When the new source and load are connected to the grid, many harmonic components are generated, and the harmonics will affect the vibration characteristics of the gas insulated switchgear (GIS). Firstly, the types and components of the harmonics generated when the new sources or loads are connected to the grid are analyzed and summarized. Then the vibration mechanism of the GIS busbar shell is analyzed and the relationship between vibration-related physical quantities and excitation current is investigated. Finally, the simulation model is established based on the existing GIS single-phase busbar shell in the laboratory as a prototype, and the vibration characteristics of GIS under the excitation of multi-frequency sinusoidal current are simulated. Through simulation calculations, it is found that the vibration amplitude of the GIS shell is roughly symmetrically distributed in the axial direction. And the electromagnetic force on GIS is proportional to the frequency of excitation current and the square of the excitation current amplitude. The vibration acceleration frequency of GIS is twice the frequency of the excitation current. When there are multiple harmonic currents, its vibration frequencies are richer and it is easier to cause mechanical resonance. The vibration under current excitation of 50 Hz, 100 Hz, 150 Hz, 200 Hz and 300 Hz is relatively weak, and the maximum vibration acceleration under these five excitation frequencies is 0.58 mm/s 2 . But under the excitation of the 5th harmonic (250 Hz) current, the vibration acceleration of the GIS busbar shell is about 80 mm/s 2 , which is much greater than the results under other frequency excitations.

Due to the variety, size and shape of the invasive animals in substation, the general target detection and case segmentation tasks are often faced with the problems of fewer data and lack of diversity. Optical flow estimation can accurately detect the boundary of the moving object through the change of optical flow during the moving process of the object. RAFT can effectively detect boundaries for small animals moving at low speeds. Therefore, RAFT for small animal intrusion detection can not only effectively eliminate the interference of non-invasive objects, but also cancel the range of intrusion targets, and improve the generalization ability of moving object intrusion

传统高压电气驱动控制方法存在失效率、故障率较高等问题,因此提出一种基于PLC的高压电气驱动控制方法.应用中央处理器、输入输出模块、用户程序处理器、系统程序处理器以及电源构成PLC控制器.采用容量较大、寿命近似于服从指数分布的电容,构建直流母线所支撑的电容模型、控制电路模型和功率元器件(IGBT)模型.通过串联的方式确定故障率,以此实现高压电气的驱动控制系统可靠性研究.实验结果表明与传统方法相比,所提方法对高压电气的驱动控制效果好、故障率低,具有高可靠性以及强鲁棒性.

为有效减少配电网施工期风险行为的出现,设计了一种配电网风险行为智能监控预警系统.通过构建预警指标体系完成数据预处理,采用AJAX技术和OLEDB Provider技术实现系统数据以及数据库实时刷新,及时发现配电网中存在的风险行为.测试结果表明:当监控系统获得风险行为等级后,立即发布预警信息,系统界面上直接显示风险等级和具体预警信息,并给出相似案例解决方案.系统达到了理想的监控预警效果,满足配电网功能需求,一定程度上规避了风险行为的发生.

电流互感器的暂态特性及其评价方法是影响保护装置、关系到系统安全稳定的关键因素,但当下国内缺少对直流电流互感器暂态特性校验的相关研究.因此,为了实现直流电流互感器上升时间,最大过冲,暂态延时以及周期稳定性等暂态性能参数的校验及评价,提出了一种基于重采样技术的直流互感器校验系统.基于校验系统,得到互感器评价的指标依据,进一步提出基于灰色理论的直流互感器特性评价方法.最后通过暂态性能试验,得到了被测直流互感器的暂态特性参数,并建立了其评价模型,通过案例分析,给出不同互感器的量化评价得分值.所提出的方法在直流电流互感器现场校验中具有重要的借鉴价值.

The online monitoring device for transformer core and clamp grounding current can accurately monitor the changes in grounding current of the core and clamp, and timely and effectively detect whether there are multiple grounding situations and other abnormal conditions in the transformer core and clamp. It has been widely used in the power system and gradually replaces the manual inspection of transformer core and clamp grounding current. However, after the installation and operation of such online monitoring devices in the converter station, it was found that there were problems such as unreasonable design and incomplete performance testing plans. This article, by measuring and analyzing the grounding current waveform of the converter transformer core and clamp, identifies the reasons for the abnormal measurement results of the grounding current online monitoring devices for the iron core and clamp during the installation and operation of the converter, and proposes corresponding measures, A higher precision harmonic detection technology and laboratory performance detection method have been proposed at the same time.

Online monitoring and analysis of transformer oil chromatography is of great significance for the assessment of internal insulation with transformer operation. The existence of numerous invalid monitoring sensors in the field makes the quality of online monitoring data degraded, which makes the online monitoring system unable to monitor the operating status of transformers in a timely and accurate manner. This paper propose a data-driven method for evaluating the effectiveness of oil chromatography monitoring sensors by selecting a fixed-length feature data set from online data for evaluation, and then using the distribution of abnormal values, the distribution of consecutive identical values, the variation of coefficient of variation and the variation of gas production rate in the feature data set as criteria to judge the feature data set and obtain the corresponding discriminant values. Afterwards, the discriminant values are assigned weights according to the focus of each criterion to obtain the sensor status values, which are compared with the preset tolerance level to obtain the sensor evaluation results. The method proposed evaluates the effectiveness of online monitoring sensors from several aspects, which can detect faulty sensors in time and is of great significance for improving the accuracy of online monitoring data and the reliability of monitoring device.

针对等温松弛电流法在配电电缆绝缘状态评估中的问题及难题,本文采用国产未老化的10 kV配电电缆新样作为检测对象,通过检测140℃下加速热老化288 h过程中电缆段的等温松弛电流和绝缘切片的高场电导,分析了热老化过程中表征绝缘状态的电流松弛分量、老化因子(A)和阈值电场(Et)变化趋势及范围.结果表明:等温松弛电流中存在3个明显的极化松弛峰,时间常数τ1、τ2和τ3分别在7～12 s、31～39 s和210～536 s范围;热老化过程中等温松弛电流峰2和峰3对应的材料陷阱改变较大,其中峰3的改变最为明显;基于等温松弛电流的老化因子A在1.72～3.17范围,随老化时间的增加老化因子A先降后升,而对应的电导阈值电场Et呈先升后降的趋势,这表明阈值电场(Et)和老化因子(A)存在明显的关联,均是绝缘材料内部分子结构的宏观外在表象;国产电缆未老化时的老化因子A为1.91,已近德国标准DIN VDE 0276的"老年"状态,而热老化48 h时的老化因子(A)降至1.72,达到德国标准的"较好"状态,表明国产电缆老化因子A的偏高可能与电缆交联副产物量的残留相关,应完善国产电缆生产中的脱气工艺.

The gas insulated switchgear (GIS) vibrates during operation. To analyze the impact of harmonic components in the power grid on the vibration characteristics of the GIS. This paper analyzes the vibration mechanism of the GIS busbar shell, and the relationship between the vibration-related physical quantities and excitation current is established. In addition, the vibration test platform is established based on the existing GIS single-phase bus barrel model in the laboratory, and the vibration characteristics of the GIS at different measuring point and under the excitation of multi-frequency sinusoidal current are measured. The measurement results indicate that the vibration amplitude of the GIS shell is roughly symmetrically distributed in the axial direction, and the main vibration acceleration frequency is twice the frequency of the excitation current. When multiple harmonic currents coexist, its vibration frequency is more abundant, and it is easier to cause mechanical resonance.

For effective detection of electrical equipment for partial discharge phenomenon, this article, taking the research of intelligent video detection algorithm, this paper discusses mainly the significance of equipment partial discharge detection algorithm, after introduce intelligent video detection algorithm, simultaneously discharge detection system design, analysis, the basic principle of the detection system, finally combining case to verify this algorithm system testing result, confirmed this system is valid. The method presented in this paper can be used to establish an intelligent video detection algorithm system for partial discharge of electrical equipment effectively. The system is verified to be able to accurately detect and identify whether partial discharge exists in the equipment, and the recognition accuracy is 97

为进一步减轻输电线路进行定期检查、巡视的任务,文章提出了一种利用智能化无人机巡检技术,对航拍图像进行线路的提取和跟踪.采用直方图均衡化及图像滤波对航拍图像进行预处理,解决了航拍图像光照强度以及背景对输电线路元素提取的干扰;采用LSD算法实现了线路边缘的提取,在去除图像背景信号的基础上使用Hough变换数学算法实现了输电线路的准确连接;分别采用粒子滤波和扩展卡尔曼滤波两种图像跟踪方法对航拍视频进行线路跟踪,通过建立输电线运动模型,用仿真软件对其进行识别,两种方法的检测准确度分别为95.34％和94.72％,证实文章处理算法可实现输电线路的提取和跟踪.

For effective detection of electrical equipment for partial discharge phenomenon, this article, taking the research of intelligent video detection algorithm, this paper discusses mainly the significance of equipment partial discharge detection algorithm, after introduce intelligent video detection algorithm, simultaneously discharge detection system design, analysis, the basic principle of the detection system, finally combining case to verify this algorithm system testing result, confirmed this system is valid. The method presented in this paper can be used to establish an intelligent video detection algorithm system for partial discharge of electrical equipment effectively. The system is verified to be able to accurately detect and identify whether partial discharge exists in the equipment, and the recognition accuracy is 97

提出了一种基于油色谱时频域数据和残差注意力的变电站故障分类模型.对收集到的油色谱数据,计算其频域分量和时频域分量的特征比值,将所有数据作为网络的输入来训练网络;残差注意力网络通过跨层连接的方式来堆叠注意力模块,以降低网络的过拟合影响并提升模型训练速度,同时注意力模块能够重点关注对结果影响大的信息,进一步提高对变电站故障分类的准确度.通过实际数据验证了所提方法的有效性和性能的优越性.

电流产生的热效应是影响电缆使用寿命和老化故障的主要原因,建立电缆温度特性模型极其重要.电力企业应能够正确估计配电网电缆的相关老化故障率,然而现有的电缆故障率估计是在额定温度下进行计算的,并没有考虑实际运行中温度变化的影响.采用一种基于人工神经网络的方法估计电缆最高温度,该温度变化满足一定的日负荷曲线.人工神经网络只需4个容易获取的输入变量,利用电缆绝缘组合电热寿命模型,对预测温度曲线各阶段的寿命损失进行估计.最后,利用该寿命模型和概率失效模型预测未来一段时间内电力电缆的故障率.结果表明,失效概率的估计与实际结果一致性高,说明所估算的电缆温度三级逐步变化曲线能够真实反映电缆瞬态温度变化.

In recent years, with the improvement of living standards, people's demand for electricity has gradually increased. With the rapid development of substation informatization and digitalization, intelligent analysis technology can conduct real-time status assessment of substation equipment and improve the efficiency of fault handling in smart substations. The purpose of this paper is to study the research and application of intelligent analysis technology in the design of substation condition monitoring system. This paper analyzes the requirements of the substation condition monitoring system based on intelligent analysis technology, and describes the application architecture of the system and the total volume architecture of the software in detail. This article tests the designed system, and the experimental results show that the system CPU utilization rate is maintained at 50%~60%, and the memory utilization rate is maintained at about 61%~64%. It can be seen that the various components of the system can coordinate and operate stably, and the resource utilization rate fluctuates little, indicating the feasibility of the system architecture.

传统的溶解气体分析方法和基于溶解气体分析数据的人工智能技术在变压器早期故障诊断中的应用由来已久.Dempster-Shafer证据理论已被应用于存在不确定性和冲突的各种面向人工智能的应用中.为了克服故障类型之间的冲突及提升变压器故障诊断正确率,该文提出了基于Dempster-Shafer证据理论和人工智能的变压器故障诊断方法.利用反向传播(Back propagation,BP)神经网络基于5种关键气体的浓度百分比检测变压器故障,并将其作为第一证据.利用模糊逻辑基于3种气体比率检测变压器故障,并将其作为第二证据.利用证据理论对BP神经网络和模糊逻辑检测结果进行集成分析,得到最终的诊断结果.研究结果表明证据理论和人工智能在变压器故障诊断中具有良好的应用前景.

在对变压器常见故障进行介绍的基础上,针对BP神经网络存在的缺陷,提出了经量子免疫优化的BP神经网络算法,通过与不同算法的对比,验证了该算法的准确性和快速性.

Transformer’s dissolved gas analysis(DGA) is a very important means of transformer condition maintenance. With the development of technology, more and more transformers have been installed with online DGA devices,but there is no standard to determine the abnormal gas generation rate of dissolved gas in on-line oil. In order to mine the information of transformer online monitoring data, this paper firstly classifies the changing trend of dissolved gas volume fraction in four kinds of oil after data filtering, which are respectively rising, fluctuating, stable and falling. Then on the quantity statistics found that smooth and growth trend is the main trend. Then counted the growth trend of generation rate of gas volume, using the weibull distribution function and the normal distribution function fitting after their generation rate distribution, the sub-point of distribution function is used as the basis to judge the abnormal gas generation rate. The results show that the threshold method determined by us is strict and has regional characteristics.

This paper introduces an abnormal oil color spectrum of converter transformer during commissioning of UHVDC transmission project. The application of transformer integrated monitoring system based on ultrasonic local discharge, UHF local discharge and high frequency local discharge integrated software and hardware is used to detect and locate the floating potential discharge defects of converter transformer. The rheologic voltage is carried out by endoscope to locate and other parts The method of in-chip inspection verifies the feasibility of the integrated monitoring system for finding similar discharge defects of converter transformer, and provides an effective detection method for fast and accurate detection of transformer defects.

Transient instability accidents are one of the main reasons that disrupt stable operation of power systems and cause economic losses in power grid, and transient stability assessment is an important part of power system safety and stability analysis. Therefore, an analytical algorithm for transient stability margin is proposed in this paper based on asymmetric fault model, where additional impedance is calculated in the case of asymmetrical short circuit and network model of multi-machine system is simplified. In addition, on the basis of the simplified network model, transient stability margin index is established according to equal area criterion. Then, segmented model of aggregated work angle is proposed to further deduce analytical expression of transient stability margin so that influence of fault location and duration on stability margin under asymmetric short circuit can be analyzed. Finally, simulations are performed in four-machine system and New England system to verify effectiveness of proposed method.