Because insulators provide electrical insulation and mechanical support for electric transmission lines, these components are of paramount importance to safe and reliable operations of power systems. However, insulators are often considered to be prone to different faults, e.g., bunch-drop, which demands a novel solution for accurate fault-detection and fault-location. Current research efforts have primarily focused on the bunch-drop fault of glass insulators, and the study of ceramic insulators has not been reported to date. To this end, this paper proposes an algorithmic solution for bunch-drop fault detection for both glass and ceramic insulators based on spatial morphological features, which can be integrated into an unmanned aerial vehicle (UAV)-based inspection system. Color models can be established based on the unique color features of both glass and ceramic insulators. Next, the target areas of the insulators can be identified according to the color determination combined with the insulator’s spatial features. The target area is morphologically processed to highlight the fault location, and the rules are established based on the spatial feature differences between the insulators with and without faults. Consequently, the fault location can be accurately identified, and the coordinates can be determined. The performance of the proposed solution is evaluated in comparison with existing solutions. The numerical results demonstrate that the proposed solution can detect bunch-drop faults of insulators with a better than average detection rate. In addition, the performance is assessed and validated in terms of robustness and real-time performance.

Bolts are the most numerous fasteners in transmission lines and are prone to losing their split pins. How to realize the automatic pin-missing defect detection for bolts in transmission lines so as to achieve timely and efficient trouble shooting is a difficult problem and the long-term research target of power systems. In this paper, an automatic detection model called Automatic Visual Shape Clustering Network (AVSCNet) for pin-missing defect is constructed. Firstly, an unsupervised clustering method for the visual shapes of bolts is proposed and applied to construct a defect detection model which can learn the difference of visual shape. Next, three deep convolutional neural network optimization methods are used in the model: the feature enhancement, feature fusion and region feature extraction. The defect detection results are obtained by applying the regression calculation and classification to the regional features. In this paper, the object detection model of different networks is used to test the dataset of pin-missing defect constructed by the aerial images of transmission lines from multiple locations, and it is evaluated by various indicators and is fully verified. The results show that our method can achieve considerably satisfactory detection effect.

In the detection of insulator defects on transmission lines, the detection precision is still not ideal, primarily attributed to the significant variation in target scale and complex image backgrounds. We propose the multiscale channel information (MCI)-global-local attention (GLA), a plug-in designed for YOLO series models, featuring two modules: the MCI extraction module and the GLA based on context information module (GLA-CI). MCI comprehensively extracts and utilizes multiscale feature map information, while GLA-CI captures both global context information and local spatial details, thereby augmenting the learning capability of networks. Experimental results indicate that the MCI-GLA plug-in improves the average precision (AP) of YOLOv4 to YOLOv8 models in detecting insulator breakage defects by 7.3%, 4.6%, 4.5%, 4.0%, and 5.3%, respectively. In particular, YOLOv7+MCI-GLA exhibits superior precision and inference time compared to other methods on self-constructed and public datasets. The code for this article can be found at https://github.com/falian0527/MCI-GLA .

Aiming at the problems of complex background, tiny-size objects, long-tailed distribution, and so on, a hybrid knowledge region-based convolutional neural network (HK R-CNN) is proposed to detect multiple fittings in aerial images of transmission lines. First, the structure combination rules of transmission line fittings are studied, and the relationships of co-occurrence connection and spatial location between fittings are effectively extracted through a data-driven way. Second, the position-sensitive score map (PSSM) is utilized to express the immobilized connection structure of the fittings and extract their visual features. Finally, distinct relationship forms are instantiated by the integrated knowledge modules based on graph learning. The proposed model can enhance the corresponding visual features and realize fitting classification and position regression. Experimental results show that the proposed model can accurately detect the multiple fittings on transmission lines, and the detection performance for sample deficiency and tiny-size fittings is improved significantly compared to the commonly used high-performance model, Faster R-CNN.

Transmission lines’ status detection and fault diagnosis are based on the high-accuracy detection of typical fittings in aerial inspection photographs. Detecting tiny-size fittings in complicated sceneries is still an unresolved issue, nevertheless, because of the constraints of the small number of feature pixels. Considering the characteristics of fitting connection structures, we proposed a novel method named context-based graph reasoning model (CGRM), which is based on multiscale context, self-attention map, and graph learning. This proposed model includes one graph-based global context (GGC) subnetwork and one multiscale local context (MLC) subnetwork. The GGC effectively extracted the pixel-level global map based on multihead attention mechanism to capture global context and the graph convolutional neural network (GCN) was further used for reasoning. The MLC exploited the internal and external contextual information of multiscale for each unique proposal to capture its local context. The final detection result is then reached by fusing the global and local circumstances. Experimental results well demonstrate the superiority of the proposed model for fitting detection. In addition, compared with the original Faster R-CNN, the detection accuracy of CGRM is increased by 16.3%. It also provides a new idea for general object detection of tiny-size targets.

Aiming at the problems of complex background, diverse shapes, and object occlusion in aerial images, a cascade reasoning graph network (CRGN) is proposed for multi-fitting detection on transmission lines. First of all, for these three problems mentioned above, co-occurrence knowledge, semantic knowledge, and spatial knowledge were constructed to represent the co-relation of objects by analyzing the characteristics of the transmission line fittings. Next, the Supervised Graph Learning (SGL), Graph Attention network (GAT), and Graph Convolutional Network (GCN) were employed to reason corresponding knowledge. In addition, to generate more accurate proposals for the graph reasoning module, resampling was carried out through the cascade network. Finally, the enhanced features were fused with the original visual features to recognize and position the fittings. Test results show that CRGN can improve the detection effect of multi-fittings on the transmission line, especially for some hard-detection fittings.