Search Results (92)

In this work, we present a neural network-based study capable of predicting faults in oil-insulated power transformers through the analysis of dissolved gases. The advantage of this study lies in using data already collected by electric power companies, which gather it to comply with international or regional standards; however, they sometimes act only after the equipment is already in a faulty condition. Therefore, the challenge in this work was data regularization, as collections typically occur at long intervals of 6 to 12 months. Furthermore, samples are often irregular, as data collection depends on factors such as weather and the availability of maintenance teams. As a result of this work, Multilayer Perceptron (MLP), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM) were used to predict failures with advanced forecasts ranging from 1 to 6 months, achieving accuracies of 97.5% and 85%, respectively. Thus, these models prove to be important tools for maintenance planning, enabling adequate predictability for organizing equipment shutdowns without the need for high investments in installing tools to capture this information online and adapting substations to send data to control rooms or other analysis centers. Full article

Oil-filled current transformers are crucial in high-voltage substations, directly affecting grid safety and reliability. Traditional defect diagnosis methods often show low accuracy and limited monitoring coverage, failing to meet operation and maintenance requirements. This paper proposes an AI-empowered digital twin-based defect diagnosis method that addresses typical issues like oil leakage, insulation damage, and moisture ingress by extracting relevant characteristic parameters to create an evaluation index system. A digital twin model integrates winding, core, and thermal flow characteristics, enabling real-time acquisition of operation parameters and precise mapping between physical and virtual transformers. A dual-model AI framework using Extreme Gradient Boosting (XGBoost) and Support Vector Machine (SVM) is introduced for intelligent defect identification and early defect prediction through multi-source data fusion. Finally, a corresponding diagnostic system is developed and verified using actual operation data from a 220 kV substation in Liaoning Province. The results show that the proposed method enables the online monitoring of multiple operating parameters, and the dual-model framework exhibits higher diagnostic accuracy and faster computation speed compared with Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), providing effective support for intelligent condition-based maintenance of current transformers. Full article

Reliable fault detection along transmission corridors is essential for preventing small defects from developing into long outages and costly emergency operations. This study aims to improve the field reliability of an open vocabulary vision language backbone without retraining the large model in an end-to-end manner. The work focuses on four operational fault classes in multi-region corridor imagery collected during routine inspections and uses a Florence-2 vision language model as the base recognizer. On top of this backbone, three domain-specific components are introduced. A subclass-aware fusion scheme keeps probability mass within the active parent concept so that insulator icing and conductor icing produce stable, action-oriented decisions. A Power-Line Focus Then Crop normalization uses an attention-guided corridor window together with isotropic resizing so that thin conductors and small fittings remain visible in the processed image. A corridor geo prior reduces scores as the distance from the mapped centerline increases and in this way suppresses detections that lie outside the corridor. All methods are evaluated under a shared preprocessing and scoring pipeline in training-free and parameter-efficient tuning modes. Experiments on unseen regions show higher accuracy for skinny and low-contrast faults, fewer false alarms outside the right-of-way, and improved score calibration in the confidence range used for triage, while keeping throughput and memory usage suitable for unmanned aerial vehicles and substation edge devices. Full article

Power supply for traction substations (TSs) of AC railways has traditionally been provided by 110–220 kV overhead transmission lines (OHL). These OHLs can be damaged during strong winds and ice formation. Furthermore, these lines generate significant electromagnetic fields (EMFs), which adversely affect maintenance personnel, the public, and the environment. Mitigating the resulting damages requires the establishment of protection zones, necessitating significant land allocation. Enhancing the reliability of power supply to traction substations and reducing EMF levels can be achieved through the use of gas-insulated lines (GIL), whose application in the power industry of many countries is continuously increasing. The aim of the research presented in this article was to develop computer models for determining the EMF of a GIL supplying a group of traction substations, taking into account actual traction loads characterized by non-sinusoidal waveforms and asymmetry. To solve this problem, an approach implemented in the Fazonord AC-DC software package, based on the use of phase coordinates, was applied. This allowed for the correct accounting of the skin effect and proximity effect in the massive current-carrying parts of the GIL, as well as the influence of asymmetry and harmonic distortions. The simulation results showed that the use of GIL brings the voltage unbalance factors at the 110 kV busbars of the traction substations within the permissible range, with the maximum values of these coefficients not exceeding 2%. The results of the harmonic distortion assessment demonstrated a significant reduction in harmonic distortion factors in the 110 kV network for the GIL compared to the OHL. The performed electromagnetic field calculations confirmed that the GIL generates magnetic field strengths one order of magnitude lower than those of the OHL. The obtained results lead to the conclusion that the use of gas-insulated lines for powering traction substations is highly effective, ensuring increased reliability, improved power quality, and a reduced negative impact of EMF on personnel, the public, the environment, and electronic equipment. Full article

Gas-insulated switchgear (GIS) serves as the core equipment in substations. Its partial discharge detection requires ultrasonic sensors to be precisely aligned with millimeter-level measurement points. However, existing technologies face three major bottlenecks: the lack of surface texture on GIS makes visual feature extraction difficult; strong electromagnetic interference in substations causes image noise and loss of feature point tracking; and fixed gain control easily leads to end-effector jitter, reducing positioning accuracy. To address these challenges, this paper first employs AprilTag visual markers to define GIS measurement point features, establishing an image-based visual servo model that integrates GIS surface curvature constraints. Second, it proposes an adaptive gain algorithm based on model predictive control, dynamically adjusting gain in real-time according to visual error, electromagnetic interference intensity, and contact force feedback, balancing convergence speed and motion stability. Finally, experiments conducted on a GIS inspection platform built using a Franka Panda robotic arm demonstrate that the proposed algorithm reduces positioning errors, increases positioning speed, and improves positioning accuracy compared to fixed-gain algorithms, providing technical support for the engineering application of GIS partial discharge detection robots. Full article

The DC traction power system adopts the track as the return rail. When the track-to-earth insulation in the subway tunnel deteriorates, stray currents will cause electrochemical corrosion to tunnel steel structures and seriously affect the service life and safety of metro tunnels. Stray currents cannot be directly measured and can only be calculated. Therefore, a calculation model with a hollow circular cross-section structure was proposed, and the stray current distribution in tunnel steel structures was calculated. In addition, the effects of different rail-to-ground transition resistances and adjacent buried metallic pipelines on the stray current distribution of the tunnel steel structures were taken into account. The results show that the total amount of stray current dispersed into the tunnel steel structures and soil is similar. The stray current density distribution in each steel tunnel is related to its location. The total stray current carried by the steel structures of the bottom tunnel segment is 102, 15.7 and 3.1 times higher than that of the top, upper and lower side tunnel segments, respectively. The reduction in the transition resistance and increase in the distance of the train from the traction substation increase the total rail leakage current and have a small effect on the percentage distribution of stray current in tunnel structures. The buried metal pipeline parallel to the tunnel has a lower impact on the total stray current leakage, but can reduce the total stray current in steel structures and drainage net, enlarging the positive stray current scope of some tunnel steel bars, further increasing the stray current density on tunnel steel bars. The results of this study can be used to determine the degree of corrosion of the underground steel tunnels and thereby provide support for corrosion prevention. Full article

The paper presents a hybrid intelligent expert diagnostic system (HIESD) of power transformer (PT) subsystems realized on the basis of integration of measuring and computing hardware and software complexes into a single functional architecture. HIESD performs online diagnostics of four main subsystems of PT: 1—insulating (liquid and solid insulation); 2—electromagnetic (windings, magnetic conductor); 3—voltage regulation; and 4—high-voltage inputs. Computational complexes and modules of the system are connected with the real object of power grids, 110/10 kV substation, which interact with each other and contain a relational database of retrospective offline data of the PT “life cycle” (including test and measurement results), supplemented by online monitoring data of the main subsystems, corrected by high-precision test measurements; analytical complex, in which the work of calculation modules of the operational state of PT subsystems is supplemented by predictive analytics and machine learning modules; and a knowledge base, sections of which are regularly updated and supplemented. The system architecture is tested at industrial facilities in terms of online transformer diagnostics based on dissolved gas analysis (DGA) data. Additionally, a theoretical model of diagnostics based on the electromagnetic characteristics of the transformer, which takes into account distorted and nonlinear modes of its operation, is presented. The scientific significance of the work consists of the presentation of the following new provisions: Methodology and algorithm for diagnostics of electromagnetic parameters of ST, taking into account nonlinearity and non-sinusoidality of winding currents and voltages; formation of optimal client–service architecture of training models of hybrid system based on the processes of data storage and management; and modification of the moth–flame algorithm to optimize the smoothing coefficient in the process of training a probabilistic neural network Full article

Partial Discharge (PD) measurement is one of the effective methods for assessing the internal insulation condition of power transformers in factories and substations. The pulse current signals generated by PD within transformer windings are significantly influenced by the winding structure during their propagation from the discharge source to the external measurement system. This influence may lead to misinterpretation of the insulation status, particularly in the analysis of PD measurement results. Such effects are closely related to the signal transmission path and distance and exhibit a strong correlation with the winding transfer function, manifesting as attenuation, distortion, or delay of the measured signals compared to the original PD waveforms. Therefore, it is essential to investigate the impact of the discharge path on the propagation characteristics of transformer windings and its effect on PD waveforms. This paper establishes a simplified distributed parameter model of a 180-turn single-winding multi-conductor transmission line using the finite element method and mathematical modeling, deriving the transfer functions between the winding head or winding end and various internal discharge positions. By injecting different types of PD waveforms collected in the laboratory at various discharge locations within the winding, the alterations of PD signals propagated to the winding head and winding end are simulated, and clustering analysis is performed on the propagated PD signals of different types. Full article

The new passive phase change thermal storage window integrates advanced energy-saving materials and technologies to provide efficient insulation and mechanical properties. It is suitable for green buildings. Through on-site experiments and simulations in summer, autumn, and winter in Jilin City, the cyclic use function of summer insulation and winter heating has been verified. This article establishes a numerical model and compares it with measured data to verify the accuracy of the model. In order to further verify the practicality of the new window, it was applied and tested at the Yichun substation in the cold winter region. The results showed that the new window can significantly reduce energy consumption while increasing indoor temperature. This article used a refined model established by Green Building Saville and Airpak3.0 software to deeply analyze the energy consumption and temperature field distribution of the window, and verified the reliability of numerical analysis in performance prediction. This study not only proves the effectiveness of the new phase change thermal storage window but also provides a new solution for the energy-saving design of green buildings. Full article

Gas Insulated Switchgear (GIS) is a type of critical substation equipment in the power system, and its safe and stable operation is of great significance for ensuring the reliability of power system operation. To accurately identify partial discharge in GIS, this paper proposes an acoustic identification method based on improved mel frequency cepstral coefficients (MFCC) and dung beetle algorithm optimized random forest (DBO-RF) based on the ultrasonic detection method. Firstly, three types of typical GIS partial discharge defects, namely free metal particles, suspended potential, and surface discharge, were designed and constructed. Secondly, wavelet denoising was used to weaken the influence of noise on ultrasonic signals, and conventional, first-order, and second-order differential MFCC feature parameters were extracted, followed by principal component analysis for dimensionality reduction optimization. Finally, the feature parameters after dimensionality reduction optimization were input into the DBO-RF model for fault identification. The results show that this method can accurately identify partial discharge of typical GIS defects, with a recognition accuracy reaching 92.2%. The research results can provide a basis for GIS insulation fault detection and diagnosis. Full article

Existing seismic evaluations of electrical equipment in substations mainly focus on post-type equipment, with few studies addressing the suspended equipment that exhibits significant geometric nonlinearity. Most of the vulnerability analyses on substation equipment consider only ground motion uncertainty, not processing other uncertainties including material properties. Thus, this paper investigates the seismic responses of an ±800 kV suspended filter capacitor using a simulation model. A new approach for vulnerability assessment based on an adaptive boosting (AdaBoost) regressor is proposed considering the uncertainties of multiple material parameters of the suspension insulators. It is applied to the filter capacitor and validated by conventional incremental dynamic analysis (IDA). In addition, the influence of the pre-tension force of the bottommost suspension insulators is also discussed. The results indicate that increasing the pre-tension force can avoid pressure generation in the insulators and reduce the maximum displacements of the filter capacitor. The failure probability will significantly increase when the pre-tension force increases from 20 kN, although the growth rate continues to fall. The established AdaBoost regressors substantially lower the calculational cost while maintaining an accurate vulnerability prediction, compared to IDA. The proposed method is endorsed due to its high accuracy and low calculation cost, although its feasibility is validated by only one suspended filter capacitor in this paper. Full article

High-voltage transmission and substation projects at high altitudes are pivotal in realizing the objective of universal electricity access. However, the reduced air density at elevated heights facilitates the formation and propagation of discharges, posing more stringent challenges to the external insulation of these projects compared to their counterparts in plains areas. Furthermore, considering the influence of meteorological conditions such as rainfall, it is imperative to conduct comprehensive experimental studies on the insulation properties of air gaps to inform the design and maintenance of engineered external insulation. This paper presents the results of rod–plane gap discharge tests conducted under dripping conditions at an actual high-altitude location of 2500 m. The employed test methodology effectively simulates the impact of rainfall on the insulation characteristics of the gap. Based on the experimental findings, a detailed analysis is conducted on the effects of gap distance, dripping flow rate, and conductivity on the gap breakdown voltage. Additionally, the discharge paths and underlying mechanisms under water-dripping conditions on rod electrodes are briefly discussed. The acquired data and conclusions contribute to a deeper understanding of the mechanisms governing rainfall effects on gap discharges and provide valuable insights for the design of external insulation in high-altitude HVDC transmission projects. Full article

Ultraviolet (UV) imaging technology has been used in corona discharge detection by characterizing the discharge degree through the detected number of photons in the UV imager or facular area of the UV image. This paper is to expand the UV imaging method in the electrical equipment’s fault detection and improve the accuracy of its detection. First, an image segmentation algorithm based on Gaussian function color mapping is proposed for the segmentation of colored facular areas in the UV image, and its effectiveness is proved. Second, the testing results for a high-voltage insulator’s discharge are used to fit the distance attenuation function of the facular area. The relationship between the voltage and the attenuation function coefficient is obtained by analyzing the experimental results. Finally, by analyzing actual inspection data of insulators in a substation, it is found that different defect types of insulators have different characteristics of changes in the facular area during the discharge. Based on the characteristics, accurate direct detection by using UV imaging can be realized for the defect types of discharging insulators. Full article

The secondary equipment of a substation is pivotal for maintaining the safe and reliable operation of the power grid. However, over time, insulation defects can inevitably arise in this equipment. Gas detection in substation secondary equipment has proven to be an effective method for assessing its insulation status. In this paper, we employed a density functional theory (DFT) approach to simulate the adsorption process of three types of fault gases from substation secondary equipment onto Cr-modified BN nanosheets. From the doped and adsorption models, two stable structures were chosen, and by calculating their band structures, density of states, and differential charge density, we uncovered the relevant adsorption and sensing mechanisms. Our findings reveal that Cr-modified BN nanosheets possess robust gas-sensing capabilities, particularly in capturing O₃, which is primarily attributable to the contribution of Cr’s 4d orbital electron layer. Specifically, the adsorption capacity of Cr-modified BN nanosheets for fault gases in substation secondary equipment follows the order: O₃ > NO₂ > CO. The adsorption of Cr-BN on the three target gases mainly tends to be chemisorption accompanied by chemical bond breaking. Notably, there are significant changes in the electronic properties of the adsorbent substrate before and after the adsorption of the target gas molecules, resulting in alterations in its overall conductivity. This research lays the theoretical groundwork for the experimental development of high-performance gas-sensitive sensors designed to detect fault gases in substation secondary equipment. Full article

Monitoring the insulation condition of power cables is essential for ensuring the safe and stable operation of the substation power supply system. Leakage current is an important indicator of insulation performance of power cables. However, the application of leakage current monitoring methods in substations is limited due to issues such as neutral line shunting on the load side and the spatial isolation of the phase-to-neutral line in the power cabinet. This paper proposes an insulation monitoring method based on distributed current principal component analysis for power cables in substations. Firstly, the leakage current of substation power cable is measured by a distributed current extraction method, and the cable insulation condition is preliminarily judged. Then, considering the problem of measurement error interference in the process of distributed current synthesis, an evaluation method of power cable insulation state based on principal component analysis of distributed current is proposed. To verify the feasibility of the proposed method, both simulation and laboratory tests were conducted. The results indicate that the proposed method can effectively measure the leakage current of power cables in substations and realize the accurate distinction between measurement error and cable insulation degradation characteristics. The method offers a novel idea for insulation monitoring of substation power cables. Full article