With a high proportion of new energy and power electronic equipment connected to the modern power system, a new type of subsynchronous oscillation (SSO) is triggered, which affects the safe and stable operation of the system. Accurate analysis and identification of the SSO source becomes the key to studying this problem. This article presents a novel method to analyze SSOs. First, multisynchrosqueezing transform is applied to the signal to get the concentrated time–frequency analysis results. Then, the ridge tracking method is utilized to identify and reconstruct the subsynchronous component signals. The method of dissipating energy flow is applied to locate the source and sink of the SSO in the subsynchronous component signals. The performances of the proposed method are verified using electromagnetic transient simulations in a three-wind farms system and a modified IEEE 10-generator 39-bus New England power system.

Incipient faults in power cables are a serious threat to power safety and are difficult to accurately identify. The traditional pattern recognition method based on feature extraction and feature selection has strong subjectivity. If the key feature information cannot be extracted accurately, the recognition accuracy will directly decrease. To accurately identify incipient faults in power cables, this paper combines a sparse autoencoder and a deep belief network to form a deep neural network, which relies on the powerful learning ability of the neural network to classify and identify various cable fault signals, without requiring preprocessing operations for the fault signals. The experimental results demonstrate that the proposed approach can effectively identify cable incipient faults from other disturbances with a similar overcurrent phenomenon and has a higher recognition accuracy and reliability than the traditional pattern recognition method.

Frequent occurrences of blackouts have made the reliability of power grid much more concerned in the last few years. Recent work reveals that some important lines can have critical impact on the blackouts in power system. Based on the newest progress in the field of complex network theory, power grids are treated as small world networks. This paper calculates the topological characteristic parameters of the power grid, investigates the tolerance of power grid against random failures and targeted attacks, and proposes a methodology for the study of the relationship between small-world effects and the reliability of power grid. The failure simulation results of a practical large power grid show that the power grid is much robust facing random failures but becomes much vulnerable in front of attacks on selective nodes.

To avoid power supply hazards caused by cable failures, this paper presents an approach of incipient cable failure recognition and classification based on variational mode decomposition (VMD) and a convolutional neural network (CNN). By using VMD, the original current signal is decomposed into seven modes with different center frequencies. Then, 42 features are extracted for the seven modes and used to construct a feature vector as input of the CNN to classify incipient cable failure through deep learning. Compared with using the original signals directly as the CNN input, the proposed approach is more efficient and robust. Experiments on different classifiers, namely, the decision tree (DT), K-nearest neighbor (KNN), BP neural network (BP) and support vector machine (SVM), and show that the CNN outperforms the other classifiers in terms of accuracy.

By scanning static, not moving, objects along both the horizontal and vertical axes instead of one, structured light illumination achieves more accurate and robust 3D surface reconstructions but with greater latency on computing 3D point clouds. If scanning is performed along only one axis, it has been reported that look-up tables, manually derived from the calibration matrices of a camera and a projector, can significantly help to speed up computation; however, it has been nearly impossible to manually derive similar look-up tables for phases scanned along two axes. In this Letter, we bridge this divide by introducing the constraint of epipolar geometry to automatically compute look-up tables and thus, significantly speed up computing 3D point clouds with only basic arithmetic operations rather than time-consuming matrix computations. Experimental results show that the proposed method, using only single-thread CPU computing, reduces process latency by an order of magnitude.

Accurately detecting oil leakage from a power transformer is important to maintain its normal operation. Deep learning (DL) methods have achieved satisfactory performance in automatic oil detection, but challenges remain due to the small amount of training data and oil targets with large variations in position, shape, and scale. To manage these issues, we propose a dual attention residual U-net (DAttRes-Unet) within a U-net architecture that extensively uses a residual network as well as spatial and channel-wise attention modules. To overcome the vanishing gradient problem due to deeper layers and a small amount of training data, a residual module from ResNet18 is used to construct the encoder path in the U-net framework. Meanwhile, to overcome the issue of training difficulty for the network, inspired by the advantage of transfer learning, initial network parameters in the encoder are obtained from the pre-trained ResNet18 on the ImageNet dataset. Further, in the decoder path, spatial attention and channel attention are integrated to highlight oil-stained regions while suppressing the background or irrelevant parts/channels. To facilitate the acquisition of the fluorescence images of the transformer, we designed a portable acquisition device integrating an ultraviolet light source and a digital camera. The proposed network is trained on the amount of fluorescence images after data augmentation is used and tested on actual fluorescence images. The experiment results show that the proposed DAttRes-Unet network can recognize oil-stained regions with a high accuracy of $98.49\%$ for various shapes and scales of oil leakage.