In recent years, subsynchronous control interaction (SSCI) has frequently taken place in renewable-connected power systems. To counter this issue, utilities have been seeking tools for fast and accurate identification of SSCI events. The main challenges monitoring are the time-varying nature uncertain modes Accordingly, paper presents a simple but effective method that takes advantage intrinsic time-scale decomposition (ITD). purpose is to improve accuracy robustness ITD by incorporating...

In recent years, the proliferation of renewable generations significantly increases severity and possibility subsynchronous oscillations (SSO). These events can result in significant loss generation impose great threats to system stability equipment safefy. Accurate knowledge SSO parameters (SSO frequency, magnitude damping) is crucial for its effective mitigation. This paper presents a method identify based on synchrophasors. The basic idea estimate by analyzing spectral leakage information...

Identifying sources of subsynchronous resonance (SSR) is crucial for understanding and mitigating incidents. Recent studies have shown that SSR impedance power are effective indicators can identify an source. However, the calculation two indexes requires voltage current phasors as inputs, which not directly available from existing online monitoring systems. To address this issue, paper presents a novel method to calculate impedance/power based on synchrophasors provided by wide-area system....

The proportion of new energy sources, such as wind, photovoltaic and hydropower, in the power grid is increasing year by year. In addition, a large number nonlinear loads are connected to grid, resulting frequent quality disturbances (PQDs), which pose challenges stability reliability system. Accurate identification these crucial for effective management protection. Although deep learning methods have high accuracy, their lack interpretability can limit acceptance engineering applications....

<div class="section abstract"><div class="htmlview paragraph">Thermal management system of electric vehicles (EVs) is critical for the vehicle's safety and stability. While maintaining components within their optimal temperature ranges, it also essential to reduce energy consumption thermal system. Firstly, a kind architecture integrated (ITMS) proposed, which can operate in multiple modes meet various demands. Two typical operating vehicle cooling summer heating winter, utilizes...

The detection of forced oscillations, especially distinguishing them from natural has emerged as a major concern in power system stability monitoring. Deep learning (DL) holds significant potential for detecting oscillations correctly. However, existing artificial neural networks (ANNs) face challenges when employed edge devices timely due to their inherent complex computations and high consumption. This paper proposes novel hybrid network that integrates spiking recurrent (SRNN) with long...

With a high proportion of new energy and power electronic equipment connected to the modern system, type subsynchronous oscillation (SSO) is triggered, which affects safe stable operation system. Accurate analysis identification SSO source becomes key studying this problem. This article presents novel method analyze SSOs. First, multisynchrosqueezing transform applied signal get concentrated time–frequency results. Then, ridge tracking utilized identify reconstruct component signals. The...

To avoid power supply hazards caused by cable failures, this paper presents an approach of incipient failure recognition and classification based on variational mode decomposition (VMD) 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 used to construct feature vector as input CNN classify through deep learning. Compared signals directly input, proposed more...

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

Incipient faults in power cables are a serious threat to safety and difficult accurately identify. The traditional pattern recognition method based on feature extraction selection has strong subjectivity. If the key information cannot be extracted accurately, accuracy will directly decrease. To identify incipient cables, this paper combines sparse autoencoder deep belief network form neural network, which relies powerful learning ability of classify various cable fault signals, without...

Cable incipient fault is an intermittent arc fault, and may evolve into a permanent fault. Due to the short duration of conventional overcurrent protection device cannot detect it. A cable identification method proposed in this study, using restricted Boltzmann machine (RBM) stacked autoencoder (SAE). Firstly, disturbance current waveforms data effectively compressed by RBM, which can improve analysis efficiency obtain shallow features data. Then, used as input SAE, optimal network...

In this paper, we propose an unified variational approach for image dehazing and denoising from a single input image. Total variation regularization terms are used in the energy functional. Also, use negative gradient descent method to solve corresponding Euler-Lagrange equations. To obtain good initial values, improve estimation of transmission map with windows adaptive based on dark channel prior which can overcomes block effects. The numerical results demonstrate that our algorithm is...

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 detection, but challenges remain due the small amount of training data and targets with large variations position, shape, scale. To manage these issues, we propose dual attention residual U-net (DAttRes-Unet) within architecture that extensively uses network as well spatial channel-wise modules. overcome...

In this study, an AC transmission line fault ride-through control strategy is studied, which can quickly isolate the points and modular multilevel converter–unified power flow controller (UPFC) when occurs. After cleared, UPFC also be re-put into normal operation quickly. Above all, improve reliability utilisation of UPFC, protect security UPFC.

By scanning static, not moving, objects along both the horizontal and vertical axes instead of one, structured light illumination achieves more accurate robust 3D surface reconstructions but with greater latency on computing point clouds. If is performed only one axis, it has been reported that look-up tables, manually derived from calibration matrices a camera projector, can significantly help to speed up computation; however, nearly impossible derive similar tables for phases scanned two...

The objective of this study is to explore and compare the strength associations between work-related potential traumatic events burnout among operating room nurses based on three different approaches.The followed a multisite cross-sectional design.A stratified sampling method was conducted. Cities in Shandong Province were divided into four groups, two tertiary hospitals randomly selected from all cities each group. A total 361 eligible provided valid questionnaires June November 2019....

According to the correlation between product quality and equipment degradation state, an maintenance policy is designed by integrating periodic inspection control. In this policy, np-chart used monitor abnormal shift of characteristic based on equipment. By considering result corresponding action chosen. Furthermore, optimal model control proposed solved with genetic algorithm. The experimental results validated feasibility model.

To efficiently reconstruct magnetic resonance images (MRI) from highly undersampled measurements by using compressed sensing (CS), in this letter, we propose a hybrid regularization model deep prior and low-rank prior. The local is explored fast flexible denoising convolutional neural network (FFDNet). compensate for 1) the generalization capability of FFDNet on artifact noise caused undersampling K-space 2) inaccurate estimation various ratios, as weighted Schatten p-norm to obtain global...

Abstract Non‐intrusive load monitoring (NILM) is an important technology for deeply mining consumers' internal electricity consumption information, which can improve the level of awareness and significantly demand‐side management capability smart grid. For a long time, traditional NILM faces challenge huge data, training time low accuracy. To address this issue, paper proposes adaptative lightweight seq2subseq model. The model adaptively determines optimum window length active power segment...