Multi-view subspace clustering (MVSC) has been drawn wide attentions in the area of pattern recognition and data mining. However, for a multi-view dataset with n samples and V views from k clusters, MVSC commonly requires O(Vn2) memory for storing the view-specific graph matrices and O(n3) time for the eigenvalue decomposition of a shared graph matrix. Hence, most of MVSC methods are difficult to handle the large-scale multi-view data problem. To address this issue, this paper proposes an Anchor-based Multi-View Subspace Clustering with Graph Learning (AMVSCGL) method. Instead of constructing a n×n graph matrix, our method generates a shared coefficient matrix with the size of n×k based on few learned view-specific anchors. Moreover, through further merging a graph learning term, this shared coefficient matrix can simultaneously capture the global and local information among multiple views and few learned view-specific anchors for clustering. Experimental results on seven large-scale multi-view data verify our AMVSCGL’s effectiveness and superiority in comparison with some state-of-the-art methods.

Most traditional artificial intelligence-based fault location methods are very dependent on fault signal selection and feature extraction, which is often based on prior knowledge. Further, these methods are usually very sensitive to line parameters and selected fault characteristics, so the generalization performance is poor and cannot be applied to different lines. In order to solve the above problems, this paper proposes a two-terminal fault location fusion model, which combines a convolutional neural network (CNN), an attention module (AM), and multi-head long short-term memory (multi-head-LSTM). First, the CNN is used to accomplish the self-extraction of fault data features. Second, the CBAM (convolutional block attention module) model is embedded into the convolutional neural network to selectively learn fault features autonomously. Furthermore, the LSTM is combined to learn the deep timing characteristics. Finally, a MLP output layer is used to determine the optimal weights to construct a fusion model based on the results of the two-terminal relative fault location model and then output the final location result. Simulation studies show that this method has a high location accuracy, does not require the design of complex feature extraction algorithms, and exhibits good generalization performance for lines with different parameters, which is of great importance for the development of AI-based methods of fault location.

Insulator is one of the most critical components of power transmission lines and its timely and accurate defect detection is considered important to ensure reliable and safe operation of transmission grids. This paper proposes an efficient augmentation method of aerial images captured using the unmanned aerial vehicle for the accurate detection of insulators with self-detonation defects. Through the adoption of the improved Resnet-18 model with the insulator edge features and the Grad-CAM based saliency map generation, the proposed solution can well maintain the vital regions for fine-grained classification in the augmentation process. The proposed solution is extensively assessed in comparison with the CNN-based benchmark methods through experiments. The numerical results indicate that the improved ResNet-18 model with the augmented images outperform the existing solutions and can identify the self-detonation defects with an accuracy of 95.1%.

Background: The condition of the power transformer directly affects the reliability and efficiency of the power system. The dissolved gas analysis (DGA) has been widely recognized as one of the effective methods in the field of transformer fault diagnosis. Objective: To tackle the problem of insufficient single transformer fault data and weak generalization ability of the diagnosis model, this paper proposes a transformer fault diagnosis model based on data cleaning and transfer learning. Methods: 21 kinds of dissolved gas characteristics of the to-be-diagnosed transformer (TDT) and auxiliary transformers (ATs)are selected as fault features to detect transformer fault. The first data cleaning is used for auxiliary fault data (AFD) based on similarity analysis between target fault data (TFD) and AFD. Then the TFD and AFD are all cleaned to remove the singular edge interference data for the second cleaning. The transfer learning algorithm is applied to extract effective information from AFD and train the fault diagnosis model. Results: Test results show that the proposed method can improve the efficiency of fault diagnosis and the accuracy of fault identification Conclusion: The two data cleanings complement each other and both play a role in eliminating bad data and ensuring the accuracy of the fault diagnosis. Transfer learning can effectively extract effective information from AFD and train a better transformer fault diagnotor to improve fault diagnosis accuracy.

With the increasing scale and complexity of powerline construction, the challenges of powerline system operation and maintenance are gradually increasing. The research and application of unmanned aerial vehicle (UAV) Lidar technology for powerline inspections is developing rapidly. The Lidar point cloud and visible light measurement are processed intelligently by the powerline multi-source and heterogeneous data automatic fusion technology. Then the three-dimensional model of the powerline system and electrical equipment is obtained. Consequently, the efficient resolving of point cloud data for powerlines, identification of equipment locations and types are realized. The fast measurement and elaborating modeling of the three-dimensional system for powerlines is obtained, which may effectively and comprehensively show the operation status of powerlines. The point cloud classification algorithm is adopted in this paper. Experimental results demonstrated that the proposed method performed well in the detection accuracy of identification and classification of lines and pylons in a complex environment. The classification accuracies for transmission lines and distribution lines are 97.26% and 95.29% respectively. The average classification accuracies of both lines and pylons are 80.88% and 82.25%, respectively.

With the development of the automatic inspection of unmanned aerial vehicles (UAVs), improving the detection accuracy of insulators will not only help further insulator state detection and fault diagnosis but also contribute to the early landing of the UAVs’ automatic inspection system. In this paper, we propose a data augmentation method based on the random crop to improve the detection accuracy of insulators. Firstly, it ensures the validity of the label by generating a patch that contains the centers of all ground truth boxes. Secondly, it achieves a balance between protecting the ground truth and random cropping by limiting the area ratio of each ground truth box before and after random cropping. We find that these two steps increase the attention of the model to the insulator. On the self-made insulator dataset, the solution achieves 91.2% and 89.3% mAP in YOLOv3 and RetinaNet respectively, which is 3% and 1.5% better than the random crop.