Currently, solar photovoltaic (PV) systems are a priority for end-use decarbonization, aimed at reducing reliance on fossil fuels. However, PV systems are typically exposed to outdoor conditions, making them more susceptible to aging and damage. In this paper, a predictive maintenance approach that integrates digital twin technology with the copula-based model is proposed. This integration enables accurate simulation of the PV system’s condition and precise representation of the correlation between the power output of the digital twin and that of the actual system. Given the power output of the digital twin, predictive maintenance is performed based on the conditional cumulative distribution function (CDF) of the actual power output, which is derived from the copula model. A comprehensive case study was conducted to evaluate the performance of the proposed approach named OCAD (Optimal Copula-based Anomaly Detector), which achieved an accuracy of 92.51% and an F1-score of 92.13%. This significantly outperforms conventional models, including SVM, KNN, and ANN, demonstrating the effectiveness of the proposed predictive maintenance strategy.

Precise perception of subtle anomalies in power equipment—such as insulator cracks, conductor corrosion, or foreign intrusions—is vital for ensuring the reliability of smart grids. However, foundational vision-language models (VLMs) like CLIP exhibit poor domain transfer and fail to capture minute defect semantics. We propose VisPower, a curriculum-guided multimodal alignment framework that progressively enhances fine-grained perception through two training stages: (1) Semantic Grounding, leveraging 100 K long-caption pairs to establish a robust linguistic-visual foundation, and (2) Contrastive Refinement, using 24 K region-level and hard-negative samples to strengthen discrimination among visually similar anomalies. Trained on our curated PowerAnomalyVL dataset, VisPower achieves an 18.4% absolute gain in zero-shot retrieval accuracy and a 16.8% improvement in open-vocabulary defect detection (OV-DD) over strong CLIP baselines. These results demonstrate the effectiveness of curriculum-based multimodal alignment for high-stakes industrial anomaly perception.

With the rapid development of energy transition and power system informatization, the efficient integration and feature migration of multimodal power data have become critical challenges for intelligent power systems. Existing methods often overlook fine-grained semantic relationships in cross-modal alignment, leading to low information utilization. This paper proposes a multimodal power sample feature migration method based on dual cross-modal information decoupling. By introducing a fine-grained image–text alignment strategy and a dual-stream attention mechanism, deep integration and efficient migration of multimodal features are achieved. Experiments demonstrate that the proposed method outperforms baseline models (e.g., LLaVA, Qwen) in power scenario description (CSD), event localization (CELC), and knowledge question answering (CKQ), with significant improvements of up to 12.8% in key metrics such as image captioning (IC) and grounded captioning (GC). The method provides a robust solution for multimodal feature migration in power inspection and real-time monitoring, showing high practical value in industrial applications.

Analog gauges are fundamental for data acquisition in numerous industrial sectors, yet the automated reading of these devices is significantly hampered by a scarcity of large-scale, comprehensively annotated datasets. This data bottleneck impedes the development of robust and accurate computer vision algorithms. Here we introduce SyncG, a large-scale synthetic benchmark created to address this critical gap. We developed a generative framework using Blender and Python to produce 20,000 high-resolution, photorealistic gauge images across 145 diverse and challenging environmental settings. Our method allows for precise parametric control over both measurement attributes and visual appearances, ensuring a high degree of diversity and realism. Crucially, we present a fully automated annotation pipeline that generates detailed and accurate ground-truth data for a range of tasks, including object detection, keypoint localization, semantic segmentation, and optical character recognition. By providing this extensive and meticulously annotated benchmark, SyncG facilitates the training and evaluation of sophisticated gauge-reading models and supports the exploration of broader computer vision challenges, such as the interpretation of clock-like graphical representations by multimodal large models.