Bolted connections are extensively utilized in aerospace, civil, and mechanical systems for structural assembly. However, inevitable structural vibrations can induce bolt loosening, leading to preload reduction and potential structural failure. Early-stage preload degradation, particularly during initial loosening, is often undetectable by conventional monitoring methods due to limited sensitivity and poor noise resilience. To address these limitations, this study proposes an intelligent bolt preload monitoring framework that combines electromechanical impedance (EMI) signal analysis with a parallel deep learning architecture. A multiphysics-coupled model of flange joint connections is developed to reveal the nonlinear relationships between preload degradation and changes in EMI conductance spectra, specifically resonance peak shifts and amplitude attenuation. Based on this insight, a parallel convolutional neural network (P-CNN) is designed, employing dual branches with 1 × 3 and 1 × 7 convolutional kernels to extract local and global spectral features, respectively. The architecture integrates dilated convolution to expand frequency–domain receptive fields and an enhanced SENet-based channel attention mechanism to adaptively highlight informative frequency bands. Experimental validation on a flange-bolt platform demonstrates that the proposed P-CNN achieves 99.86% classification accuracy, outperforming traditional CNNs by 20.65%. Moreover, the model maintains over 95% accuracy with only 25% of the original training samples, confirming its robustness and data efficiency. The results demonstrate the feasibility and scalability of the proposed approach for real-time, small-sample, and noise-resilient structural health monitoring of bolted connections.

To address the insufficient fusion of electromechanical impedance (EMI) response features from multiple sensors and the limited characterization of spatial relationships between sensors and bolt nodes in four-bolt connection structures, this study proposes an improved graph convolutional network (GCN) model integrating Batch Normalization (BN) and Distance Weighting (DW) strategies for bolt preload-loss state identification. First, PZT sensor nodes and bolt nodes are jointly represented as a graph structure, and the correlation coefficient deviation (CCD) is extracted as the EMI response feature. Then, a weighted adjacency matrix is constructed according to the geometric distances between sensor nodes and bolt nodes to describe the spatial coupling relationships among different nodes. Subsequently, the weighted adjacency matrix and node features are input into the GCN, and a BN layer is introduced after the graph convolutional layers to reduce the influence of multi-channel feature distribution variations on model training stability. Experimental results on a four-bolt connection structure show that the proposed GCN-BN-DW model outperforms the Basic GCN, GCN-BN, GCN-DW, and several benchmark models in terms of prediction accuracy and stability. Under the strict five-fold cross-validation protocol, the proposed model achieves a test MAE of $2.400\pm 0.100$, RMSE of $3.302\pm 0.239$, MASE of $0.300\pm 0.013$, and $R^2$ of $0.821\pm 0.033$. These results indicate that the proposed model can effectively integrate multi-sensor EMI features and sensor–bolt spatial relationships, providing a feasible graph-based modeling approach for bolt preload-loss state identification.