Substation Equipment Research Articles

A Defect Detection Method for Substation Equipment Based on Image Data Generation and Deep Learning

A Defect Detection Method for Substation Equipment Based on Image Data Generation and Deep Learning

Improving the reliability of power distribution substations equipment for life extension by considering Condition Based Maintenance

Maintenance of aged power equipment is a proven technique for establishing systems reliability and longevity. It is extensively relevant when combined with Condition Based Maintenance (CBM) approaches for predicting power system infrastructure life, especially with imminent obsolescence. The research focuses on distribution companies with mixed aged power infrastructure, which continuously degradate. A significant setback in older systems is the scarcity of replacement parts leading to unplanned investment in substantial infrastructure due to unexpected failed components that are no longer in production. To guarantee excellent infrastructure health in older equipment, utility companies should consider applying Condition Based Maintenance (CBM) using Artificial Neural Network (ANN) to stabilize older equipment and restore malfunctioning assets. Studies have shown that the life span of older equipment can be extended when adequate maintenance strategies are put in place through the prediction of possible failures using equipment inspections and risk matrix. CBM's strategy improved the Key Performance Indicator (KPIs) System Average Interruption Duration Index (SAIDI) has improved by lowering the average monthly customers power interruptions by 19,15 % lesser time spent without electricity. The System Average Interruption Frequency Index (SAIFI) was improved by lowering the average monthly power interruptions frequency by 20,63% lesser outage frequency. The Distribution Supply Loss Index (DSLI) was improved by dropping the average monthly power losses by 7,5% power losses saved. The Customers Average Interruption Duration Index (CAIDI) was improved by lowering the average customer interruption by 36.1% improvement from the average period before the CBM optimization. The Average System Availability Index (ASAI) was improved by shortening the average annual interruption durations by 1,36%. The ASUI was improved by increasing the average duration of electrical power availability by 1.28%. The optimization of CBM was measured over 24 moths period.

Development of A Vertical Wire Clamp Mechanism and Wiring Device

With the improvement of social productivity, high-quality power supply is the main requirement for the power industry. To ensure the stability of power supply, power supply companies need to regularly maintain and repair power equipment, during which the use of grounding wire devices is necessary to protect the working process of maintenance personnel. The existing TV, lightning arrester, and circuit isolation switches of 110kV and above grades in substations mostly use the vertical wire connection method to connect with the equipment. During equipment maintenance, there is a risk of virtual connection and dropping when maintenance personnel install grounding wires on such wires, which threatens the safety of the power grid and personnel. To ensure smooth and stable substation equipment maintenance, a vertical wire clamp mechanism and wiring device have been developed, which not only improves the efficiency of maintenance operations and reduces the labor intensity of maintenance personnel but also reduces the work risks during maintenance operations, and is worth promoting in the industry.

A lighter weight substation infrared defect detection algorithm combining de‐weighted feature fusion and loss function fusion

AbstractThe traditional infrared inspection of substations is usually done by employees with handheld infrared equipment, but the traditional inspection efficiency is not high, and some of the inspection locations have harsh environments, high voltage levels, and high‐risk factors. Given the above problems, this paper proposes an improved defect detection algorithm for substations based on YOLO v7 to solve the difficult problem of infrared inspection of substations. First, the lighter SE‐GhostNetV2 feature extraction network is designed to reduce the computation volume; second, the de‐weighted BIFPN structure is designed for the substation infrared image features to improve the ability of information interaction; finally, the new C‐NWD Loss is proposed to realize the detection of smaller substation equipment and reducing missed detections. The experimental results show that the hybrid accuracy of the algorithm designed in this paper is improved from 92.1% to 96.6%, the model parameters are reduced by 40.1%, the computation amount is reduced by 65%, the detection speed is improved by 87 FPS, and the false detection and missed detections is less, which can achieve real‐time infrared inspection of substations and solve the difficulties existing in traditional substation infrared detection.

Retracted: Image Analysis Method of Substation Equipment Based on Convolutional Neural Network

Retracted: Image Analysis Method of Substation Equipment Based on Convolutional Neural Network

Worn Power Transformers Influence on the Rural Electrical Networks Electrical Supply Reliability

The energy supply of agricultural enterprises is characterized by a number of significant problems, the solution of which has been an urgent task for several decades. Characteristic problems are widely known and considered in the scientific and educational literature: the location of agricultural objects on a large territory, their remoteness from central substations, remoteness from the road network, which makes it difficult for emergency teams to access in case of accidents, a high degree of operation of substation equipment and air lines At the same time, the re-equipment of the park of technological equipment of agricultural enterprises makes it necessary to look at the quality of energy supply in a new way - the microprocessor technology used in modern agricultural production makes high demands on the reliability of energy supply. Also, the issue related to emergency modes in the energy supply system, which lead to millions of losses due to product spoilage due to the termination of the technological process, does not lose its relevance. As you know, the energy supply system should be a model of high reliability, but upon inspection, the situation looks a little different: due to various reasons (including both the power deficit and the wear and tear of the equipment in use), the energy supply does not always meet the expectations of consumers in terms of the quality of the services provided. In the case of interruptions in the energy supply of enterprises (including agricultural ones), interruptions in the energy supply cause much more serious consequences, related to spoilage and underproduction of products and millions of losses.

Modified Analytic Hierarchy Process in Formulating Health Index Model for Substation Equipment

The level of electricity consumption per capita in Indonesia has increased by 6.6% per year on average within 2009 to 2019 and is predicted to grow until 2060. Therefore, the importance of transmission system reliability has been escalated to secure the fulfillment of electrical energy needs. A good maintenance strategy needs to be carried out in order to ensure the reliability of transmission system, one of which is through implementation of asset health index. This research aims to propose a framework that combines the Failure Mode Effect Analysis (FMEA), Analytic Hierarchy Process (AHP), and Simple Additive Weighting (SAW) methods to obtain a mathematical model of asset health index. Case study was conducted at PLN UIP3B Sulawesi in order to formulate health index model for medium voltage cubicle through quantifying the opinions of experts and practitioners in the field of 20 kV cubicle maintenance. The conclusions obtained are: 1) the use of framework based on FMEA, AHP, and SAW is able to produce multicriteria decision making model through objective quantitative approach; 2) the framework can be used as a tool to convert qualitative opinions into a series of quantitative weighting factors; 3) the framework was successfully applied to the case study of formulating cubicle health index model in UIP3B Sulawesi; 4) the framework has a good level of scalability so that in can accommodate further addition of other expert opinion in the future.

Voltage-Induced Heating Defect Detection for Electrical Equipment in Thermal Images

Voltage-induced heating defect is a type of defect that may occur in transformation substation equipment. Although this type of defect is less common compared to current-induced heating defects, it is crucial to identify it due to its association with severe insulation degradation problems that require prompt intervention. However, the temperature variations caused by these defects may be relatively subtle, making it challenging to distinguish them in thermal images. In this work, considering the characteristics of voltage-induced heating defects and the scarcity of defect data, we propose a two-stage method for defect detection. In the first stage, we employ oriented R-CNN to detect oriented parts of the equipment, accurately localizing the centerline of each part. In the second stage, we extract the temperature distribution along the centerline of specific parts and discretize them as features. Subsequently, we train one-class support vector machines based on the features extracted from normal images for defect diagnosis. Experimental results demonstrate that the proposed method is capable of accurately detecting defects while maintaining a low false positive rate.

Soft Sensing Image Analysis and Processing Method of Substation Equipment Defects

Soft Sensing Image Analysis and Processing Method of Substation Equipment Defects

Research on load transfer planning model for equipment maintenance in the substation

The maintenance, inspection, and refurbishment of substation equipment are crucial for ensuring the stability of the power grid’s operation and the reliability of power supply to users. However, currently, there is a lack of methods for rapidly and effectively planning load transfer solutions during substation equipment maintenance periods. To address this, this study is founded on the principles of transmission network planning theory, and an analysis of the similarities and disparities between the planning methods for load transfer solutions during substation equipment maintenance and traditional approaches to transmission network planning is conducted. Furthermore, this paper integrates practical constraints related to maintenance engineering and power grid load flow balance constraints. With the primary optimization objectives of minimizing investment and operational costs during system maintenance while maximizing power grid reliability, a load transfer planning model for equipment maintenance in the substation has been developed. Simultaneously, in conjunction with linear programming theory, the nonlinear constraint terms of the model have been equivalently simplified to enhance the computational performance of the model. Simulation analysis is conducted on case studies constructed based on the IEE-RBTS6 and IEEE-RTS79 systems to validate the effectiveness of the proposed model in solving the optimal maintenance planning problem.

Research on low frequency noise reduction device for substation equipment

Aiming at the pain point that it is difficult to control the low-frequency noise of the substation equipment, a new noise reduction method is proposed. It can reduce the noise propagation of the equipment without changing the structure of the equipment. The discrete element model of particle dampers for substation equipment is established. The energy consumption value of the particle system is used as an evaluation index. It optimizes parameters such as filling rate and particle size and determines the parameters of the scheme with the best damping effect. Through the combination of simulation and test, the test prototype was built to verify the effect. The test data showed that the total noise extremes of the first and second-floor measurement points were reduced by 14.55 dB and 6.99 dB, respectively, after installing the particle damper. This solution adds a new means of low-frequency noise control for substation equipment.

Examination and Repair of Technology of Equipment Status Based on SNN in Intelligent Substation

Aiming at the problems of poor accuracy and low reliability in equipment evaluation and decision results of examination and repair (E&R) for the traditional power system (P-S) state, an E&R technology of intelligent substation (INSU) equipment state based on SNN is proposed. Firstly, based on the operational status of devices and systems in the intelligent substation (INSU), the E&R risks of devices and systems in INSU are evaluated through analysis of device availability. Then, by analyzing traditional CNN and improved SNN networks, a P-S state E&R model for power equipment detection based on SNN is proposed. Finally, a simulation experiment was conducted to compare and analyze the proposed SNN-based INSU device state E&R model with other methods. The results show that the proposed method has a lower system risk in the E&R process and is superior to other comparison methods.

Providing a combined solution to reduce very fast transient overvoltages in gas insulated substations

The use of gas-insulated substations in high voltage levels of power systems is expanding due to its many advantages, such as the need for less space, resistance to environmental pollution, high reliability, and no need for continuous maintenance. One of the phenomena that threatens the insulation distances inside the closed enclosure in these substations is very fast transient voltages. These overvoltages are dangerous for the equipment inside the substation and connected to it as a result of the switching operation of gas-insulated substations, and if repeated, it can damage the internal insulation of the equipment. Also, these transient overvoltages in special cases such as extremely high voltages may cause serious damage to expensive substation equipment. Therefore, in this article, while examining the existing methods to limit very fast transient overvoltages in different and sensitive points of GIS substations, a new combined method based on the simultaneous use of nanocrystalline rings in the busbar and two XLPE cable paths, The direction of connecting the power transformer to the substation is provided. The results of the simulation on the 230 kV side of the GIS substation of Arak city show that the method proposed in this article has the lowest range of overvoltages compared to other methods. By using the proposed combined method, the range of very fast transient overvoltages in the power transformer terminal of the network under study is reduced by 60 % and this reduction can be seen in other points of the substation as well.

Lightning Arrester Analysis at Pandu 150 Kv Substation

The process of distributing electricity from the substation to the consumers often occurs interference, electrical interference at the station caused by two factors that are internal factors and external factors. Internal factors such as lack of good equipment, while external factors such as human error and natural disturbances such as lightning, earthquakes, flood, wind and others. Safety protection system on electrical equipment of Pandu substation. Surge arresters play an important role in Pandu substations to limit switching overvoltages and lightning strikes, followed by overvoltages from lightning current to earth. the efficiency of the arrester is a function of the distance from its location to the protected equipment, the maximum system voltage achieved is 165 kilo vot, the arrester`s rated voltage is 132 kilo volt line impedance /conductor 475,764 ohms, air insulation breakdown voltage 1515.8 kilo voltv, arrester discharge current 4.27 kilo ampers and an optimal distance between arrester and transformer 10.96 meters.

A Visual Fault Detection Algorithm of Substation Equipment Based on Improved YOLOv5

The development of artificial intelligence technology provides a new model for substation inspection in the power industry, and effective defect diagnosis can avoid the impact of substation equipment defects on the power grid and improve the reliability and stability of power grid operation. Aiming to combat the problem of poor recognition of small targets due to large differences in equipment morphology in complex substation scenarios, a visual fault detection algorithm of substation equipment based on improved YOLOv5 is proposed. Firstly, a deformable convolution module is introduced into the backbone network to achieve adaptive learning of scale and receptive field size. Secondly, in the neck of the network, a simple and effective BiFPN structure is used instead of PANet. The multi-level feature combination of the network is adjusted by a floating adaptive weighted fusion strategy. Lastly, an additional small object detection layer is added to detect shallower feature maps. Experimental results demonstrate that the improved algorithm effectively enhances the performance of power equipment and defect recognition. The overall recall rate has increased by 7.7%, precision rate has increased by nearly 6.3%, and mAP@0.5 has improved by 4.6%. The improved model exhibits superior performance.

Post-Earthquake Rapid Assessment Method for Electrical Function of Equipment in Substations

To assess the electrical function of equipment in substations after earthquakes, a rapid assessment method integrating electrical function conversion relation, numerical simulation and map proxy model was introduced. An intermediate mechanical index (IMI) directly related to electrical function could be defined through various theoretical analyses. And a simulation model of equipment is developed for obtaining seismic response data of IMI and easily monitored mechanical indices (EMI). Afterward, a composite map, specifically from the EMI to electrical function, could be formed mathematically by combining the aforementioned conversion and simulation model. Using the response data as training samples, the map would be represented by a proxy model embedded individual or ensemble machine learning algorithms. Once the actual seismic responses are collected by monitoring during earthquakes, the post-earthquake assessment would be conducted based on the input–output operation of the map proxy model. Finally, a practical case was studied using the approach for the electrical contact status of a grid-side bushing installed on a transformer. The error analysis corroborated the accuracy and usefulness of this proposed method. It can be employed analogously for post-earthquake assessments of other equipment and electrical functions, although only one example has validated the feasibility in this paper.

The Influence of Hot Point on MTU CB Condition at the Pgeli-Giugur 1 Bay Line (PT. PLN Paya Geli Substation)

Local heating that occurs in substation equipment is caused by the current flowing in the conductor due to resistance. The parts that often experience heating are the terminals and connections at the substation, especially between two different metals, as well as the conductor cross-section which decreases due to corrosion. So that part must be considered. As for how to control or check the temperature is done by using thermovision. The heat temperature of the Circuit Breaker (CB) equipment at the Bay line PGELI-GIUGUR1 at Paya GeIi Substation is still in normal conditions where the temperature ranges from 20oC-43oC. But one phase need attention if temperature more than 70oC, it is needed for improvement plans. The temperature difference between the phases of the CB equipment at Bay Iine P. GELI-GLUGUR 1 at Paya Geli Substation has reached condition 5 (five), so it needs serious attention and a repair plan, to avoid short circuits between phases (R, S, T).

Seismic interconnecting effects of multi-span flexible conductor-post electrical equipment coupling system

Previous seismic studies have mostly focused on standalone equipment and single-span coupling systems in electrical substations. To fully consider the impact of adjacent equipment, this paper proposed and validated a motion equations-based numerical solution method for seismic responses of multi-span flexible conductor-post equipment coupling systems (CPECSs). Based on this, the influence of equipment frequency, sag-to-span ratio, peak ground acceleration, and equipment number on seismic responses of multi-span CPECSs was investigated. Finally, the equipment range that significantly influences the seismic response of a piece of equipment was studied, thus the concept of seismic correlation segment was further proposed, beyond which the equipment can be ignored in terms of its influence on seismic responses. The results indicate that the proposed numerical method exhibits enough accuracy based on the validation by simulation techniques. The influencing laws of various interconnection factors on seismic responses of equipment provide support for seismic design of substations. Moreover, the seismic correlation segment can be obtained by presetting the response ratio of a piece of equipment in multi-span to single-span systems, not only reducing the number of concerned equipment but also maintaining the calculation accuracy.

Feature selection algorithm for substation main equipment defect text mining based on natural language processing

AbstractThe dimension of relevant text feature space and feature weight of substation main equipment defect information is high, so it is difficult to accurately select mining features. The Natural Language Processing (NLP) medium and short‐term neural network model is used to realise the defect information text feature word segmentation in the log. After extracting the text features of defect information of main substation equipment with high categories to form the feature space; the TF‐IDF algorithm is designed to calculate the importance weight of text keywords, judge the criticality of defect information text feature vocabulary, accurately locate defect information text features, and realise defect information text feature mining. Experiments show that the algorithm has high precision for specific word segmentation of massive substation main equipment log information.

An Identification Method for Irregular Components Related to Terminal Blocks in Equipment Cabinet of Power Substation.

Despite the continuous advancement of intelligent power substations, the terminal block components within equipment cabinet inspection work still often require loads of personnel. The repetitive documentary works not only lack efficiency but are also susceptible to inaccuracies introduced by substation personnel. To resolve the problem of lengthy, time-consuming inspections, a terminal block component detection and identification method is presented in this paper. The identification method is a multi-stage system that incorporates a streamlined version of You Only Look Once version 7 (YOLOv7), a fusion of YOLOv7 and differential binarization (DB), and the utilization of PaddleOCR. Firstly, the YOLOv7 Area-Oriented (YOLOv7-AO) model is developed to precisely locate the complete region of terminal blocks within substation scene images. The compact area extraction model rapidly cuts out the valid proportion of the input image. Furthermore, the DB segmentation head is integrated into the YOLOv7 model to effectively handle the densely arranged, irregularly shaped block components. To detect all the components within a target electrical cabinet of substation equipment, the YOLOv7 model with a differential binarization attention head (YOLOv7-DBAH) is proposed, integrating spatial and channel attention mechanisms. Finally, a general OCR algorithm is applied to the cropped-out instances after image distortion to match and record the component's identity information. The experimental results show that the YOLOv7-AO model reaches high detection accuracy with good portability, gaining 4.45 times faster running speed. Moreover, the terminal block component detection results show that the YOLOv7-DBAH model achieves the highest evaluation metrics, increasing the F1-score from 0.83 to 0.89 and boosting the precision to over 0.91. The proposed method achieves the goal of terminal block component identification and can be applied in practical situations.