The combination of power intelligent inspection and edge computing plays a crucial role in the construction Internet Things transparent grid. However, as consequence low devices, detection speed model running on devices tends to be slow. Accordingly, fast accurate method line is proposed this article. First, for key component lines, RepVGG, diverse branch block (DBB), efficient channel attention (ECA), improved spatial pyramid pooling (SPP) are utilized improve YOLOv5, giving rise RepYOLO....

Incipient faults in power distribution systems potentially lead to catastrophic failures. Detection of incipient contributes proactive fault management and predictive maintenance, which effectively improves supply reliability. Since the are infrequent transient, few samples can be procured real applications. In this paper, a detection method based on human-level concept learning (HLCL) is proposed address problem. The contains two steps: waveform decomposition (HLWD) hierarchical...

Analogous deployment of phase measurement units (PMUs), the increase data quantum and deregulation energy market, all call for robust state evaluation in large scale power systems. Implementing model based estimators is impracticable as complexity solving high dimension flow equations. In this paper, we first represent massive streaming PMU big random matrix flow. Motivated by exploiting variations covariance data, a novel algorithm then developed on multiple dimensional test. The proposed...

Accurate recognition of distribution line fault types can provide directional guidance for operation and maintenance personnel. Based on the analysis time-frequency features waveform, a recognized method type was proposed in this paper. Through modeling theoretical waveforms different types, characteristic parameters, which could characterize from three aspects, time domain, frequency electric arc, were put forward. Calculation formula extracting parameters according to waveform data...

The switching frequency of power electronic devices has become much higher than before, which brings great challenges to real-time simulators. small time step in high simulations remarkably increases the difficulty satisfy requirement. This article realizes accurate simulation a solid-state transformer (SST) with 50 kHz at 250 ns on field-programmable gate array (FPGA)-based platform. hybrid companion circuit modeling method and compact-electromagnetic transient program (EMTP) algorithm are...

Intelligent perception is the cornerstone of digitalisation power grid. Due to closest connection with users, information ability distribution network directly affects reliability supply. Distribution has a wide range geographical and equipment types. The application intelligent high complexity dynamics under limitation both technology management. Therefore, study first sorts out current status in from three fields including automation, metering systems, inspection. Then, constraints...

The accurate detection of high-frequency transient fault currents in overhead transmission lines is the basis malfunction and diagnosis. This paper proposes a novel differential winding printed circuit board (PCB) Rogowski coil for lines. interference mechanism sensor surrounding line analyzed guideline elimination obtained, then proposed, where branch return PCB were designed to be strictly symmetrical by using joining structure two semi-rings collinear twisted pair windings each semi-ring....

This paper presents a self-powered wireless temperature sensor node for power grid monitoring. With an electromagnetic energy harvester, the can operate without battery. In order to reduce consumption, several techniques, including deep duty-cycle operation, simple chip architecture with only transmitter, and careful control of sleeping power, are adopted, reducing average consumption 3.26 μW. The measurement results show that range is from 0 80 °C resolution 0.8 °C. 2-FSK modulation on...

Partial discharge (PD) localization is an effective way to detect the insulation problem of power equipment. Considering environmental adaptability and low hardware cost, a novel ultrahigh frequency (UHF) PD algorithm based on received signal strength indication (RSSI) fingerprint proposed. The methodology includes two stages: in offline, RSSI map established by filed test BP neural network trained. Particle swarm optimization (PSO) also adopted choose initial weight network. In online...

This paper presents a novel energy-harvesting model which takes the primary current, secondary turns, dimension, magnitude of magnetic flux density B, and core loss resistance into consideration systematically. The relationship among potential maximum output power, dimension energy harvesting coil (EHC), load type EHC, turns is predicted by theoretical analysis further verified experiments. A high power harvester also developed tested. It shown that this 0.7 mW/g at 10 A, more than 2 times...

This paper presents a novel and analytical approach to identifying lightning strike after it has struck an overhead transmission line. The identification method is mainly based on the traveling waves' time-domain parameters, such as polarity, amplitude, half-wavelength. main differences in these parameters across different types are analyzed. Subsequently, robust algorithm proposed. An instrumentation system implemented verify algorithm. overall performances of methodology demonstrated using...

Intelligent inspection robots widely applied in substations are required to capture the image consistent with calibration during routine of electrical equipment. However, it is a challenging work for robot meeting requirement due navigation error and mechanical wear. To address this problem, an active pose relocalization (APR) method proposed article. Specifically, model describing relationship between pixel plane established. Then, decoupling three-stage proportional–integral control...

Distribution of network repair scheduling after disasters (DNRSD) is important for developing a reasonable strategy and improving the efficiency distribution disasters. This study considers two cooperative relationships in model, namely, simultaneous cooperation (SC) ordered (OC), proposes new post-disaster multiple model (MCM). Compared with conventional modeling, MCM can help to adjust strategies prevent from being delayed while implementation. The original problem divided into stages,...

As a new method for power line inspection, unmanned aerial vehicle (UAV)-based inspection is efficient and low-cost. Since the flight speed of UAV fast, target auto-tracking photographing airborne equipments including visual-light camera, infrared thermal imager ultraviolet imager, very important useful function. In this work, system suitable UAV-based built, based on system, an algorithm used proposed. Theories coordinate transformation three systems (geodetic geocentric rectangular NEU...

Miniaturisation, low cost, and easy live installation are development directions of phasor measuring unit (PMU) in power distribution network lines. Here, a new distributed PMU device for wide area measurement system was designed. It gained energy from the line by high-density inductive draw-out module, measured current voltage waveforms PCB Rogowski coils spatial capacitive divider, respectively, achieved collection whole synchronous sampling. provided solution to At present, prototypes...

Image fusion has become an active and promising research topic in image processing. It provides effective way to combine several source images form a composite with more detailed information than any one of the images. An FDST-PCNN framework, which integrates finite discrete shearlet transform (FDST) pulse-coupled neural network (PCNN), is proposed possess higher ability enhance effects. We first propose structure-based saliency (SBS) map clear important features image. The SBS combines...

<abstract> <p>Short-term traffic flow prediction is crucial for intelligent transport systems and mitigating congestion. Therefore, precise of real-time conditions becoming more important. Currently, the existing models lack ability to effectively extract spatio-temporal characteristics fail adequately account impact non-linear noise. To address these issues, study proposes a hybrid short-term model based on characteristics. First, method decomposes initial sequence data into...

The electric vehicle (EV) has been popular in recent years, which also brings huge challenges to the distribution network due its energy instability. In order consider economic factors of dispatching these distributed renewable resources, voltage variation is important. A novel model‐free method put forward for collaborative management EV resources aggregators network. costs and physical constraints this issue are considered at same time. Multiagent Deep Deterministic Policy Gradient...