics over state-of-the-art methods.

Problem

• Predict Remaining Useful Life (RUL) in industrial systems with interrelated sensors.
• Model temporal and spatial dependencies in sensor data more accurately.
• Address sensor heterogeneity to improve RUL prediction performance.

Innovation

• Temporal and Heterogeneous Graph Neural Networks
• Feature-wise Linear Modulation for sensor diversity
• Fine-grained temporal and spatial correlation capture