Object detection of overhead transmission lines is a solution for promoting inspection efficiency for power companies. However, aerial images contain many complex backgrounds and small objects, and traditional algorithms are incompetent in the identification of details of power transmission lines accurately. To address this problem, this paper develops an object detection method based on optimized You Only Look Once v5-small (YOLOv5s). This method is designed to be engineering-friendly, with the objective of maximal detection accuracy and computation simplicity. Firstly, to improve the detecting accuracy of small objects, a larger scale detection layer and jump connections are added to the network. Secondly, a self-attention mechanism is adopted to merge the feature relationships between spatial and channel dimensions, which could suppress the interference of complex backgrounds and boost the salience of objects. In addition, a small object enhanced Complete Intersection over Union (CIoU) is put forward as the loss function of the bounding box regression. This loss function could increase the derived loss for small objects automatically, thereby improving the detection of small objects. Furthermore, based on the scaling factors of batch-normalization layers, a pruning method is adopted to reduce the parameters and achieve a lightweight method. Finally, case studies are fulfilled by comparing the proposed method with classic YOLOv5s, which demonstrate that the detection accuracy is increased by 4%, the model size is reduced by 58%, and the detection speed is raised by 3.3%.

Deep learning has advanced consumer electronics, particularly in predictive maintenance and resource optimization. Within the consumer internet of vehicles (CIoV) framework, these advancements have led to smarter, and more interconnected systems, improving vehicle management. As electric vehicles (EVs) become more common, accurately predicting the remaining useful life (RUL) of EV batteries has become a critical challenge. Varied EV usage patterns and conditions create complex battery degradation mechanisms, limiting traditional prediction models. To address such issues, we propose a hybrid deep learning model combining K-shape clustering with transformer networks for RUL prediction of EV batteries within the CIoV framework. This model leverages a cloud-based architecture, primarily composed of a clustering module and a prediction module. Within this framework, operational data from EVs in various scenarios are aggregated and clustered by adopting the K-shape method based on degradation trends, resulting in sub-databases. Additionally, a transformer-based RUL prediction model, integrated with typical capacity curves, is proposed to mitigate cumulative prediction errors and capture long-range dependencies within each sub-database. Extensive simulations and real-world experiments demonstrate that the proposed model not only achieves a higher prediction accuracy, but also excels in complex usage scenarios, significantly enhancing RUL prediction of EV batteries in CIoV environments.

Supervisory control and data acquisition (SCADA) systems are widely utilized in power equipment for condition monitoring. For the collected data, there generally exists a problem—missing data of different types and patterns. This leads to the poor quality and utilization difficulties of the collected data. To address this problem, this paper customizes methodology that combines an asymmetric denoising autoencoder (ADAE) and moving average filter (MAF) to perform accurate missing data imputation. First, convolution and gated recurrent unit (GRU) are applied to the encoder of the ADAE, while the decoder still utilizes the fully connected layers to form an asymmetric network structure. The ADAE extracts the local periodic and temporal features from monitoring data and then decodes the features to realize the imputation of the multi-type missing. On this basis, according to the continuity of power data in the time domain, the MAF is utilized to fuse the prior knowledge of the neighborhood of missing data to secondarily optimize the imputed data. Case studies reveal that the developed method achieves greater accuracy compared to existing models. This paper adopts experiments under different scenarios to justify that the MAF-ADAE method applies to actual power equipment monitoring data imputation.

In recent computer vision research, the pursuit of improved classification performance often leads to the adoption of complex, large-scale models. However, the actual deployment of such extensive models poses significant challenges in environments constrained by limited computing power and storage capacity. Consequently, this study is dedicated to addressing these challenges by focusing on innovative methods that enhance the classification performance of lightweight models. We propose a novel method to compress the knowledge learned by a large model into a lightweight one so that the latter can also achieve good performance in few-shot classification tasks. Specifically, we propose a dual-faceted knowledge distillation strategy that combines output-based and intermediate feature-based methods. The output-based method concentrates on distilling knowledge related to base class labels, while the intermediate feature-based approach, augmented by feature error distribution calibration, tackles the potential non-Gaussian nature of feature deviations, thereby boosting the effectiveness of knowledge transfer. Experiments conducted on MiniImageNet, CIFAR-FS, and CUB datasets demonstrate the superior performance of our method over state-of-the-art lightweight models, particularly in five-way one-shot and five-way five-shot tasks.