Power cable tunnels are typical enclosed cable-routing spaces in which cable overheating, insulation aging, and partial discharge may gradually develop into fire hazards. During the early stage of cable fires, abnormal sensor responses are often weak, localized, and continuously evolving, which increases the difficulty of early warning based on a single sensor or a single temporal feature. Motivated by cable fire early warning in power cable tunnels, this study uses cable-fire records from a publicly available indoor EN 54 fire-test-room dataset with distributed multi-sensor nodes to evaluate the proposed model under controlled laboratory conditions. In monitoring scenarios with fixed sensor nodes, temporal-only modeling methods often struggle to simultaneously characterize short-term variations, temporal evolution, and spatial differences in node responses. To address this limitation, this study proposes a multi-sensor spatiotemporal feature fusion model that integrates a gated recurrent unit (GRU), a Modern Temporal Convolutional Network (ModernTCN), and an enhanced graph convolutional network (GCN+). The proposed model adopts the ModernTCN as the temporal modeling backbone. A GRU module is introduced at the front end to encode local fluctuations and short-term continuous changes between consecutive time steps, while GCN+ is embedded at the intermediate feature stage of the backbone to model spatial correlations and cross-node coordinated responses among fixed sensor nodes. Experimental results show that the proposed model achieves strong classification performance in the cable fire early warning discrimination task, with a test accuracy of 0.9884 and a false negative rate (FNR) reduced to 0.0150. The comparative experimental results indicate that the proposed model achieves better overall performance than typical temporal baseline models. The ablation study further shows that, under the experimental settings of this study, the introduction of GRU and GCN+ leads to overall improvements in the main evaluation metrics, suggesting that both modules provide a certain enhancement to the cable fire early warning discrimination performance of the ModernTCN backbone.

With the widespread adoption of power cables in urban distribution networks, accurate aging assessment remains challenging due to non-uniform aging patterns and severe class imbalance across aging levels. Traditional models, relying on identical training-test distribution assumptions, often fail when encountering unseen operational data. To overcome these limitations, this paper proposes a novel cable aging assessment framework applying feature map-based knowledge distillation (FMKD) and adaptive layer regeneration (LR). The key innovation lies in a dual-phase learning mechanism:(1) The knowledge distillation (KD) module extracts latent cross-category correlations between minority and majority classes, effectively mitigating catastrophic forgetting during updates, (2) A parameter transfer-based LR strategy enables rapid adaptation to new-task data (minority samples) while preserving old-task knowledge. Comprehensive experimental results demonstrate that the model simultaneously optimizes new-task identification (unseen samples) and old-task retention (known samples), achieving satisfactory accuracy across varying data ratios.