Search

Routine visual inspection is fundamental to the preventive maintenance of power equipment. Convolutional neural networks (CNNs) substantially reduce the number of parameters and efficiently extract image features for classification tasks. In the actual production and operation process of substations, due to the limitation of safety distance, camera monitoring, inspection robots, etc., cannot be very close to the target. The operational environment of power equipment leads to scale variations in the main target and thus compromises the performance of conventional models. To address the challenges posed by scale fluctuations in power equipment image datasets, while adhering to the requirements for model efficiency and enhanced inter-channel communication, this paper proposed the ResNet Cross-Layer Parameter Sharing (ResNetCPS) framework. The core idea is that the network output should remain consistent for the same object at different scales. The proposed framework facilitates weight sharing across different layers within the convolutional network, establishing connections between pertinent channels across layers and leveraging the scale invariance inherent in image datasets. Additionally, for substation image processing mainly based on edge devices, smaller models must be used to reduce the expenditure of computing power. The Cross-Layer Parameter Sharing framework not only reduces the overall number of model parameters but also decreases training time. To further enhance the representation of critical features while suppressing less important or redundant ones, an Inserting and Adjacency Attention (IAA) module is designed. This mechanism improves the model’s overall performance by dynamically adjusting the importance of different channels. Experimental results demonstrate that the proposed method significantly enhances network efficiency, reduces the total parameter storage space, and improves training efficiency without sacrificing accuracy. Specifically, models incorporating the Cross-Layer Parameter Sharing module achieved a reduction in the number of parameters and model size by 10% to 30% compared to the baseline models.

At present, substation operation ticket system is developed based on an expert system, which has some problems such as knowledge base redundancy, intelligence deficiency and automatic learning ability. To solve this problem, this paper proposes an operation sequence reasoning model based on the knowledge base of the Neo4j knowledge graph and DuelingDQN (Dueling Deep Q Network) algorithm. Firstly, the diagram structure model of substation main wiring was established using the Neo4j knowledge graph. Based on the diagram structure model, the operable equipment set of the operation task was searched to form the task space, action space and action selection model of DuelingDQN. The reward and punishment function was designed based on the “five defense” rules and the state change of equipment. Make DuelingDQN model and Neo4j model interact in real time, and automatically learn the operation sequence. The test results show that the method proposed in this paper can automatically deduce the correct operation steps under different wiring modes and realize the transfer within the station, which is of great significance to the intellectualization of the operation ticket system.

The residual magnetic field in a magnetic shielding device with a multilayer high permeability material (permalloy) structure can be obtained at the nanotesla (nT) level or even lower. At present, in the process of designing a magnetic shielding device, most of the external environmental magnetic field settings are set at the size of the Earth’s environmental magnetic field, but the instruments inside the magnetic shielding device need to be powered, the active compensation coil needs to be powered, and the degaussing coil of passive shielding layer needs to be powered, so substations need to be used around magnetic shielding devices. The magnetic field generated by the substation will affect the magnetic shielding device, so this paper analyzes and measures the magnetic field generated by the substation. Firstly, the finite element model of a substation is established, and the influence of different substations on the environmental magnetic field is analyzed by changing the power. Secondly, the test method of a substation environment magnetic field is determined. Finally, the site test was carried out to measure the influence of different power substations and different distances on the magnetic field, and its influence on the magnetic shielding device was analyzed, which provided an important basis for the construction of the magnetic shielding device.

Liberalization of the electricity market has forced the use of economic and efficient maintenance techniques. Thus, it is necessary to extend the useful life of the facilities in a perfect state of service, and with quality supply for customers. Furthermore, thermography is a maintenance technique that can be implemented quickly, has low cost, and is very effective in terms of the results provided. For this reason, it is very widespread within the electricity sector. As substations are critical facilities within the electrical supply, thermographic inspections are carried out on them very frequently. However, to ensure that the results obtained are reliable, a series of requirements must be met. A compilation of the complete process of the performance of a correct thermography in substations is shown. The factors that affect performing a correct thermographic inspection are indicated. These can be procedural, technical, and environmental. In addition, conditions for conducting thermographic inspections and the action to performed on a hot spot are indicated. The hot spot is usually identified with a current and wind speed other than nominal; these two variables can mask the true severity of the hot spot. For this reason, the extrapolation of the detected temperature to the nominal current conditions and in the absence of wind is carried out using a proposed formula. Finally, two examples of application of the proposed formula and the recommended action on them are exposed.

The accurate and timely detection of irregular behavior of substation personnel plays an important role in maintaining personal safety and preventing power outage accidents. This paper proposes a method for irregular behaviors detection (IBD) of substation personnel based on an improved YOLOv4 which uses MobileNetV3 to replace the CSPDarkNet53 feature extraction network, depthwise separable convolution and efficient channel attention (ECA) to optimize the SPP and PANet networks, and four scales of feature maps to fuse to improve the detection accuracy. First, an image dataset was constructed using video data and still photographs preprocessed by the gamma correction method. Then, the improved YOLOv4 model was trained by combining Mosaic data enhancement, cosine annealing, and label smoothing skills. Several detection cases were carried out, and the experimental results showed that the proposed improved YOLOv4 model has high accuracy, with a mean average precision (mAP) of 83.51%, as well as a fast detection speed, with a frames per second (FPS) of 38.06 pictures/s. This represents better performance than other object detection methods, including Faster RCNN, SSD, YOLOv3, and YOLOv4. This study offers a reference for the IBD of substation personnel and provides an automated intelligent monitoring method.

Renewable generation in power systems has proved to be challenging for system operators owing to the increasing levels of penetration. The operation of power systems currently requires additional flexibility and reserves due to the intermittency and unpredictability of renewable generators. However, it is difficult to precisely predict and control the stochastic nature of renewable sources; nevertheless, its capacity continues to increase. To monitor and control renewable generators efficiently, the entire system needs to be established in a hierarchical order. This study proposed the concept of a substation that is uniquely designed for renewable interconnection. The purpose of this substation is simple: to make the renewable generators dispatchable to operators such that each group of renewable generators is sufficiently stable to be considered as conventional generators. For this purpose, methods for sizing and controlling energy storage system are proposed based on forecasts and error distributions.

A method for separating multisource partial discharges (PDs) in a substation is proposed based on selected bispectra of ultrahigh frequency (UHF) electromagnetic waves. Bispectra are sensitive to Gaussian noises and processes of symmetrical distribution. The phase information contained in bispectra can be useful and important for further signal processing. Bifrequencies where Fisher-like class separability measures between signals’ bispectra achieve their maximums are selected as characteristic parameters of the signals. Then, the selected bispectra are utilized for training the radial basis neural network to separate PD UHF signals in a substation. The method is used to analyze simulated UHF signals mixed with Gaussian white noise and frequency-fixed interference, and to separate PD UHF signals that are collected in a 500 kV substation. In order to prove the validity of the proposed separation method, the localization results are compared with the results calculated by time delay sequence, and the proposed separating algorithm is verified in the interference circumstances of a substation. However, the exact location of PD sources cannot be calculated according to the time delay sequence when the PD sources in a substation are close to each other or there are fewer than four antennas for receiving signals.