Search Results (229)

This study presents a Variational Autoencoder (VAE)-based framework for the unsupervised mechanical fault diagnosis of high-voltage isolation switches. By analyzing voltage and current signals to compute instantaneous power sequences, the method detects anomalies through reconstruction errors. Experimental results from both laboratory and real-world datasets demonstrate that the VAE model outperforms traditional methods, offering high diagnostic accuracy and robustness without the need for labeled data or manual feature extraction. This approach provides an effective solution for the real-time monitoring and predictive maintenance of high-voltage switchgear. Full article

The insulating rod of aramid fiber-reinforced epoxy resin composites (AFRP) is an important component of gas-insulated switchgear (GIS). Under complex working conditions, the high temperature caused by voltage, current, and external climate change becomes one of the important factors that aggravate the interface degradation between aramid fiber (AF) and epoxy resin (EP). In this paper, molecular dynamics (MD) simulation software is used to study the effect of temperature on the interfacial properties of AF/EP. At the same time, the mechanism of improving the interfacial properties of three nanoparticles with different properties (insulator Al₂O₃, semiconductor ZnO, and conductor carbon nanotube (CNT)) is explored. The results show that the increase in temperature will greatly reduce the interfacial van der Waals force, thereby reducing the interfacial binding energy between AF and EP, making the interfacial wettability worse. Furthermore, the addition of the three fillers can improve the interfacial adhesion of the composite material. Among them, Al₂O₃ and CNT maintain a large dipole moment at high temperature, making the van der Waals force more stable and the adhesion performance attenuation less. The Mulliken charge and energy gap of Al₂O₃ and ZnO decrease slightly with temperature but are still higher than AF, which is conducive to maintaining good interfacial insulation performance. Full article

Deep learning-based models have achieved considerable success in partial discharge (PD) fault diagnosis for power systems, enhancing grid asset safety and improving reliability. However, traditional approaches often rely on centralized training, which demands significant resources and fails to account for the impact of noisy operating conditions on Intelligent Electronic Devices (IEDs). In a gas-insulated switchgear (GIS), PD measurement data collected in noisy environments exhibit diverse feature distributions and a wide range of class representations, posing significant challenges for trained models under complex conditions. To address these challenges, we propose a Self-Supervised Asynchronous Federated Learning (SSAFL) approach for PD diagnosis in noisy IED environments. The proposed technique integrates asynchronous federated learning with self-supervised learning, enabling IEDs to learn robust pattern representations while preserving local data privacy and mitigating the effects of resource heterogeneity among IEDs. Experimental results demonstrate that the proposed SSAFL framework achieves overall accuracies of 98% and 95% on the training and testing datasets, respectively. Additionally, for the floating class in IED 1, SSAFL improves the F1-score by 5% compared to Self-Supervised Federated Learning (SSFL). These results indicate that the proposed SSAFL method offers greater adaptability to real-world scenarios. In particular, it effectively addresses the scarcity of labeled data, ensures data privacy, and efficiently utilizes heterogeneous local resources. Full article

Surface charge accumulation is considered one of the key factors that lead to unexpected insulator flashover failures in gas-insulated switchgear (GIS). With the existence of metal particles, charge accumulation characteristics on insulator surfaces become intricate in eco-friendly gases under AC voltage. In this study, the surface charge behavior on a down-scaled 252 kV AC GIS basin insulator model with a linear metal particle adhered to the HV electrode on the convex surface in compressed air (80%N₂/20%O₂) and C₄F₇N/CO₂ mixtures was investigated. After applying an AC voltage of 40 kV for 5 min, the charge densities on both surfaces were measured, and the effect of the metal particle and gas parameters was discussed. The results showed that charge spots were induced by metal particles on the insulator surfaces, and the polarities of which varied with the gas atmosphere. A decrease in maximum charge density was detected with an increase in C₄F₇N proportion at 0.1 MPa, and soar of which was observed at 0.5 MPa. With an increase in gas pressure, the maximum charge density increased in both atmospheres. The total quantity of charges showed similar behavior to the charge densities. It is indicated that the high electronegativity of C₄F₇N molecules presents a competing relationship in charge accumulation as the pressure increases. Full article

Aiming at the challenge of trajectory planning for a continuum manipulator in the confined spaces of gas-insulated switchgear (GIS) chambers during intelligent operation and maintenance of power equipment, this paper proposes a configuration space (C-space) obstacle-avoidance planning method based on an improved RRT-Connect algorithm. By constructing a virtual joint-space obstacle map, the collision-avoidance problem in Cartesian space is transformed into a joint-space path search problem, significantly reducing the computational burden of frequent inverse kinematics solutions inherent in traditional methods. Compared to the RRT-Connect algorithm, improvements in node expansion strategies and greedy optimization mechanisms effectively minimize redundant nodes and enhance path generation efficiency: the number of iterations is reduced by 68% and convergence speed is improved by 35%. Combined with polynomial-driven trajectory planning, the method successfully resolves and smoothens driving cable length variations, achieving efficient and stable control for both the end-effector and arm configuration of a dual-segment continuum manipulator. Simulation and experimental results demonstrate that the proposed algorithm rapidly generates collision-free arm configuration trajectories with high trajectory coincidence in typical GIS chamber scenarios, verifying its comprehensive advantages in real-time performance, safety, and motion smoothness. This work provides theoretical support for the application of continuum manipulator in precision operation and maintenance of power equipment. Full article

The underwater unstructured environment poses new challenges for the miniaturization and flexibility of underwater vehicles. This paper proposes a method of using micrometer-scale vibrations of piezoelectric vibrators to drive macroscopic jets. Then, we use two coupled piezoelectric jet driving units to construct a miniature underwater vehicle. Numerical simulation is used to investigate the flow field characteristics of coupled jets. Finally, the impact of the angle between the two piezoelectric jet drive units on the propulsion force is analyzed. The miniature underwater vehicle measures 77.8 mm in length and 87 mm in width. While achieving miniaturization, it maintains high flexibility, maneuverability, and controllability. By adjusting the input signals to the two piezoelectric jet drive units, the miniature underwater vehicle can move in a straight line, turn, and rotate. Its maximum linear velocity reaches 54.23 mm/s. Its outstanding motion ability and environmental adaptability allow it to perform various tasks in unknown and complex environments. It also has broad application prospects. Full article

Fault diagnosis based on the partial discharge (PD) recognition has been widely applied on a gas-insulated line breaker (GILB) and gas-insulated switchgear (GIS) as a reliable online condition monitoring method. This paper dealt with insulation defect diagnosis based on a Random Forest (RF) algorithm with an optimized feature selection method. Four different types of insulation defect models, such as the free-moving particle (FMP) defect, the protrusion-on-conductor (POC) defect, the protrusion-on-enclosure (POE) defect, and the delamination defect, were prepared to simulate representative PD single pulses and PRPD patterns generated from the GILB. The PD signals generated from defect models were detected using the PRPD sensor which can detect phase-synchronized PD signals with the applied high-voltage (HV) signals without the need for additional equipment. Various statistical PD features were extracted from PD single pulses and PRPD patterns according to four kinds of PD defect models, and optimized features were selected with respect to variance importance analysis. Two kinds of PD datasets were established using all statistical features and top-ranked features. From the experimental results, the RF algorithm achieved accuracy rates exceeding 92%, and the PD datasets using only half of the statistical PD features could reduce the computational times while maintaining the accuracy rates. Full article

The alumina doped epoxy resin composites have been widely used to prepare the basin-type insulators in gas-insulated switchgear (GIS). In recent years, the air cavity defects in the basin-type insulators became one of the most common factors to induce GIS faults. Therefore, the development of novel detection techniques for air cavities in epoxy resin composites is of great importance. In this study, multiple epoxy resin samples containing various submillimeter air cavities were prepared. Long pulse thermography (LPT) was employed to detect defects in the epoxy resin composite, and multiple data processing methods were applied to extract the characteristics of the air cavity defects. Quantitative analysis was also used to characterize the detection effectiveness in different thermograms. Experimental results show that derivative thermograms are capable of detecting air cavity defects with a diameter of 0.2 mm at a depth of 1.2 mm. The derivative thermograms can reduce noise and sharpen the defect recognition, exhibiting a high signal-to-noise ratio (SNR). This study also analyzes the impact of the aspect ratio on the detection result, which indicates that the defect with a small aspect ratio is difficult to detect. Based on the infrared thermography technology, this work provides a promising route for defects detection in basin-type insulators. Full article

GIS circuit breakers play a critical role in maintaining the reliability of modern power systems. However, mechanical failures, such as spring fatigue, transmission rod jamming, and loosening of structural components, can significantly impact their performance. Traditional diagnostic methods struggle to identify these issues effectively due to the enclosed nature of GIS equipment. This study explores the use of vibration signal analysis, specifically during the closing transient phase of the GIS circuit breaker. The proposed method combines wavelet packet decomposition, rough set theory for feature extraction and dimensionality reduction, and the S_Kohonen neural network for fault type identification. Experimental results demonstrate the robustness and accuracy of the method, achieving a diagnostic accuracy of 96.7% in identifying mechanical faults. Compared with traditional methods, this approach offers improved efficiency and accuracy in diagnosing GIS circuit breaker faults. The proposed method is highly applicable for predictive maintenance and fault diagnosis in power grid systems, contributing to enhanced operational safety and reliability. 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

This paper proposes a novel Ordinal Regression Multi-Task Learning (OR-MTL) framework to address challenges in multi-task diagnosis of PD in Gas-Insulated Switchgear (GIS). GIS PD diagnosis typically involves tasks such as discharge-type identification and severity assessment, which is essentially an ordinal regression problem facing challenges such as high label noise and inconsistent ranking of prediction outcomes. To address these challenges, the OR-MTL framework introduces two key innovations: a dynamic task-weighting strategy based on excess risk estimation, which mitigates the negative impact of label noise on multi-task learning weight allocation, and an ordinal regression loss function based on conditional probability, which ensures consistent prediction ranking through conditional probability chains. Experiments on GIS PD datasets demonstrate that the excess risk-based task-weighting strategy exhibits superior robustness compared to traditional methods in high-noise environments, while the proposed ranking consistency loss function significantly improves the accuracy of severity assessment and reduces errors. Ablation studies further validate the effectiveness of the complete OR-MTL framework. This research not only provides an efficient solution for GIS PD diagnosis but also offers new insights and methodologies for multi-task learning involving ordinal regression tasks. Full article

Air switchgear is an important power equipment in the transmission, transformation, and distribution process of the power system. Insulation defects can lead to partial discharge, which is one of the primary causes of air switchgear failure. Current monitoring methods primarily rely on detecting ultra-high frequency or ultrasonic signals generated by partial discharge to identify insulation defects. However, these methods are prone to external signal interference, resulting in substantial detection errors. Based on gas discharge theory and engineering practice, this paper uses three typical defects to represent the main insulation defects of air switchgear, namely metal protrusion defects, insulation layer air gap defects, and metal particle defects. After that, the validity of the numerical model to describe the partial discharge process of air switchgear insulation defects is verified by the volt-ampere characteristic curve. The discharge process of three typical defect models was investigated by using the numerical model, and the variation curves of the volume fractions of CO, NO₂, and O₃ gases at different voltage levels and different discharge durations were obtained. After analysis, the volume fractions of the three characteristic gases are unique under different defect models and partial discharge quantities. Finally, this paper designed a partial discharge inversion method based on characteristic gases, and fitted time-domain regression equations and partial discharge inversion regression equations based on the changes in volume fractions of the three characteristic gases measured. The research results of this paper provide a theoretical basis for online detection of partial discharge in high-voltage air switchgear through characteristic gases. The method proposed in this paper can also be applied to other gas-insulated equipment, such as GIS, metal-enclosed switchgear, and vacuum circuit breakers. Full article

Due to the challenges in antenna installation and detection performance caused by metal obstruction along the propagation path at a Gas-Insulated Switchgear (GIS) cable terminal, as well as the adverse effects of environmental interference on the detection of partial discharge (PD) by existing flexible antennas, this paper proposes a directional flexible antenna design to mitigate these issues and improve detection performance. The proposed design employs a coplanar waveguide (CPW)-fed monopole antenna structure, where the grounding plane is extended to the back of the antenna to enhance directional reception. The designed flexible antenna measures 88.5 × 70 × 20 mm, and its low-profile design allows it to be easily mounted on the outer wall of the epoxy sleeve at the GIS cable terminal. The measurement results show that the flexible antenna has a Voltage Standing Wave Ratio (VSWR) of less than 2 in the 0.541–3 GHz frequency range. It also maintains stable impedance characteristics across various bending radii, with an average effective height of 10.79 mm in the 0.3–1.5 GHz frequency range. A GIS cable terminal PD experimental platform was established, and the experimental results demonstrate that the bending has minimal impact on the detection performance of the flexible antenna, which can cover the detection range of the GIS cable terminal; metal obstruction significantly impacts the PD signal amplitude, and the designed flexible antenna is suitable for detecting PDs in confined spaces with metal obstruction. Full article

Insulation pull rods used in gas-insulated switchgear (GIS) inevitably contain the micro defects generated during production. The intelligent identification method, which requires large datasets with a balanced distribution of defect types, is regarded as the prevailing way to avoid insulation faults. However, the number of defective pull rods is limited, and the occurrence of different types of defects is highly imbalanced in actual production, leading to poor recognition performance. Thus, this work proposes a data preprocessing method for the insulation pull rod defect feature dataset. In this work, the YOLOv5s algorithm is used to detect defects in insulation pull rod images, creating a dataset with five defect categories. Two preprocessing methods for impurities and bubbles are introduced, including copy–paste within images and bounding box corrections for hair-like impurities. The results show that these two methods can specifically enhance small-sized defect targets while maintaining the detection performance for other types of targets. In contrast, the proposed method integrates copy–paste within images with Mosaic data augmentation and corrects bounding boxes for hair-like impurities significantly improving the model’s performance. Full article

To improve the efficiency and precision of fault diagnosis for isolation switches within Gas-insulated switchgear (GIS), this study introduces an advanced technique utilizing an enhanced support vector data description (SVDD) algorithm. Initially, various operational states of the GIS isolation switch are simulated, and the corresponding vibration signals are captured. Subsequently, both the entropy and time-domain features of these signals are extracted to construct a multi-dimensional feature space. High-dimensional feature datasets are then reduced in dimensionality using the kernel principal component analysis (KPCA) method. Furthermore, the conventional SVDD algorithm is modified by incorporating a penalty factor, which allows for a more adaptable classification boundary. This adaptation not only focuses on positive samples but also considers the influence of selected negative samples on the classification hypersphere. Finally, the collected experimental data are classified and predicted. The results indicate that this GIS fault-diagnosis approach effectively overcomes the limitations of traditional methods, which are heavily dependent on training sample data and demonstrate poor algorithm generalization performance. This method is proven to be applicable for the fault diagnosis of isolation switches in GIS. Full article