Non-intrusive temperature rise fault-identification of distribution cabinet based on tensor block-matching

In this study,a novel non-intrusive temperature rise fault-identification method for a distribution cabinet based on tensor block-matching is proposed.Two-stage data repair is used to reconstruct the temperature-field information to support the demand for temperature rise fault-identification of non-intrusive distribution cabinets.In the coarse-repair stage,this method is based on the outside temperature information of the distribution cabinet,using tensor block-matching technology to search for an appropriate tensor block in the temperature-field tensor dictionary,filling the target space area from the outside to the inside,and realizing the reconstruction of the three-dimensional temperature field inside the distribution cabinet.In the fine-repair stage,tensor super-resolution technology is used to fill the temperature field obtained from coarse repair to realize the smoothing of the temperature-field information inside the distribution cabinet.Non-intrusive temperature rise fault-identification is realized by setting clustering rules and temperature thresholds to compare the location of the heat source with the location of the distribution cabinet components.The simulation results show that the temperature-field reconstruction error is reduced by 82.42%compared with the traditional technology,and the temperature rise fault-identification accuracy is greater than 86%,verifying the feasibility and effectiveness of the temperature-field reconstruction and temperature rise fault-identification.

Repulsive firefly algorithm-based optimal switching device placement in power distribution systems

To achieve optimal configuration of switching devices in a power distribution system,this paper proposes a repulsive firefly algorithm-based optimal switching device placement method.In this method,the influence of territorial repulsion during firefly courtship is considered.The algorithm is practically applied to optimize the position and quantity of switching devices,while avoiding its convergence to the local optimal solution.The experimental simulation results have showed that the proposed repulsive firefly algorithm is feasible and effective,with satisfying global search capability and convergence speed,holding potential applications in setting value calculation of relay protection and distribution network automation control.

Image sequence-based risk behavior detection of power operation inspection personnel

A novel image sequence-based risk behavior detection method to achieve high-precision risk behavior detection for power maintenance personnel is proposed in this paper.In this method,the original image sequence data is first separated from the foreground and background.Then,the free anchor frame detection method is used in the foreground image to detect the personnel and correct their direction.Finally,human posture nodes are extracted from each frame of the image sequence,which are then used to identify the abnormal behavior of the human.Simulation experiment results demonstrate that the proposed algorithm has significant advantages in terms of the accuracy of human posture node detection and risk behavior identification.

THz Wave Detection of Gap Defects Based on a Convolutional Neural Network Improved by a Residual Shrinkage Network

Internal air gap is a serious type of defect in the insulation equipment,which threatens the safe operation of the power grid.In order to diagnose the position and thickness of the internal air gap,this paper proposes a terahertz wave detection method based on wavelet analysis and a CNN(convolution neural network)model.According to the time-frequency characteristics of the wavelet cluster,the calculation method of air gap depth is proposed.To determine the thickness of the internal air gap,the performances of several classification methods,such as waveform feature analysis,Bayes,MLP(Multi-layer Perceptron),SVM(Support Vector Machine)and CNN are compared.The results show that the CNN modified by a residual shrinkage network and SVM(CNN-RSN-SVM)has the best performance.By adjusting the parameters,the classification accuracy of the CNN-RSN-SVM model can be elevated to 98.91%.Furthermore,the 3D imaging method of air gap defect based on wavelet analysis and CNNRSN-SVM classification model is formed.