Electrical Substation Equipment Research Articles

Infrared image target detection for substation electrical equipment based on improved faster region-based convolutional neural network algorithm.

Substation electrical equipment generates a massive number of infrared images during operation. However, the overall quality of the infrared images is low and it lacks image detail information. When using traditional target detection algorithms for detection, feature extraction poses great difficulties. Therefore, to address this problem, this paper proposes a target detection algorithm based on the improved faster region-based convolutional neural network (Faster R-CNN). It achieves the correct identification of different types of electrical equipment in infrared images. First, the algorithm improves the backbone network of Faster R-CNN for feature extraction. An InResNet structure is proposed to replace the residual block structure of the original ResNet-34 network, which enhances the richness of feature extraction. Second, the rectified linear unit activation function in the original feature extraction network is replaced by the exponential linear unit activation function, and group normalization is used instead of batch normalization as the network normalization method. Then, the dense connection structure is introduced into the ResNet-34 network, and the whole network is called residual dense connection network. Finally, the improved Faster R-CNN is compared to the original Faster R-CNN, a single-shot multibox detector, and you only look once v3 plus spatial pyramid pooling. The experimental results show that the improved algorithm has the highest mean average precision and average recall for most of the substation electrical equipment in infrared images. Moreover, from the confidence level of the detected electrical equipment and the accuracy of the prediction box, the improved Faster R-CNN has the best performance.

Seismic Assessment of Electrical Equipment in Power Substations: A Case Study for Circuit Breakers

Electric power is essential in post-earthquake periods for the continuous functionality of disaster management and emergency services. In addition, interruption of electric power can cause significant economic losses due to downtime of critical facilities. Therefore, it is very important to maintain seismic safety of electric power systems and components. There are existing seismic regulations and standards regarding electric power systems, especially in the United States of America (USA) and Europe. A similar regulation has been prepared recently in Türkiye, which is a country in a seismically active region. This study focuses on the current state of practice regarding the seismic assessment of electrical equipment in power stations and implementation of the regulations on seismic qualification of these systems. Among many electrical equipment, circuit breakers have been selected for case study. The seismic assessment of the selected high voltage equipment has been performed according to the new regulation under the seismic hazard specifically defined for Türkiye. The case study experiment presents the new methodology in evaluating and classifying the seismic response of high voltage electrical equipment and provides insight to the expected behaviour of circuit breakers under earthquake induced action.

Target detection of substation electrical equipment from infrared images using an improved faster regions with convolutional neural network features algorithm

The failure of substation equipment can cause incalculable losses to the economy and power consumption of the whole country. The use of infrared images is a powerful tool to obtain equipment temperature, which can then be used directly to diagnose substation equipment without stopping the operation of the equipment. In this paper, the authors focus on the correct identification of different types of electrical equipment from the infrared images. An improved faster regions with convolutional neural network features (faster R-CNN) algorithm is proposed, which shows very high detection accuracy for substation equipment. Firstly, the backbone of the faster R-CNN is optimised. A new network, the ResNet-30 network, is designed to reduce the redundancy of the ResNet-34 network and increases the proportion of residual blocks in the network in the previous stages. Next, the deep receptive field is combined with the shallow receptive field of the network and a double-shortcut structure with a large convolutional kernel is proposed. This enhances the ability of network feature extraction. A cross-channel shortcut is proposed at the channel transition of the network based on the channel number relationship between the dual-shortcut structures. Finally, the proposed method is compared with faster R-CNNs whose backbones are ResNet-50 plus a feature pyramid network (ResNet-50+FPN), you only look once v3 plus spatial pyramid pooling (YOLOv3+SPP) and a single-shot multibox detector (SSD). The results show that the improved model not only has a smaller number of parameters and low requirements for graphics processing unit (GPU) equipment, but also has the highest mean average precision (mAP) for mostly substation equipment in the test-set. This lays a foundation for fault diagnosis of substation equipment in the future.

A rapid seismic fragility and risk analysis of electrical substation equipment considering modeling uncertainties

This study aims to evaluate the influences of modeling-related uncertainties on the seismic response and fragility function of the four vulnerable components of electrical substation equipment, taking into account the dynamic interaction between apparatuses via bus slider-rigid bus conductors. The 3D finite element model for interconnected disconnect switch- circuit breaker-current transformer-surge arrester system is developed in OpenSees software. A sensitivity analysis is conducted to evaluate and rank the importance of individual random variables on the seismic responses. To incorporate modeling uncertainties into the failure fragility function, probabilistic structural interconnected simulations are generated using the Latin hypercube sampling technique. The fragility curves for each apparatus in the connected system are derived using incremental dynamic analysis (IDA). An efficient procedure based on the endurance time (ET) method is presented for estimating response distributions and fragility parameters of the interconnected apparatuses while considering modeling uncertainty. The proposed approach provides acceptable results compared to those from the IDA while tremendously reducing computer run-time. This investigation also puts forth a rapid detailed seismic risk analysis framework using scenario sampling analysis. To this end, the ET response distributions are exploited as equipment response models within reliability-based risk analysis. Results indicate that the damping ratio and porcelain elastic modulus have a substantial effect on the seismic responses of equipment. In addition, modeling uncertainties affect the median and dispersion values of the failure fragilities by up to −5.9% and +22% on average for all equipment cases, respectively. According to the loss curves, it is observed that the circuit breaker contributes the greatest to the system's overall loss, whereas the surge arrester contributes the least.

Floor response spectra and seismic design method of electrical equipment installed on floor in indoor substation

Electrical equipment installed on floors is a typical type of nonstructural component in indoor substations, which could be subjected to earthquake loading during seismic events. To investigate the seismic design method of floor electrical equipment in indoor substations, simulation models of four whole-indoor substations comprising main control buildings and their floor electrical equipment were established. Seismic response spectrum analyses of main-attachment structures were performed with a high number of ground motions as inputs. Using mathematical statistics and data fitting methods, this research suggested the calculation formula of amplification factor of floor acceleration response spectrum. Specifically, when the periodic ratio of electrical equipment to main control building is in the range of 0.9–1.1, the system would produce a strong resonance-like effect with a peak spectral amplification factor. The floor response spectrum for seismic design was influenced by four factors: equipment importance category, floor position, damping ratio of electrical equipment, and torsion effect of main control building. Following that, a seismic design method especially applicable for electrical equipment installed on floor in indoor substation, which combines amplification factor and calculation method of seismic action indicated in the relevant specification, was presented. Lastly, a typical 220 kV whole-indoor substation was taken as an example to validate the accuracy of the design method highlighted in this article.

Seismic performance improvement using bolt-on isolators on interconnected slender electrical equipment

The slender electrical equipment in substations is fragile to damage during earthquakes owing to the seismically sensitive structure, low material strength, and coupling effects from interconnected equipment. To improve the seismic performance of the slender electrical equipment in the interconnected circuit system, the design and characterization of an assembled isolation system were recommended. The solution was based on a novelty combination application of bolt-on isolators and a support block by reducing the bending stiffness of slender equipment to achieve vibration isolation function. The isolation function test was performed on isolators from characteristics of stiffness variation and damping. Finally, the effectiveness of the proposed isolation system was proved in seismic performance improvement of interconnected slender electrical equipment using a comparison shaking table test, which was performed on a full-scale interconnected circuit, consisting of two ±800kV composite pillar insulators connected by a tubular busbar. Therefore, thus isolation system can provide effective seismic protection for interconnected slender equipment in proper design.

CURRENT TRENDS IN DESIGN OF ELECTRIC SUBSTATIONS

The issue of using modern equipment in the construction and modernization of electrical substations is discussed in the article. 
 The current state of electrical substation equipment is analyzed. It is shown that more than half of the equipment has exhausted its technical resource. The percentage of refusals due to aging has increased significantly. 
 Modern trends in design and new concepts of construction and installation of electrical substations are described. The complete-block technology of construction of electrical substations is considered. 
 The experience of substation reconstruction in Europe is presented. ODD, MTS and GIS technologies are compared. 
 The main suppliers of equipment for electrical substations in Ukraine are characterized. 
 Variants of the use of electric and gas equipment are described.
 Concepts of closed modular construction and "hybrid modules" are given.
 Gradual changes to the traditional for the unified energy system of Ukraine scheme "two working bus systems with a bypass bus system" are presented, depending on the choice of switching devices.
 New schematic solutions for substations on desolderings are provided (the RP scheme of the TP supply voltage on desolderings with a jumper on separate equipment; a typical RP scheme of the TP supply voltage on desolderings on integrated power equipment, the RP scheme of the TP supply voltage on desolderings with a jumper on enlarged cells on an integral power equipment). The advantages and disadvantages of the presented schemes are analyzed. On the basis of a complex analysis, conclusions are made about the advantages and disadvantages of the presented schemes and the criteria for choosing one or another scheme and the corresponding equipment are presented.

Detailed seismic risk analysis of electrical substation equipment using a reliability based approach

Detailed seismic risk analysis of electrical substation equipment using a reliability based approach

Back Flashover Probability of the Overhead Power Line Insulation Taking into Account the Soil Ionization and Frequency Response Features

Back flashovers caused by a lightning strike on an overhead power line tower or overhead ground wire give rise to voltage surges dangerous for the insulation of power substation electrical equipment. A pulse back flashover turns into a short-circuit arc leading to the power line tripping. Calculations of voltage surges in a single–circuit 110 kV power line are carried out using the methods of the grounding devices theory, and the back flashover probability is estimated based on the curve of dangerous currents. The insulation back flashover probability for a power line tower with a ground wire in areas with high-resistance soil is determined by the grounding conductor surge impedance. It is shown that the analysis carried out with taking into account the soil ionization and frequency response features yields an essentially lower back flashover probability. The second ground wire placed under the power line wires reduces the inductance of the ground wires, thereby intensifying the spread of current through the grounding conductors of neighboring towers. This leads to a decreased tower voltage and an increased voltage induced on the wires, thus resulting in a decreased voltage across the insulation voltage and, hence, lower back flashover probability. The factors governing a positive effect from using grounding counterpoises of an overhead power line in areas with high-resistance soil are shown, and the conditions under which this effect is achieved are determined.

Research on the Design of UAV Relay Charging High-rise Platform for Electrical Equipment Live Detection in Substation

The multi-rotor UAV inspection technology has received extensive attention in the live detection of electrical equipment in substations and has begun to be practically applied. However, due to the short endurance and the characteristics of intermittent operations, the UAV needs to frequently travel between the operational airspace and the cabin, which seriously affects the operational efficiency of the inspection. This paper first introduces the traditional substation electrical equipment live detection technology and then summarizes the application of UAV inspection in the substation electrical equipment live detection. Finally, in view of the shortcomings of the existing technology, this paper proposes a design scheme of a relay-charging high-rise platform for live detection and inspection of electrical equipment in substations. The relay charging high-rise platform can be divided into six parts according to the functional structure: high-altitude apron, UAV landing guidance system, UAV automatic binding system, high insulation strength power supply system, and platform monitoring system. In this paper, the overall structure of the relay charging high-level platform and the technical solutions of each component are described in detail. The technical solution can effectively improve the efficiency and safety of multi-rotor UAV inspection operations for live detection of electrical equipment in substations.

Infrared Image Target Detection of Substation Electrical Equipment Using an Improved Faster R-CNN

Infrared camera can be used to monitor the condition of substation electrical equipment. Fast and accurate target detection algorithm is the key for infrared intelligent on-line routing inspection. However, the performance of traditional detection algorithm is poor due to the complex background of substation. To solve this problem, this paper proposes a target detection model based on the improved faster region-based convolutional neural networks (Faster R-CNN), which can be used for automatic detection of five kinds of electrical equipment in substations. The feature extraction network of this model is improved based on VGG16 by abandoning some high-level convolutions to accelerate the training and testing speed. Meanwhile, the 1:3 and 3:1 aspect ratio of anchor are added to improve the detection accuracy of elongated equipment. Experiments are performed on an infrared image dataset of substation to detect five types of equipment. The robustness tests of our model are carried out, too. The results show that our model performs well in detection accuracy and speed, achieving a mean detected accuracy of 95.32% and running at 11 frame/second. In addition, our model is robust to noise and lightness, which is suitable to other substations. Comparing to other models, our model has the highest mAP@0.5 of 92.78%.

Thermal Fault Diagnosis of Electrical Equipment in Substations Using Lightweight Convolutional Neural Network

Real-time equipment condition monitoring is crucial to ensure the regular operation of the electric system. However, the deployed heavy convolutional neural networks (CNNs) are defective for edge computation and offline diagnosis. The purpose of this article is to present a system for detecting overheating faults of substation equipment using infrared photos and U-Net deep learning techniques. First, a stepwise encoder employs a lightweight CNN (LCNN) based on inverted residuals with depthwise separable convolution. The fault location is then decoded in the decoder using stepwise upsampling and nearest-neighbor interpolation. We additionally incorporate low-level detail feature information from the encoder to include additional fault data. Finally, testing findings on our dataset demonstrated the proposed method’s superior reliability and efficiency under a variety of evaluation metrics. Ultimately, we reached a lighter structure and leading estimation with a small training dataset, so our method is well-suited for deployment on mobile devices.

Digital protection of electrical equipment in railway transport

In this scientific study, an analysis of the modernization of the digital protection of AC traction substation electrical equipment in operation, in particular power transformers, the implementation of the basic provisions for the implementation of digital protection of power transformers, finding algorithms for the implementation of both measuring and logic elements of digital protection, mathematical models of digital protection of power transformers are obtained, a method for blocking current protection is implemented, a method is selected finding the setpoints of the stage, obtaining differential protection, the schemes of secondary switching of digital protection are considered, the results of the scientific research carried out in the microprocessor terminal of protection of power transformers.

Numerical modeling for the seismic response of interconnected electrical substation equipment

Numerical modeling for the seismic response of interconnected electrical substation equipment

Comparison of Traditional Image Segmentation Methods Applied to Thermograms of Power Substation Equipment

The variation in the thermal state of electrical energy substation equipment is normally associated with natural wear or equipment failure. This can be detected by infrared thermography, but technically it demands a long time to analyze these images. Computational analysis can allow an automated, more agile, and more efficient analysis to detect overheated regions in thermographic images. Therefore, it is necessary to segment the region of interest in the images; however, the results may diverge depending on the technique used. Thus, this article presents the improvement of four different techniques implemented in Python and applied in a substation under real operating conditions for a period of eleven months. The performance of the four methods was compared using eight statistical performance measures, and the efficiency was measured by the runtime. The segmentation results showed that the methods based on a threshold (Otsu and Histogram-Based Threshold) were fast, with processing times of 0.11 to 0.24 s, but caused excessive segmentation, presenting the lowest accuracy (0.160 and 0.444) and precision (0.004 and 0.049, respectively). The clustering-based methods (Cluster K-means and Fuzzy C-means) showed similar results to each other but were more accurate (0.936 to 1.000), more precise (0.965 to 1.000), and slower, with 2.55 and 38.8 s, respectively, compared to the threshold methods. The Fuzzy C-means method obtained the highest values of specificity, accuracy, and precision among the methods under analysis, followed by the Cluster K-means method.

Novel Spiral-Gap Shielding Shell for a Rogowski Current Sensor

Rogowski current sensors play an important role in detecting the condition of electrical power substation equipment. An electromagnetic field shielding shell is necessary for some of these sensors to operate correctly, especially those with large diameters and small heights. These are used for frequency-response analysis in power transformers. In this study, the magnetic-shielding effectiveness of a normal C-type metal shell was tested and simulated. The distribution and direction of the magnetic field were analyzed using finite-element simulation calculations to reveal the reasons for its poor shielding effectiveness. It was found that the magnetic field induced by an interference current crosses the shell and enters its cavity through the gap in its inner wall. Shells with larger inner-diameter-to-height ratios have worse magnetic-shielding effectiveness. Therefore, a novel shell structure with a spiral gap is proposed here. The magnetic-shielding effectiveness of this new type of shell was analyzed by further simulations and verified in experimental tests. The results showed that a shell with a spiral gap has better shielding effectiveness when it has a long gap. In addition, the spiral gap was found not to inhibit the current-measurement function of the sensor. This provides a new approach to the design of electromagnetic shielding shells for Rogowski sensors.

Compilation of a Local Electrical Insulation Pollution Map in the Sheikh-Najar Industrial Region of Syria

A method for improving the performance reliability of electrical installations under the conditions of polluting the insulation of the 66 and 230 kV overhead lines (OHL) and outdoor switchgears (OSG) in the Sheikh-Najar industrial region near Aleppo, the economic capital of Syria, is considered. According to the relevant regulatory documents, the most efficient approach to selecting the insulation levels is the one based on compiling regional and local insulation pollution maps (IPMs) in the territory where the grid facilities are located. An electronic local IPM in the Sheikh-Najar industrial region was compiled using the characteristics of industrial pollution sources. The article presents the climatic characteristics of the Aleppo city area, the electrical circuit diagram and insulation characteristics of the existing 66 and 230 kV OHLs and OSGs, the characteristics of industrial pollution sources (in terms of produced goods types and amounts), estimated pollution degrees (PD) at various distances from the enterprise boundaries with a circular wind rose, and those adjusted for the real wind rose in the city of Aleppo, and the local IPM of the Sheikh-Najar region drawn using the AutoCAD software. It has been established that there are zones with insulation pollution degrees 2, 3 and 4 in the Sheikh-Najar industrial region territory. Based on the study results, recommendations have been elaborated for increasing the specific effective creepage distance of the OHL and OSG insulation by adding linear insulators to the strings, for choosing the optimal types of substation electrical equipment, and for taking preventive measures. To refine the boundaries of local IPM zones, it is recommended to study the features characterizing the pollution of electrical installations insulation caused by both industrial and natural factors, as well as to generalize the experience gained from the operation of electrical installations in the Sheikh-Najar industrial region.

Temperature prediction of substation equipment based on back-propagation neural network -simulated annealing

The substation is an important part of the smart grid. The stable operation of electrical equipment in the substation is related to the stability of the grid. According to the statistical results, among the common substation equipment failures, thermal failures have a larger proportion. Thermal faults can be monitored through the surface temperature of the equipment, and predicting the changing trend of the equipment temperature in advance is of great significance for reducing equipment faults in substations. For this reason, this paper proposes a method for predicting the temperature of substation equipment based on BP neural network-simulated annealing algorithm, using equipment parameters, environmental information parameters, etc. to predict the temperature of electrical equipment in the substation, so as to realize early warning of thermal faults in substation equipment. Through comparative analysis, it is verified that the method proposed in this paper can accurately predict the temperature of substation equipment, which provides strong guarantee and support for the safety management of substation electrical equipment.

Brief Analysis of Substation Electrical Equipment Installation Debugging and Operation Maintenance Technology

Brief Analysis of Substation Electrical Equipment Installation Debugging and Operation Maintenance Technology

Image-Based Incipient Fault Classification of Electrical Substation Equipment by Transfer Learning of Deep Convolutional Neural Network

A transfer learning-based deep convolutional neural network (DCNN) is employed in this article to identify several typical electrical substation equipment incipient faults. Image dataset contains 11 000 captured electrical substation equipment images, and each image inside the dataset was labeled as normal condition or typical incipient faults (insulation oil leakage, insulator contamination, rusting, and paint off). High-dimension features of electrical substation equipment images were first extracted by classical pre-trained DCNN architectures through the transfer learning method, and different incipient faults were then classified by the fully-connected (FC) neural network using the SoftMax activation function. Remarkable fault classification accuracy was obtained on the validation image, which verifies the effectiveness of the purposed method. Performances of various pre-trained classic DCNN architectures were explored and evaluated by t-distributed stochastic neighbor embedding (t-SNE) feature cluster maps, learning curves, and confusion matrixes. Results show that a model consists of MobileNetV2 DCNN architecture and two FC neural network layers could finalize fault classification tasks on 1000 images in 25 s with an accuracy of 98% which achieves better performance than traditional image classify methods. The proposed method could be useful for designing an electrical substation image monitoring system thus providing early prediction of incipient equipment faults.