Maximum Inner Product Method for Extracting the Path-Loss Parameters in Primary Transformer Substations

In order to deploy short-range wireless communication devices in the primary transformer substation, a Maximum Inner Product(MIP) Method is proposed to extract the path-loss parameters in 110 kV and 220 kV primary transformer substations. The maximum inner product of the testing data is calculated to find out the loss index n and the standard deviation σ, and then the pathloss models can be set up. By comparing the MIP with Minimum Mean Square estimation(MMSE) and Cumulative Sum(CUSUM), MIP can match the measured values best. In order to apply the MIP path-loss model, under the initial signal to noise ratio(SNR) at 5 dB and 10 dB, a ZigBee simulation system is constructed to validate the situation that bit error rate(BER) varies with distance. And the ZigBee devices with 5 units are tested in a 220 kV primary transformer substation. The result of the test proves that the path-loss model is accurate.

Design Of MV/LV Substation Transformer

A substation is a part of an electrical generation, transmission, and distribution system. Substations generally have switching, protection and control equipment, and transformers. The low voltage distribution networks are supplied from MV/LV substation transformer that represent the last step of bringing transformation to the? low voltage and ensuring the? protection and monitoring of the network. There are three types of MV/LV substation: pole-mounted transformer substation, the substation in an envelope and substation in masonry. This paper presents a general description for different MV/LV substation and a methodology to design the various elements making up the public distribution substation (choice of the emplacement, engineering, power transformer, choice of MV cells, circuit breakers, fuses, disconnect? switch, conductors,...etc).

Research on the Seismic-Geological Conditions for a Large Transformer Substation-A Case Study in the Shimian Region,Sichuan Province

A seismic-geological disaster can obviously affect an engineering site in three aspects:the first is ground faulting caused by the earthquake;the second is strong ground motion;the third is geological disasters such as landslides,mud-rock flows and liquefaction.Through the case study of selection of the huge transformer substation in the Shimian region of Sichuan Province,this paper proposes that the activity pattern and spatial distribution of faults near the site are crucial factors for evaluating the seismic-geological conditions for the location of huge transformer substations.

Planning of Anti-Disaster Transformer Substation Based on NN and PSO

Recently, the frequent extreme natural disasters made enormous damage to the electric grid leading to blackouts. The lifeline system aiming at providing continuous power supply for the important load in extreme natural disasters was designed in that condition. In this paper, a developed model for planning of the transformer substation in lifeline system? which considered the effect of existing transformer substations, the motivated areas and punishment areas was proposed. The Hopfield NN was adopted to solve the feeders and the PSO was adopted to new the locations of the transformer substations based on the feeders. The planning result not only took fully use of the existing substation but also get the suitable location for new construction which was satisfactory.

基于改进Transformer的变电站复杂场景下电力设备分割

【目的】变电站电力设备种类多设备之间连接关系复杂,普遍存在设备位置和图像对比较为单一,实际应用中只能获得有限数量的目标图像和标记以及传统方式分割带来的电力设备图像分割精度不够的问题,将卷积神经网络(Convolution Neural Network,CNN)与Transformmer结合组成新模型进行变电站电力设备的分割,提出了一种基于编解码器结构的新型SE-Transfomer(Substation Equipment Transformer)网络。【方法】为了获取局部上下文信息,编码器首先利用CNN提取空间特征图。同时,对特征图进行了精心改造,多尺度特征输入进行全局特征建模。该解码器利用Transformer提取全局深层特征,并进行逐步上采样来预测详细的分割图。SE-Transfomer在山西省梁家庄变电站数据集上进行广泛实验,其纵向结果的Dice系数(Dice)、召回率(Recall)、特异度(Specificity)和均方根误差(RMSE)分别为89.31%,90.52%,89.62%和11.32.【结果】结果表明,SE-Transfomer在变电站电力设备的扫描上获得了与以往最先进的分割方法相当或更高的结果。

Planning of Anti-Disaster Transformer Substation Based on NN and PSO

Recently, the frequent extreme natural disasters made enormous damage to the electric grid leading to blackouts. The lifeline system aiming at providing continuous power supply for the important load in extreme natural disasters was designed in that condition. In this paper, a developed model for planning of the transformer substation in lifeline system which considered the effect of existing transformer substations, the motivated areas and punishment areas was proposed. The Hopfield NN （neural network） was adopted to solve the feeders and the PSO （particle swarm optimization） was adopted to new the locations of the transformer substations based on the feeders. The planning result not only took fully use of the existing substation but also got the suitable location for new construction which was satisfactory.

Mitigation of Transients in Capacitor Coupled Substations Using Traditional RLC Filter Techniques

This article presents an extensive examination and modeling of Capacitor Coupled Substations (CCS), noting some of their inherent constraints. The underlying implementation of a CCS is to supply electricity directly from high-voltage (HV) transmission lines to low-voltage (LV) consumers through coupling capacitors and is said to be cost-effective as compared to conventional distribution networks. However, the functionality of such substations is susceptible to various transient phenomena, including ferroresonance and overvoltage occurrences. To address these challenges, the study uses simulations to evaluate the effectiveness of conventional resistor-inductor-capacitor (RLC) filter in mitigating hazardous overvoltage resulting from transients. The proposed methodology entails using standard RLC filter to suppress transients and its associated overvoltage risks. Through a series of MATLAB/Simulink simulations, the research emphasizes the practical effectiveness of this technique. The study examines the impact of transients under varied operational scenarios, including no-load switching conditions, temporary short-circuits, and load on/off events. The primary aim of the article is to assess the viability of using an established technology to manage system instabilities upon the energization of a CCS under no-load circumstances or in case of a short-circuit fault occurring on the primary side of the CCS distribution transformer. The findings underscore the effectiveness of conventional RLC filters in suppressing transients induced by the CCS no-load switching.

基于transformer的门控双塔模型预测H1N1流感抗原性

流感病毒血凝素蛋白的快速演变导致新的病毒株不断产生,新的病毒株可能引起季节性流感甚至全球流感大爆发。及时检测出抗原变异体对疫苗的筛选和设计至关重要。鲁棒的抗原性预测模型是应对疫苗挑战的有效方法。各种端到端的特征学习工具为蛋白组学提供了良好的特征表示方法,但是现有的甲型流感预测模型还不能有效地提取并利用血凝素蛋白氨基酸序列中的特征。基于transformer设计一个门控双塔模型,通过输入甲型流感病毒血凝素蛋白的氨基酸序列,利用两个并行的编码器分别从血凝素蛋白氨基酸序列的时间维和空间维上捕捉抗原特征,并学习特征与预测结果间的非线性关系。为了减少数据中的噪声,融合时间维与空间维上的特征时,通过门机制自适应地获取衡量它们相对重要性的权重进行选择性融合,最后使用融合特征预测H1N1流感抗原变异株。在H1N1数据集上的实验结果表明,该模型利用优秀的非线性特征学习能力提高了抗原变异的预测性能,同时具有良好的鲁棒性。

基于Transformer和注意力机制的角钢塔螺栓缺陷检测模型

螺帽缺失、螺栓缺失是角钢塔建设阶段常见的结构缺陷,但由于特征区分度低现有目标检测算法对螺栓缺陷检出率较低.针对这个问题,首先基于Transformer对卷积特征进行特征编码提出了全局信息提取算子,其次通过通道注意力机制自适应组合候选检测框多尺度缩放后引入的局部背景信息,最后基于图像分割与背景融合对螺栓缺陷样本进行数据扩增.消融实验表明上述策略均能有效提升螺栓缺陷检测效果且相互不排斥,与其他典型算法对比验证了本文算法的先进性.

A Monitoring Method for Transmission Tower Foots Displacement Based on Wind-Induced Vibration Response

The displacement of transmission tower feet can seriously affect the safe operation of the tower,and the accuracy of structural health monitoring methods is limited at the present stage.The application of deep learning method provides new ideas for structural health monitoring of towers,but the current amount of tower vibration fault data is restricted to provide adequate training data for Deep Learning(DL).In this paper,we propose a DT-DL based tower foot displacement monitoring method,which firstly simulates the wind-induced vibration response data of the tower under each fault condition by finite element method.Then the vibration signal visualization and Data Transfer(DT)are used to add tower fault data samples to solve the problem of insufficient actual data quantity.Subsequently,the dynamic response test is carried out under different tower fault states,and the tower fault monitoring is carried out by the DL method.Finally,the proposed method is compared with the traditional online monitoring method,and it is found that this method can significantly improve the rate of convergence and recognition accuracy in the recognition process.The results show that the method can effectively identify the tower foot displacement state,which can greatly reduce the accidents that occurred due to the tower foot displacement.

A New Approach with Three Dimension Figure and ANSI/IEEE C57.104 Standard Rule Diagnoses Transformer’s Insulating Oil

The dissolved gas analysis (DGA) is an effective method for detecting incipient faults in immersed oil power transformers. In this paper, we investigate the DGA methods and employ the ANSI/IEEE C57.104 standards (guidelines for the interpretation of gases generated in oil-immersed transformers) and IEC Basic Gas Ratio method to design a heuristic power transformer fault diagnosis tool in practice. The proposed tool is implemented by a MATLAB program and it can provide users a transformer diagnosis result. The user keys in the data of H2, CH4, C2H2, C2H4, and C2H6 gases dissolved from the immersed oil transformer’s insulating oil measured by ASTM D3612. The analyzed results will be represented in texts and figures. The real measured data of the transformer oil were taken from Taiwan Power Company substations to verify the validation and accuracy of the developed diagnosis tool.

优化Swin Transformer的塔式起重机销轴安全状态识别算法

为减小塔式起重机运行安全隐患,提高机器视觉检验销轴连接状态的准确率,提出一种优化Swim Transformer的塔式起重机销轴安全状态识别算法;首先通过采集工地现场塔式起重机销轴安全状态图像,创建数据集;其次对数据集中销轴安全状态分类,并进行独热编码;然后基于Swin Transformer算法,建立销轴安全状态的识别模型,构造和优化损失函数;再运用AdamW优化器更新梯度,经过1000次训练迭代后得到最终模型;最后在所创建的销轴图像数据集上,进行试验验证。结果表明:所提优化算法提高了塔式起重机销轴安全状态识别能力:准确率为99.4%、平均精度为99.4%,平均召回率为99.4%,平均特异度为99.6%,呈现出良好的分类和泛化能力;同时明显优于ShuffleNet、DenseNet和EfficientNet等3种典型算法;与原Swin Transformer算法相比,准确率也提高了3.6%。

A New Principle of Fault Identification of on the Same Tower Based on Traveling Wave Reactive Powers

In order to improve the reliability of fault identification of the double-circuit transmission lines on the same tower, a new algorithm for fast protection of double-circuit transmission lines on the same tower based on the reactive powers of traveling wave is proposed. With the implementation of S-transform, the initial traveling wave reactive powers are calculated and the change characteristics of reactive power under different fault conditions are studied. The protection criterion is constructed by analyzing the ratio of the reactive powers of the same end on double-circuit transmission lines and the ratio of the reactive powers at both ends on the same line. According to the ratio of reactive power on the same side of the line and both ends of the same line, it is possible to identify whether the faults of the double-circuit line of the same tower occurred in or out of the protection zone. A large number of simulation results show that the protection performance is sensitive and reliable, and quick to respond. The criterion is simple and is basically not affected by fault initial angles, fault types, and transitional resistances.

基于Transformer技术改进的Yolov5鸟巢识别算法研究

基于高密度遮挡下鸟巢识别正确率低的问题,提出一种基于Transformer技术改进的Yolov5变电站鸟巢识别算法模型。首先将现有Yolov5算法原本的Yolo预测头(Yolo Prediction Heads)替换为Transformer预测头(Transformer Prediction Heads,TPH),同时,为了提高对小物体的检测能力新增了一个预测头。然后嵌入卷积注意力模块(Convolutional Block Attention Module,CBAM),提取注意区域,以抵制干扰信息,关注有用的目标对象。最后利用CSPDarknet53结构设计思想,提取最终的特征图,经CSP模块将输出的特征图进行快速降维。实验结果表明,对比Yolov5算法,TPH-Yolov5算法的mAP(Meanaverage Precision)值提高了15.7%。

高比例分布式电源配电网中低压柔性互联协调规划

柔性互联技术是解决高比例分布式电源(distributed generation,DG)配电网面临诸多问题的有效手段之一。提出了一种基于多层优化的配电网中压与低压柔性互联协调规划方法。首先,建立基于电力电子柔性互联设备(flexible interconnected devices,FID)的中低压柔性互联配电网潮流模型。然后,构建三层协调规划模型,上层以低压FID年运行成本及台区变压器负载率的年方差最小为目标,中层以中压FID年运行成本及从上级电网年购电成本最小为目标,分别决策低压和中压FID的安装位置与容量,下层以各场景的从上级电网购电成本最小为目标优化系统运行,并采用自适应粒子群优化和二阶锥规划相结合的混合算法求解。最后,采用含高比例DG的IEEE 33节点配电网进行算例分析,通过柔性互联规划系统的年综合运行成本降低了19.01%,台区变压器负载率的年方差减少了82.59%,验证了所提规划模型的有效性。

基于改进Faster R-CNN的变电站设备外部缺陷检测

针对变电站设备外部缺陷目标检测任务中目标形状多样,周围环境复杂,当前代表性算法识别准确度低,错检漏检严重的问题,对比了众多目标检测算法在变电站设备缺陷数据集上的检测结果,检测精度较高的是添加了特征融合金字塔结构的Faster R-CNN(faster region-based convolutional network)算法,但其对小目标物体和设备渗漏油的检测精度仍有提升空间,为此设计一种基于Faster R-CNN的改进算法。改进算法通过对输入图像进行数据增强,在网络中添加SPP(spatial pyramid pooling)结构以及改进特征融合方式,对分类以及边界框回归损失函数进行改进的方式来提高缺陷的检测精度。与原Faster R-CNN算法进行对比,改进算法在变电站设备缺陷目标检测数据集的检测结果中AP(average precision)(0.5∶0.95)提高了2.7个百分点,AP(0.5)提高了4.3个百分点,对小目标物体的检测精度也提高了1.8个百分点,试验结果验证了该方法的有效性。

基于电子式电压互感器边界特性分析的35 kV配网输电线路单端暂态量保护方案及其整定

随着分布式电源广泛接入配电网,传统三段式电流保护方案的性能严重劣化。单端暂态量边界保护由于具备不依赖电源特性等突出优势,有望成为改善主动配电网保护配置性能的有效方案,但其需依附于线路边界强健的滤波作用。为此,该文研究发现,可利用智能变电站和智能开闭所中电子式电压互感器、金属氧化物避雷器与其余设备杂散电容共同作为线路边界,其优异的高频滤波作用能够为暂态量保护方案的设计奠定基础;其次,利用区内外故障时电压行波高频频带能量差异构造保护判据,并基于整定门槛与动作时序的合理配合形成单端暂态量阶段式保护方案;最后,基于PSCAD仿真平台验证所提方案的有效性、灵敏性与可靠性,其可与电流保护方案协同互济以强化主动配电网继电保护方案的动作性能。

基于AKNN异常检验与ADPC聚类的低压台区拓扑识别方法

低压台区拓扑信息的准确记录是进行台区线损分析、三相不平衡治理等工作的基础。针对目前拓扑档案排查成本高且效率低的问题,提出一种基于自适应k近邻(adaptive k nearest neighbor,AKNN)异常检验和自适应密度峰值(adaptive density peaks clustering,ADPC)聚类的低压台区拓扑识别方法。该方法利用动态时间弯曲(dynamic time warping,DTW)距离度量低压台区用户间电压序列的相似性,通过AKNN异常检验算法检验并校正异常的用户与变压器之间的关系(简称“户变关系”),在得到正确户变关系的基础上,采用ADPC聚类算法对台区内用户进行相位识别;最后,通过实际台区算例分析验证了该方法不需要人为设置参数,能有效实现低压台区的拓扑识别,具有较高的适用性与准确性。

太阳塔高分辨率光谱观测系统研制与实验教学应用

该文以推进实测天文课程教学改革与提升天文实验教学质量为目标,对太阳塔硬件基础设施进行重新设计与系统优化,研制了一套太阳塔高分辨率光谱观测系统。该系统满足太阳光球、色球层特征谱线的高分辨观测需求,可达到研究太阳黑子和耀斑特性的观测精度。开放式的光路设计与模块化实验平台有助于学生将光学理论与天文实践相结合。文章设计“定标汞灯的光谱拍摄与谱线证认”和“太阳高分辨率光谱拍摄与谱线证认”两个实操型创新实验,从多重视角增进学生开展有关太阳科研的兴趣。实验将实践教学与科学研究充分结合,有效推动了天文实验类课程的教学改革。

地铁地下变电站主变压器室温度控制仿真研究

[目的]在地下变电站内的变压器工作时会产生巨大的热量。若热量不能及时被排出,将会产生主变压器超温等问题,甚至会发生设备故障或火灾事故。因此,需对地铁变电站主变压器室的温度控制进行研究。[方法]以济南轨道交通3号线110 kV地下变电站(齐川站)为例,通过理论分析和数值模拟,考虑机械排风量、变压器放热量及室外环境温度的影响,对主变压器室内的温度控制进行研究;分析8种不同通风工况下,主变压器室内的温度演变规律。[结果及结论]以理论计算值设置机械排风量,可以有效排除变压器产生的热量,且理论计算风量偏保守。现有设计风机可有效排除变压器产生的热量,最大可排除变压器3倍发热量。在室外环境温度为40℃的不利情况下,现有设计风机仍可有效排除变压器产生的热量,实现温度控制目标。