Search

Artificial intelligence is the general trend in the field of power equipment fault diagnosis. However, limited by operation characteristics and data defects, the application of the intelligent diagnosis method in power transformers is still in the initial stage. To fill this research gap, in this article, a novel double-stacked autoencoder (DSAE) is proposed for a fast and accurate judgment of power transformer health conditions with an imbalanced data structure. Three problems affecting the diagnosis effectiveness are overcome by a DSAE framework, an aging-tolerance criterion, and an advanced sparse deep clustering network. The proposed DSAE method is validated by two case studies based on an actual power transformer dataset. The results indicate that the proposed DSAE method can achieve a fairly reliable diagnosis with a higher accuracy and less time than the other methods, which demonstrates the superiority and effectiveness of the proposed approach.

Предложен подход к диагностике сложного и габаритного оборудования на примере определения технического состояния дизельного двигателя. Отличительной особенностью дизельного двигателя является сложность конструкции, требующая применения комплекса методов для обеспечения полноты контроля и чувствительности при выявлении дефектов на ранних стадиях развития. Описана схема обработки данных, позволяющая повысить чувствительность при диагностике за счет комплексного анализа данных различной физической природы с использованием анализа сингулярного спектра. Повышение чувствительности обосновывается путем численного моделирования и обработки результатов измерения диагностических параметров в реальных производственных условиях. В качестве показателей чувствительности рассматриваются расстояния между координатами центров кластеров параметров исправного и неисправного состояния в исходном пространстве и в пространстве главных компонент. Продемонстрировано, что предлагаемый подход обеспечивает повышение чувствительности в условиях, когда влияние дефекта на диагностические параметры сопоставимо с действием случайных факторов в объекте диагностирования. Указанное повышение качества диагностирования достигается благодаря корреляции между параметрами за счет их представления в виде траекторных матриц. Помимо повышения чувствительности при выявлении дефектов также достигается и существенное сжатие информации, которая используется для определения состояния. Преимуществом предлагаемого подхода также является наглядная визуализация результатов The article suggests an approach to the diagnosis of complex and oversized equipment by the example of determining the technical condition of a diesel engine. A distinctive feature of the diesel engine is the complexity of the design, which requires the use of a set of methods to ensure complete control and sensitivity when detecting defects at early stages of development. We describe the data processing scheme, which allows you to increase the sensitivity in diagnostics due to the complex analysis of data of various physical nature using the principal component method. The increase in sensitivity is justified by numerical modeling and processing the results of measuring diagnostic parameters in real production conditions. Distances between coordinates of centers of clusters of parameters of serviceable and faulty state in initial space and in space of principal components are considered as indicators of sensitivity. We demonstrated that the proposed approach provides increased sensitivity in conditions where the effect of a defect on diagnostic parameters is comparable to measurement errors. The indicated improvement in the quality of diagnostics is achieved due to the correlation between the parameters due to their representation in the form of trajectory matrices. In addition to increasing sensitivity when detecting defects, significant compression of information that is used to determine the state is also achieved. The advantage of the proposed approach is also the vivid visualization of the results

Despite the complicated fault mechanism of power equipment, with the increasing promotion and development of the Ubiquitous Power Internet of Things (UPIoT), the fault information of power equipment can be instantly saved, which makes possible intelligent diagnosis via fault samples. This study proposes a new method to implement comprehensive intelligent diagnosis by adopting the ShuffleNet lightweight convolution neural network (SLCNN). Considering the requirements of the UPIoT intelligent terminal, this study constructs six models, which are measured in terms of recognition accuracy, model storage, and calculation cost when applied to insulation and mechanical datasets. Compared with the existing models, the SLCNN outperforms them significantly in terms of recognition accuracy, with an accuracy of 95.77% and 99.9% in insulation and mechanical fault diagnoses, respectively. The SLCNN also demonstrates obvious advantages in other performance indicators, all of which contribute to its use in the accurate and reliable fault diagnosis of power equipment in the UPIoT context. Furthermore, through comparing feature maps, it is discovered that the aliasing degree and boundary of insulation defects are not as obvious as those of mechanical faults, which means that insulation fault diagnosis is much more difficult than mechanical fault diagnosis.

Currently, in order to ensure the safety of industrial facilities, diagnostics and monitoring of the condition of potentially dangerous equipment and the risks of its operation are being actively developed. At the same time, the risk assessment during the operation of various technical devices (TD) is carried out on the basis of the available damage statistics, which has accumulated over the past period of the TD operation, i.e., a probabilistic approach is used. This approach is imperfect and insufficiently objective since the risk assessment is done for the future period of time when the state of technical conditions can change significantly and fatigue damage to individual equipment units can occur in those zones that, as a rule, do not coincide with the calculated ones. The article proposes to carry out a risk assessment based on early diagnosis of the most damaged elements of TPP equipment. To implement this task, it is necessary to use more extensive methods of nondestructive testing of the actual stress-strain state in order to identify stress concentration zones (SCZ): the main sources of damage and modern methods of early diagnostics—acoustic emission, metal magnetic memory (MMM), and thermal control. An example of early diagnostics of developing damage from the practice of using the MMM method when monitoring the bend of a steam line is considered. It is shown that the difference in economic damage in risk assessment for TPPs with cross-links can be significant in case of damage to the steam line and damage to the boiler pipe.

The text classification of power equipment defect is of great significance to equipment health condition evaluation and power equipment maintenance decisions. Most of the existing classification methods do not sufficiently consider the semantic relation between words in the same sentence and cannot extract deep semantic features. To tackle those problems, this article proposes a novel classification method by combining the self-attention mechanism and multi-channel pyramid convolution neural networks. We utilize the bidirectional gated recurrent unit to model the text sequence and, on this basis, improve self-attention layer to dot multiplication on the forward and backward features to obtain the global attention score. Thereby, effective features are enhanced, invalid features are weakened, and important text representation vectors are obtained. To solve the problem that the shallow network structure cannot extract deep semantic features, we design a multi-channel pyramid convolution network, which first extracts deep text features from the channels of different windows and then fuses the text features of each channel. By comparing with the state-of-the-art methods, the model in this article has better performance in text classification of power equipment defects.

As a non‐contact temperature distribution measurement method, infrared thermography (IRT) has emerged as an indispensable tool in condition monitoring and fault diagnosis of electrical equipment based on the absolute and relative temperature values. Manual fault inspection, as an expert‐experiences based evaluation method, has formed a mature technical scheme with a large number of application cases. However, the efficiency and accuracy of manual fault inspection are being challenged by the rapid growth in the number of equipment in power grid. The situation is improving with the advanced of image processing technique. Machine‐assisted fault diagnosis provides a novel method to assist human beings to complete fault diagnosis under the intervention of human prior knowledge. However, the limitations of infrared images bring challenges to image analysis processing especially target detection. In pursuit of automatic fault diagnosis, deep learning algorithms are introduced to achieve target detection in the complex environment. This study reviews the development of IRT‐based diagnostics beginning with the general procedures, objects, and limitations of IRT‐based fault inspection, and then gives an insight into the popular machine‐assisted fault diagnosis as well as image‐based intelligent fault identification. In addition, the future recommendations of IRT are also provided from construction of intelligent infrared detection system, establishment of an open and shared infrared image database and comprehensive utilization of joint visualization diagnosis technology.

Inspection robots are popularized in substations due to the lack of personnel for operation and maintenance. However, these inspection robots remain at the level of perceptual intelligence, rather than cognition intelligence. To enable a robot to automatically detect defects of power equipment, object recognition is a critical step because criteria of infrared diagnosis vary with types of equipment. Since this task is not a big‐sample learning problem, prior knowledge needs to be added to improve existing methods. Here, an object recognition model based on human‐level concept learning is proposed, which utilizes relationship between equipment. The proposed method is composed of three parts: Mask RCNN, Bayesian Context Network and human‐level concept learning. As the backbone network, Mask RCNN, a pixel‐wise segmentation network, gives preliminary recognition results. Then, based on the object relationship graph of Bayesian Context Network, human‐level concept learning corrects the results in sequence by maximizing the conditional probability of an object given its neighbourhood. Experiments show that the accuracy of the proposed method increases 9.7% compared with its backbone network, making industrial application of this technology possible.

With the advent of the Internet of things era, many of the original power equipment and its fault information acquisition system have the problems of low efficiency, slow and inaccurate fault information collection speed, so the design of intelligent system is very important. The purpose of this study is to design the power equipment fault information acquisition system of the Internet of things, and analyze the collection speed and accuracy of the system. In this study, a power company in our city was taken as the experimental object to collect the fault information reported by the company, and put the new IOT fault information acquisition system into use in another company. After using for one month, the data collected by the power equipment fault information acquisition system of the Internet of things are compared with the original system, and the information collection amount, accuracy and acquisition speed are calculated. The research results show that the company's low-voltage user acquisition success rate has reached more than 99%, and the F1 value of the power equipment information acquisition system of the Internet of things is 96.4%, which is much higher than 86.3% and 75.7% of other systems. With the increase of time, the fault information collection efficiency can approach 99%. It shows that the power equipment information acquisition system of the Internet of things has higher accuracy and speed of information acquisition than the traditional system and other systems, and greatly improves the working efficiency of the system. The conclusion is that the function of this research system is better, the economic loss of the company is reduced, and the management is optimized. It makes contribution to the optimization and intelligent development of power equipment fault information acquisition system.

Live working in distribution work is an important way to ensure normal power supply of power equipment. Live installation tool for robot operation was proposed in this paper in order to reduce the safety accidents occurrence. Through different structures and sensor combinations, it can complete the autonomous operation by cooperating with robot, including lead wire monitoring, line detection and tightening the puncture clamp. Finally, the finite element analysis of gear transmission was carried out, and the results showed that the design of the tool can mees the strength requirements.

In power Internet of Things environment, the existing border-based protection system and the “one-time authentication, one-time authorization, and long-term effective” approach are difficult to deal with the threat of attacks from internal and external devices and users with legal authority. In order to solve the problem of authorized access of power equipment and users, combined with behavior risk assessment, a continuous trust evaluation scheme of power equipment and users is presented in this paper. The scheme is evaluated by the combination of direct trust, indirect trust, and comprehensive trust and adds the penalty reward factor and time attenuation function to improve the reliability of the results. In addition, this paper will quantify the risk of the behavior of power equipment and users and regard it as a factor affecting the degree of trust, so as to achieve continuous trust evaluation of equipment and users.

The performance of array‐based power equipment acoustic emission (AE) source directional of arrival (DOA) estimation methods is decided by not only algorithm performance, but also the array hardware parameters, that is, array aperture, sensor number, and so forth. Improving the estimation performance by hardware approaches always leads to the increase in cost. In this study, an array virtual extension method based on high‐order cumulants is proposed which can improve the sensor array performance without the need for hardware change or extra investment. Compared to low‐order cumulants, the high‐order cumulants established from Taylor expansion contain higher order terms which are omitted in low order cumulants. Therefore, they have more detailed directional information about the signal source to improve the DOA estimation performance. Moreover, because high‐order cumulants contain information only for the non‐Gaussian components, the array after extension shows better anti‐Gaussian noise performance. Depending on the establishment method of the high‐order cumulant, two types of extension including aperture extension and sensor number extension are proposed for different application scenarios. Simulation and field tests results show that the array directional resolution is improved around 40% by aperture extension and the spectrum sidelobe level is reduced about 14 dB by sensor extension.

Current maintenance mode for high-speed railway (HSR) power equipment is so outdated that can hardly adapt to the high-standard modern HSR. Therefore, a new possibility is proposed in this article to update the obsoleting maintenance mode of the HSR power equipment by adopting both predictive maintenance and proactive maintenance. With the combination of data-driven (predictive) and model-based (proactive) approaches, two principal constituents—the sample generator and the maintenance predictor—are designed. The maintenance predictor which is powered by the long short-term memory recurrent neural network is developed to realize the goal of predictive maintenance. The sample generator which is formulated by the physical degradation and failure model of HSR power equipment is proposed toward the goal of proactive maintenance. Test results on a gas-insulated switchgear have shown the powerful collaboration between the generator and the predictor, to not only accurately predict future maintenance timing of the switchgear based on historical sample data, but also enrich the data supply proactively to deal with potential data deficiency problems.

Introduction. Improving the quality and operational reliability of welded structures of power equipment is an urgent task of welding production. Its solution is possible on the basis of the development or selection of advanced methods and technologies of electroslag welding (ESW), which eliminate the causes of the formation of tempering cracks (TC) in thick-plate welds. This paper considers a comparative assessment and recommendations on the selection of such advanced ESW methods. The work objectives are to solve the problem of forming a fine-grained, uniform, crack-resistant metal structure of a welded joint with high mechanical characteristics and to reduce the negative impact of the ESW thermal cycle on the base metal. The solution to this problem is possible on the basis of a reasonable choice of methods and technologies for ESW with regulated (controlled) thermal cycle. Materials and Methods. A comparative analysis of advanced methods and technologies of ESW with a controlled thermal cycle is carried out; a comparison of their pros and cons is provided; practical recommendations on the selection of advanced methods for controlling the thermal cycle parameters are offered. Results. It is shown that moderate heat input at high-speed ESW in a narrow gap provides a single pass to form a welded joint with a finer-grained structure and high mechanical properties compared to the in-house technologies of ESW and automatic submerged-arc welding. Recommendations for practical use of the method in welding production are given. Discussion and Conclusions. The results obtained are recommended to be used in the development of ESW technology for thick-sheet welded structures of nuclear and thermal power equipment that enables to abandon postwelding heat treatment (normalization and high tempering).

To achieve comprehensive insulation deterioration motoring of power equipment and early fault warning in air-insulated substations, a data-driven partial discharge (PD) source localisation method employing noisy ultra-high frequency (UHF) received signal strength indicator (RSSI) and particle filter is proposed in this study. Compared with the existing UHF time-difference-based techniques, UHF wireless sensor arrays and RSSI-based methods provide an economical and high-adaptability solution. However, owing to the multi-pathing and shadowing effects, UHF signal attenuation cannot be modelled. Therefore, a Kalman filter was employed to smoothen the RSSI signal. Furthermore, a semi-parametric regression model is proposed to achieve a more accurate relationship between the RSSI and the transmission distance. Finally, in contrast to traditional localisation algorithms directly based on the RSSI ranging model, a particle filter was used to achieve higher accuracy. It predicted the best distribution of the position of PD by learning and considering all the system states of the previous moment. The laboratory test was performed within an area of 6 m × 6 m, and the results demonstrate that the mean PD source localisation error was 1.16 m, which gives a potential application for the identification of power equipment with insulation deterioration in a substation, while the accuracy is still needed to be verified further by field tests.

The SCADA system was developed. The development process is described. The main elements that make up the SCADA system are described. The algorithm of functioning of the SCADA system, its capabilities, and the main advantages of its use were described in detail.

The principles for developing smart sensors for monitoring the vibrational state and for vibration diagnostics of power equipment in thermal power plants are analyzed.

This research uses a deep learning algorithm to detect insulator strings automatically. Besides, all available disks (or caps) in the insulator can be successfully detected, which makes the missing cap defect easily perceived by human eyes. To fulfill that, aerial images of power equipment are collected and manually annotated. Segmented insulators are blended into background images to produce synthetic images for data augmentation. The system architecture is fine-tuned based on the mask regions with a convolutional neural network. The mAP of our method is equal to 94%, and 90% for insulator and disk respectively, which outperform the YOLOv4-based approach. The experimental results depict the robustness and accurateness of the proposed approach.

Insulation plays an important role in power system. During the production and operation of power equipment, there will inevitably be insulation defects occurring. Realizing the detection and localization of these defects is of great significance to ensure the safe and stable operation of power system. In this paper, different defect localization algorithms are proposed for transformer, cable and whole substation equipment, respectively. Experimental results show that these algorithms can reach a high localization accuracy.

This article contains an analysis of the existing methods for monitoring the technical condition of the equipment. The authors have identified several shortcomings in the existing methods of technical diagnostics. To eliminate the identified shortcomings, the authors of the article have developed a new method for monitoring the technical condition of power equipment. The developed method is based on the identification of diagnostic information. According to the developed method, the oscillations of the resonant frequency are exited in the object of research; then, using a piezoelectric sensor, we record the vibration parameters of the object of research. And after that, the obtained information is fed to a personal computer. The personal computer analyzes the received information to identify defects in the object of research. The information obtained during the registration of vibrodiagnostic signals is used as diagnostic signs of the defect’s presence. In the article, the authors considered the following types of defects: gouges from external damage, metal loss caused by corrosion, puncture, dents, cracks and defects in a weld. The processing and recording of vibrodiagnostic signals are carried out in the LabVIEW software using spectral analysis, which is often used in technical diagnostics. The article also presents the results of experimental studies.

In order to realize the automatic inspection of power equipment by UAV based on UV imager, this paper designs a fully automatic hangar deployed near substations and transmission lines to realize remote control of UAVs, automatic landing and returning Positive, UV diagnostic defect data download and other functions. The hangar can transmit data with the UV imager, and send the data back to the PC, realizing one-click automatic acquisition of UV imaging data. The research results are of great significance to promote the development of UAV inspection in the power industry.

Infrared sensing technology is more and more widely used in the construction of power Internet of Things. However, due to cost constraints, it is difficult to achieve the large-scale installation of high-precision infrared sensors. Therefore, we propose a blind super-resolution method for infrared images of power equipment to improve the imaging quality of low-cost infrared sensors. If the blur kernel estimation and non-blind super-resolution are performed at the same time, it is easy to produce sub-optimal results, so we chose to divide the blind super-resolution into two parts. First, we propose a blur kernel estimation method based on compressed sensing theory, which accurately estimates the blur kernel through low-resolution images. After estimating the blur kernel, we propose an adaptive regularization non-blind super-resolution method to achieve the high-quality reconstruction of high-resolution infrared images. According to the final experimental demonstration, the blind super-resolution method we proposed can effectively reconstruct low-resolution infrared images of power equipment. The reconstructed image has richer details and better visual effects, which can provide better conditions for the infrared diagnosis of the power system.

The information price of prefabricated power equipment and materials is one of the important parts of the whole power grid engineering equipment and materials information price system. This study largely based on “The Code of Conducts of State Grid Corporation of China” and developed a pricing model mainly based on “window” statistical iterative calculation to focuses on the price of prefabricated power equipment and materials estimation, which lays the foundation for the information price. In addition, an information price release system will be formed to improve the lean level of project cost management.

Text mining techniques has become a research hotspot in the field of power equipment defects. To summarize the research advances in the text mining techniques, this paper first analyzes the general steps and research hotspots of the techniques, and then focuses on the typical applications of text mining in the field of power equipment defects, including the construction of an ontology dictionary of electric power equipment, the evaluation of health status of the equipment based on text information, automatic classification of the defects according to the severity of the defects in the equipment, the precise extraction of defect details, the construction and application of knowledge graphs of power equipment defects. At the end of the paper, the challenges that text mining in the field of power equipment defects has to face are proposed. This work will help readers to systematically and quickly know the text mining techniques for knowledge of defects in power equipment.

To recognize errors in the power equipment defect records in real time, we propose an error recognition method based on knowledge graph technology. According to the characteristics of power equipment defect records, a method for constructing a knowledge graph of power equipment defects is presented. Then, a graph search algorithm is employed to recognize different kinds of errors in defect records, based on the knowledge graph of power equipment defects. Finally, an error recognition example in terms of transformer defect records is given, by comparing the precision, recall, F1-score, accuracy, and efficiency of the proposed method with those of machine learning methods, and the factors influencing the error recognition effects of various methods are analyzed. Results show that the proposed method performs better in error recognition of defect records than machine learning methods, and can satisfy real-time requirements.

The article presents the results regarding the elimination of constraints in the production process of a power equipment subassembly, a boiler chamber, together with an analysis of the benefits resulting from this, both financial and non-financial. The significance of bottlenecks in the production process, ways of its identification and limitations - in general - are presented. The article is a case-study of an attempt to eliminate the bottleneck in the production process of the boiler chamber, which turned out to be the process of drilling and marking-off, and work stations representing these processes. In order to eliminate the limitation, it was decided to replace the existing tracing and drilling work with a numerically controlled device - a boring machine moved from the liquidated department.. As a result, labor-intensive, manual chambers marking-off and the process of drilling holes with a smaller diameter drill have been eliminated. A number of benefits has been demonstrated resulting from the elimination of the bottleneck in the process, first of all, it was possible to reduce the duration of the marking-off and drilling operations and reduce the costs of the boiler chamber production process.

Electric power infrastructure, such as transmission lines or substations, is usually routinely inspected to assess its condition. The vast majority of typical defects in power transmission equipment manifests itself either through corona phenomena or through thermal effects. Therefore, an IR camera and a solar blind UV camera are sufficient for the detection of most defects in power transmission equipment. In the past, many network operators have relied mostly on manual inspections. In recent years, however, manned as well as unmanned aerial inspection methods, which are significantly more time effective, have become increasingly affordable and are therefore gaining in popularity rapidly.To obtain meaningful measurement results, many factors must be taken into account, which can even be difficult with conventional, static measurements. In the case of highly dynamic measurement practices (airborne or vehicle based), the combination of velocity and distance presents further challenges.This contribution is focused on the detection performance of UV and IR sensors under dynamic conditions. For this purpose, experiments were carried out with a typical IR and UV/corona camera at various distances to artificial defects. Additionally, a method for the automatic evaluation of UV und IR data based on machine learning is presented.

The article discusses the process of planning the repair of energy equipment. Using a decision support system is proposed because of the large number of rules of comparing flow charts of technical defects. Such a system can speed up the planning process and reduce economic costs. A conceptual model of the system has been built; further it will be presented as a multi-label classification of cross-cutting classes. The “one-vs-all” approach has been used: each flow chart can use its individual classifier. Metrics are proposed for evaluating classifiers: a portion of accurately classified objects, precision, fullness and F-measure. To summarize the evaluation results the concept of micro-average was chosen. A defect classification algorithm has been described. An experiment was conducted using different classification algorithms: decision trees, Bayes classifier and multilayer perceptron. The results of the experiment proved that 80-90% of the correctly classified objects were found (high values), but the average values of accuracy and fullness occurred low (3-7%). There were found sets of data, where different output data corresponded to similar input data. Thus, machine learning can be used to support decision-making, but in some cases information about the order is not complete. Defect classification can be combined with manual clarifying of results or with different algorithms.

For designing different heat and power equipment with a wide range of applications, it is necessary to measure the fields of thermophysical characteristics (temperature, pressure, velocities, etc.) in as much detail as possible. At the same time, the deployment of complex diagnostic methods is often impossible. Therefore, it is most practical to use movable probes that move in the flow and make measurements at separate points. The use of such scanning measurement methods is a complex task that requires the solution of many mechanical and thermophysical problems. The techniques of scanning probe measurements for determining thermal characteristics in the flows of various media are described. A review is given concerning the development of probe-based investigation methods since the 1960s. Joint probe developments concerning the probes made by the scientific group of the Engineering Thermophysics Department of the National Research University Moscow Power Engineering Institute and the Joint Institute for High Temperatures, Russian Academy of Sciences, for two-dimensional and three-dimensional temperature and velocity measurements in water and mercury flows are presented in detail. The experience in the development and use of scanning probes is summarized in three main designs, such as a hinged probe, a probe with eccentricity, and a longitudinal probe. Descriptions, methods of application, and the features of their operation are considered for these designs. The results obtained by using the probes of various designs in the course of experiments with water and mercury are considered. The choice of a required technique is substantiated depending on the preset conditions of the problem, such as the geometric characteristics of the investigated area, the presence of a magnetic field, the influence of thermal and gravity factors.

The general availability growth models for large scale complicated repairable system such as electric generating units, power station auxiliaries, and transmission and distribution installations are presented. The calculation formulas for the maintenance coefficient, mathematical expressions for general availability growth models, ways for estimating, and fitting on checking the parameters of the model are introduced. Availability growth models for electric generating units, power station auxiliaries, and transmission and distribution installations are given together with verification examples for availability growth models of 320–1000 MW nuclear power units and 1000 MW thermal power units, 200–1000 MW power station auxiliaries, and 220–500 kV transmission and distribution installations. The verification results for operation availability data show that the maintenance coefficients for electric generating units, power station auxiliaries, transmission and distribution installations conform to the power function, and general availability growth models conform to rules of availability growth tendency of power equipment.

This paper proposes a novel RPN-FCN based rust detection approach. The RPN-FCN generates region proposals with RPN and performs full convolution for semantic segmentation of rust. The experimental result demonstrate that this approach improves the accuracy of rust detection compared with other neural networks.

The first-year students at the technical universities often face the problem of using the previously acquired knowledge at a higher level required by engineering education. To solve this problem, the authors developed a series of lectures dedicated to establishing theoretical background, based on simulations in DigSILENT Power Factory software. In the lectures, the physical values and quantities as well as the purpose and characteristics of the power equipment are explained on the example of the simple models. This article includes the detailed description of a lesson “Introduction into Power Systems” and presents some models and ways of explaining the material. The sections below concentrate on the lecture format focusing on methods for explanation of physical quantities and introducing power system components. Sequential parts create the mosaics of grid, with the following description of basic laws and principles in power systems.

Infrared images of power equipment play an important role in power equipment status monitoring and fault identification. Aiming to resolve the problems of low resolution and insufficient clarity in the application of infrared images, we propose a blind super-resolution algorithm based on the theory of compressed sensing. It includes an improved blur kernel estimation method combined with compressed sensing theory and an improved infrared image super-resolution reconstruction algorithm based on block compressed sensing theory. In the blur kernel estimation method, we propose a blur kernel estimation algorithm under the compressed sensing framework to realize the estimation of the blur kernel from low-resolution images. In the estimation process, we define a new Lw norm to constrain the gradient image in the iterative process by analyzing the significant edge intensity changes before and after the image is blurred. With the Lw norm, the salient edges can be selected and enhanced, the intermediate latent image generated by the iteration can move closer to the clear image, and the accuracy of the blur kernel estimation can be improved. For the super-resolution reconstruction algorithm, we introduce a blur matrix and a regular total variation term into the traditional compressed sensing model and design a two-step total variation sparse iteration (TwTVSI) algorithm. Therefore, while ensuring the computational efficiency, the boundary effect caused by the block processing inside the image is removed. In addition, the design of the TwTVSI algorithm can effectively process the super-resolution model of compressed sensing with a sparse dictionary, thereby breaking through the reconstruction performance limitation of the traditional regularized super-resolution method of compressed sensing due to the lack of sparseness in the signal transform domain. The final experimental results also verify the effectiveness of our blind super-resolution algorithm.

The wide application of WebGIS provides technical support and guarantee for the optimization process of distribution network dispatching management method. In order to make a more systematic analysis of its use process, the application of WebGIS in distribution network dispatching management is studied. Mapx and Mapxtreme are selected as development tools to build distribution network geographic information platform. The load of power equipment in distribution network is analyzed by similarity measurement method, which is the basis of distribution network dispatching management. The objective function of distribution network scheduling management is constructed, and the pollen pollination algorithm is used to complete the distribution network scheduling management process. The test results show that the application of WebGIS in distribution network dispatching management is scientific and feasible, which can alleviate the problems caused by the lack of performance of conventional methods and other technical methods to a certain extent.

Capacitor voltage transformer is an important power equipment in substation, which is with great significance to the safe operation of substation. This paper summarizes and analyzes the common problems in the process of technical supervision of capacitor voltage transformer, and the oil level window of electromagnetic unit is improved to avoid the disadvantage of oil level inspection inconvenient of capacitor voltage transformer. Inclined angle between oil level window and electromagnetic unit is 60°. The oil level window is large, and the material with aging resistance and high transparency is selected. The problems existing in the oil level inspection of CVT electromagnetic unit are effectively solved and the safe and stable operation ability of equipment is enhanced by improving oil level window.

The comprehensive perception of substation equipment status is the precondition of ensuring safe operation and realizing intelligent patrol inspection of substation. With the development of digital power grid, higher requirements are put forward for the fine management of power equipment. Digital twin technology is one of the ideal ways to realize the real-time perception and evaluation of the running state of equipment by using digital technology such as sensor, Internet of Things, virtual reality and artificial intelligence. Aiming at the problem of precision constraint and error accumulation of physical model, a digital twin modeling method for substation equipment based on multi-parameter perceptual data and a method for equipment operation state evaluation is proposed.