Search Results (4)

Equipment fault prediction in maglev train systems poses substantial challenges: fault events are inherently rare, class distributions are severely imbalanced, and individual equipment units are subject to complex spatial and functional couplings that single-device statistical approaches fundamentally cannot capture. To address these challenges, this study proposes a Knowledge Graph-driven Graph Neural Network (KG-GNN) framework. A fault knowledge graph encompassing equipment, fault, temporal, and environmental entities is constructed to unify multi-source maintenance data. Graph connectivity is established via three spatial relation types (co-location, co-zone, and co-level), with edge weights derived from Laplacian-smoothed Lift scores quantifying fault co-occurrence strength. A two-layer GATv2Conv-based graph attention network is designed: the first layer employs four-head attention with explicit edge-weight integration to capture heterogeneous neighborhood influences, while the second layer produces compact node embeddings via single-head attention. A Top-20 sparsification strategy suppresses weak-association noise, and training under severe class imbalance is stabilized through Focal Loss and F2-Score-guided early stopping. On the test set, the proposed method achieves an F2-Score of 0.5703, Recall of 0.6825, and AUC-ROC of 0.9329 (single-run evaluation); multi-seed evaluation (5 seeds) yields F2 = 0.5645 ± 0.0035, Recall = 0.6789 ± 0.0095, and AUC-ROC = 0.9298 ± 0.0026, outperforming the MLP baseline by 18.3% in F2-Score and substantially exceeding GCN (F2 = 0.1476 ± 0.0176) and GATConv (F2 = 0.4284 ± 0.0097). Ablation studies confirm the individual contributions of authentic graph topology, precise edge weighting, and graph sparsification to overall performance. Full article

The exhaust gas temperature (EGT) of the gas generator is a critical indicator for the health management system of a marine gas turbine engine. Therefore, EGT prediction can not only support predictive maintenance decision-making but also serves as a reliable virtual sensor for EGT measurement. However, the engine EGT exhibits strongly nonlinear coupling relationships with other gas path variables, which causes challenges for data-driven prediction. Graph neural networks (GNNs) are particularly effective in capturing the coupling relationships among gas path sensor variables. However, conventional static graph structures fail to characterize the varying coupling strengths under different operating conditions. In this study, a thermodynamic knowledge-driven graph attention network (TKD-GAT) method is proposed for accurate and robust EGT prediction. First, a physics-guided graph topology is constructed based on the gas turbine thermodynamic equations. Subsequently, a multi-head attention mechanism is introduced to generate edge weights that capture the varying thermodynamic coupling strengths under different operation conditions. The proposed model is evaluated on a real-world LM2500 gas turbine, which is widely used in modern propulsion systems of commercial and military ships. The ablation study confirms that the thermodynamic knowledge-driven graph topology and the attention mechanism-based edge weights are both necessary to enhance the EGT prediction performance. The TKD-GAT model shows the best performance with an RMSE of 0.446% and an R² of 0.971 compared with state-of-the-art models. The paired t-test and effect size measurement (Cohen’s d) statistically confirm the significance of performance improvements. The statistical results from multiple independent experiments prove the stability of the TKD-GAT model. Additionally, the model achieves a competitive computational cost despite the integration of a physics-guided graph topology and attention mechanisms. Crucially, an interpretability analysis confirms that the learned attention weights adhere to thermodynamic principles under different operation conditions. The proposed TKD-GAT model provides an effective solution for EGT prediction in health management systems. Full article

Financial fraud detection is critical to modern economic security, yet remains challenging due to collusive group behavior, temporal drift, and severe class imbalance. Most existing graph neural network (GNN) detectors rely on pairwise edges and correlation-driven learning, which limits their ability to represent high-order group interactions and makes them vulnerable to spurious environmental cues (e.g., hubs or temporal bursts) that correlate with labels but are not necessarily causal. We propose Causal-DHG, a dynamic hypergraph framework that integrates hypergraph modeling, causal intervention, and multi-view contrastive learning. First, we construct label-agnostic hyperedges from publicly available metadata to capture high-order group structures. Second, a Multi-Head Spatio-Temporal Hypergraph Attention encoder models group-wise dependencies and their temporal evolution. Third, a Causal Disentanglement Module decomposes representations into causal and environment-related factors using HSIC regularization, and a dictionary-based backdoor adjustment approximates the interventional prediction $P(Y\mid do(C\left)\right)$ to suppress spurious correlations. Finally, we employ self-supervised multi-view contrastive learning with mild hypergraph augmentations to leverage unlabeled data and stabilize training. Experiments on YelpChi, Amazon, and DGraph-Fin show consistent gains in AUC/F1 over strong baselines such as CARE-GNN and PC-GNN, together with improved robustness under feature and structural perturbations. Full article

The vehicle routing problem (VRP), as one of the classic combinatorial optimization problems, has garnered widespread attention in recent years. Existing deep reinforcement learning (DRL)-based methods predominantly focus on node information, neglecting the edge information inherent in the graph structure. Moreover, the solution trajectories produced by these methods tend to exhibit limited diversity, hindering a thorough exploration of the solution space. In this work, we propose a novel Edge-Driven Multiple Trajectory Attention Model (E-MTAM) to solve VRPs with various scales. Our model is built upon the encoder–decoder architecture, incorporating an edge-driven multi-head attention (EDMHA) block within the encoder to better utilize edge information. During the decoding process, we enhance graph embeddings with visitation information, integrating dynamic updates into static graph embeddings. Additionally, we employ a multi-decoder architecture and introduce a regularization term to encourage the generation of diverse trajectories, thus promoting solution diversity. We conduct comprehensive experiments on three types of VRPs: (1) traveling salesman problem (TSP), (2) capacitated vehicle routing problem (CVRP), and (3) orienteering problem (OP). The experimental results demonstrate that our model outperforms existing DRL-based methods and most traditional heuristic approaches, while also exhibiting strong generalization across problems of different scales. Full article