Insulators are essential components in power transmission lines. Due to the harsh variations in bad environments, insulators may experience faults. Detecting these insulator faults promptly and effectively is an urgent issue. To rapidly and accurately locate insulators and their faulty regions in aerial images of insulators with complex backgrounds and varying fault sizes, this paper proposes an improved YOLOv8 algorithm for the detection of multiple insulator fault types (MFI-YOLO). This algorithm achieved target feature extraction in complex background images by replacing the C2F network constructed by fusing the GhostNet and multi-scale asymmetric convolution (MSA-GhostBlock). Furthermore, in the feature fusion stage, a multi-scale feature fusion structure called ResPANet, based on residual skip connections, was constructed to replace the PANet. This enhancement aims to improve the network detection accuracy in multi-target scenarios. Finally, to evaluate the algorithm's performance, this study constructed a target detection dataset containing four types of insulators: normal, self-explosive, damaged, and flashover. Experimental results indicate that, compared to the original model, the improved model has increased mean accuracy from 89.2% to 93.9%. The designed model exhibits high detection accuracy in the insulator and its three fault categories, especially for some hard-to-detect fitting.

The accuracy of insulators and their defect identification by UAVs (unmanned aerial vehicles) in transmission-line inspection needs to be further improved, and the model size of the detection algorithm is significantly reduced to make it more suitable for edge-end deployment. In this paper, the algorithm uses a lightweight GhostNet module to reconstruct the backbone feature extraction network of the YOLOv4 model and employs depthwise separable convolution in the feature fusion layer. The model is lighter on the premise of ensuring the effect of image information extraction. Meanwhile, the ECA-Net channel attention mechanism is embedded into the feature extraction layer and PANet (Path Aggregation Network) to improve the recognition accuracy of the model for small targets. The experimental results show that the size of the improved model is reduced from 244 MB to 42 MB, which is only 17.3% of the original model. At the same time, the mAp of the improved model is 0.77% higher than that of the original model, reaching 95.4%. Moreover, the mAP compared with YOLOv5-s and YOLOX-s, respectively, is improved by 1.98% and 1.29%. Finally, the improved model is deployed into Jetson Xavier NX and run at a speed of 8.8 FPS, which is 4.3 FPS faster than the original model.

The accurate and efficient detection of power lines and towers in aerial drone images with complex backgrounds is crucial for the safety of power grid operations and low-altitude drone flights. In this paper, we propose a new method that enhances the deep learning segmentation model UNet algorithm called TLSUNet. We enhance the UNet algorithm by using a lightweight backbone structure to extract the features and then reconstructing them with contextual information features. In this network model, to reduce its parameters and computational complexity, we adopt DFC-GhostNet (Dubbed Full Connected) as the backbone feature extraction network, which is composed of the DFC-GhostBottleneck structure and uses asymmetric convolution to capture long-distance targets in transmission lines, thus enhancing the model’s extraction capability. Additionally, we design a hybrid feature extraction module based on convolution and a transformer to refine deep semantic features and improve the model’s ability to locate towers and transmission lines in complex environments. Finally, we adopt the up-sampling operator CARAFE (Content-Aware Re-Assembly of FEature) to improve segmentation accuracy by enhancing target restoration using contextual neighborhood pixel information correlation under feature decoding. Our experiments on public aerial photography datasets demonstrate that the improved model requires only 8.3% of the original model’s computational effort and has only 21.4% of the original model’s parameters, while achieving a reduction in inference speed delay by 0.012 s. The segmentation metrics also showed significant improvements, with the mIOU improving from 79.75% to 86.46% and the mDice improving from 87.83% to 92.40%. These results confirm the effectiveness of our proposed method.

To further improve the accuracy and speed of UAV inspection of transmission line insulator defects, this paper proposes an insulator detection and defect identification algorithm based on YOLOv4, which is called DSMH-YOLOv4. In the feature extraction network of the YOLOv4 model, the improved algorithm improves the residual edges of the residual structure based on feature reuse and designs the backbone network D-CSPDarknet53, which greatly reduces the number of parameters and computation of the model. The SA-Net (Shuffle Attention Neural Networks) attention model is embedded in the feature fusion network to strengthen the attention of target features and improve the weight of the target. Multi-head output is added to the output layer to improve the ability of the model to recognize the small target of insulator damage. The experimental results show that the number of parameters of the improved algorithm model is only 25.98% of that of the original model, and the mAP (mean Average Precision) of the insulator and defect is increased from 92.44% to 96.14%, which provides an effective way for the implementation of edge end algorithm deployment.

In transmission lines, bolt fittings are critical components that connect towers and insulators. These fittings are prone to defects, such as loosening or missing bolts, due to natural environmental factors, posing significant risks to the system's operation. Drone inspection images are increasingly used for the intelligent detection of bolt fittings, yet the small size of bolt components and the uneven distribution of sample quantities limit detection accuracy. To address these challenges, this paper proposes a multi-type bolt fitting defect detection algorithm aimed at improving detection accuracy and robustness. To tackle the issue of small target detection, we design a novel down-sampling method that incorporates both global and local feature perception, reducing the loss of small target information. This method is integrated into the Res-PANet, a multi-scale feature fusion structure based on residual skip connections, which compensates for the loss of small target details in high-level semantic features. Additionally, to address the sample imbalance problem, we introduce adaptive class weighting and a Minimum Peripheral Point Distance (MPPD) bounding box similarity constraint to better locate imbalanced sample regions from the loss function perspective. Experimental results, using a detection dataset containing four types of targets—normal bolts, missing pins, loose pins, and missing nuts—demonstrate the effectiveness of the proposed algorithm. Compared to the original YOLOv8 model, the improved model shows a 1.9% accuracy improvement for detecting missing pins, a 3.2% improvement for loose pins, and a 4.2% improvement for missing nuts. The overall mean accuracy increased from 69.5% to 72.1%. These results provide a solid technical foundation for detecting bolt fitting defects in transmission lines, offering significant practical value for future inspection tasks.

In the context of difficulty in detection problems and the limited computing resources of various fault scales in aerial images of transmission line UAV inspections, this paper proposes a TD-YOLO algorithm (YOLO for transmission detection). Firstly, the Ghost module is used to lighten the model’s feature extraction network and prediction network, significantly reducing the number of parameters and the computational effort of the model. Secondly, the spatial and channel attention mechanism scSE (concurrent spatial and channel squeeze and channel excitation) is embedded into the feature fusion network, with PA-Net (path aggregation network) to construct a feature-balanced network, using channel weights and spatial weights as guides to achieving the balancing of multi-level and multi-scale features in the network, significantly improving the detection capability under the coexistence of multiple targets of different categories. Thirdly, a loss function, NWD (normalized Wasserstein distance), is introduced to enhance the detection of small targets, and the fusion ratio of NWD and CIoU is optimized to further compensate for the loss of accuracy caused by the lightweightedness of the model. Finally, a typical fault dataset of transmission lines is built using UAV inspection images for training and testing. The experimental results show that the TD-YOLO algorithm proposed in this article compresses 74.79% of the number of parameters and 66.92% of the calculation amount compared to YOLOv7-Tiny and increases the mAP (mean average precision) by 0.71%. The TD-YOLO was deployed into Jetson Xavier NX to simulate the UAV inspection process and was run at 23.5 FPS with good results. This study offers a reference for power line inspection and provides a possible way to deploy edge computing devices on unmanned aerial vehicles.