A fault warning for inter-turn short circuit of excitation winding of synchronous generator based on GRU-CNN

Synchronous generators are important components of power systems and are necessary to maintain its normal and stable operation.To perform the fault diagnosis of mild inter-turn short circuit in the excitation winding of a synchronous generator,a gate recurrent unit-convolutional neural network(GRU-CNN)model whose structural parameters were determined by improved particle swarm optimization(IPSO)is proposed.The outputs of the model are the excitation current and reactive power.The total offset distance,which is the fusion of the offset distance of the excitation current and offset distance of the reactive power,was selected as the fault judgment criterion.The fusion weights of the excitation current and reactive power were determined using the anti-entropy weighting method.The fault-warning threshold and fault-warning ratio were set according to the normal total offset distance,and the fault warning time was set according to the actual situation.The fault-warning time and fault-warning ratio were used to avoid misdiagnosis.The proposed method was verified experimentally.

Analysis on the fault characteristics of three-phase short-circuit for half-wavelength AC transmission lines

Half-wavelength AC transmission(HWACT) is an ultra-long distance AC transmission technology, whose electrical distance is close to half-wavelength at the system power frequency. It is very important for the construction and operation of HWACT to analyze its fault features and corresponding protection technology. In this paper, the steady-state voltage and current characteristics of the bus bar and fault point and the steady-state overvoltage distribution along the line will be analyzed when a three-phase symmetrical short-circuit fault occurs on an HWACT line. On this basis, the threephase fault characteristics for longer transmission lines are also studied.

双极短路故障下基于暂态能量抑制的MMC-HVDC电网限流设备的参数优化

模块化多电平换流器高压直流输电电网发生直流短路故障时,具有故障电流上升速率快、峰值高等特征,会严重危害电网安全。为了抑制故障电流发展,缓和高压直流断路器开断电流大小与故障切除时间之间的矛盾,需要在直流侧配置限流设备。首先,研究双极短路故障下不同类型限流设备的工作机理,并从暂态能量的角度探讨能量释放源的分布情况、暂态能量的演化特征及限流设备参数对其限流能力的影响;其次,提出基于NSGA-Ⅱ优化算法的故障限流器与直流电抗器参数优化配置计算方法;最后,在PSCAD/EMTDC仿真系统中搭建四端双极柔性直流电网模型,针对不同电气需求的应用场景,设计相应的限流设备参数优化方案。仿真测试结果表明,该优化方法能够正确地配置限流设备的参数,提高限流设备对暂态能量的抑制效率,验证了所提方法的有效性与可靠性。

Short-circuit Current Characteristics of Wind Generators

To study the effects of wind generators on distribution system protection,the short-circuit current(SCC) characteristics of wind generators is important.Although there are many researches on the issue,a clear agreement has not been reached so far.The SCC characteristics for different wind generators are studied.PSCAD simulation is performed in the same system integrated with different kinds of wind generators,and their results are compared with those reported in IEEE papers.The detection possibility by overcurrent relay(OCR)is discussed based on the simulation results.

The Detection of Inter-Turn Short Circuits in the Stator Windings of Sensorless Operating Induction Motors

This work proposes an alternative strategy to the use of a speed sensor in the implementation of active and reactive power based model reference adaptive system (PQ-MRAS) estimator in order to calculate the rotor and stator resistances of an induction motor (IM) and the use of these parameters for the detection of inter-turn short circuits (ITSC) faults in the stator of this motor. The rotor and stator resistance estimation part of the IM is performed by the PQ-MRAS method in which the rotor angular velocity is reconstructed from the interconnected high gain observer (IHGO). The ITSC fault detection part is done by the derivation of stator resistance estimated by the PQ-MRAS estimator. In addition to the speed sensorless detection of ITSC faults of the IM, an approach to determine the number of shorted turns based on the difference between the phase current of the healthy and faulty machine is proposed. Simulation results obtained from the MATLAB/Simulink platform have shown that the PQ-MRAS estimator using an interconnected high-gain observer gives very similar results to those using the speed sensor. The estimation errors in the cases of speed variation and load torque are almost identical. Variations in stator and rotor resistances influence the performance of the observer and lead to poor estimation of the rotor resistance. The results of ITSC fault detection using IHGO are very similar to the results in the literature using the same diagnostic approach with a speed sensor.

The simulation research for transient current variation in short circuit fault of urban rail transportation

Urban rail transit is one of the most important way for urban residents. However, frequent power failure, especially the short fault hinders the safe and stable operation of rail transit. The research of the transient variation of line electrical parameters in short circuit fault is the basis of researches for technology of line protection and short circuit fault location. Based on Matlab/Simulink, a 24-pulse rectifier circuit model is established, the resistance and inductance value of the catenary and rail network are calculated. The short Circuit fault simulation model of DC traction power supply system is established. The short-circuit fault of the traction network at close and distant points are simulated, the transient variation values of fault current with the different fault distance are analyzed. The simulation results show that the transient current peak of the nearby short circuit is oscillatory and convergent due to the nonlinear devices, which proves the accuracy of the model and provides a reference for the precise configuration of the line protection equipment.

基于Hotelling T2-BiLSTM的同步调相机故障诊断方法

同步调相机故障会严重影响特高压直流输电工程的稳定性。针对特高压电网中不对称电压条件下同步调相机励磁绕组匝间短路故障难以识别问题,提出基于霍特林T2-双向长短期记忆网络(Hotelling T2-BiLSTM)的同步调相机故障诊断方法。首先,从三相电压、三相电流、励磁电流、转子振动和无功功率中提取故障特征,计算Hotelling T2统计量以构建故障检测指标;然后,采用BiLSTM模型对特征进行分类,并利用逻辑回归层进行故障诊断;最后,在动模实验室中进行实验验证其有效性。实验结果表明,所提方法具有较高的故障诊断精度。

基于FFT-LSTM的抽水蓄能发电机定子匝间短路故障诊断方法

定子短路故障是抽水蓄能发电机常见的故障之一,其会对发电机的性能和安全性产生严重影响,为确保抽水蓄能发电机安全稳定运行,提出基于FFT-LSTM的抽水蓄能发电机定子短路故障诊断方法。建立抽水蓄能发电机定子绕组匝间短路故障模型,分析定子绕组匝间短路故障时,发电机定子电、磁相关状态。以抽水蓄能发电机定子绕组匝间短路故障时的三相电流信号为依据,基于磁势相等原理将三相电流变换成两相电流后,利用FFT转换定子两相电流的时域信号为频域信号,获取故障电流频谱图输入LSTM网络中进行处理,输出抽水蓄能发电机定子绕组匝间短路故障诊断结果。实验结果表明,该方法可以更好地区分抽水蓄能发电机正常与故障状态,实现抽水蓄能发电机定子绕组匝间短路故障诊断,且故障诊断的交叉熵损失低。

基于d-q变换及WOA-LSTM的异步电机定子匝间短路故障诊断方法

为了实现对异步电机定子绕组匝间短路故障的可靠在线诊断,提出一种基于d-q变换及鲸鱼优化算法(WOA)优化的长短期记忆网络(LSTM)的故障诊断方法。通过理论推导可知,d-q变换可有效提取定子电流中的特征频谱数据。采用鲸鱼优化算法对长短期记忆网络中的3个关键参数进行优化,建立WOA-LSTM故障分类模型。为了验证基于d-q变换和WOA-LSTM故障诊断方法的有效性,分别以小波变换、快速傅里叶变换及d-q变换提取电流频谱数据作为输入数据集,以一台YE2-100L1-4型异步电机为实验对象进行实验验证。研究结果表明:相比于小波变换及快速傅里叶变换,采用d-q变换能更准确的提取出定子电流中的故障特征,更精确地反映电机故障状态,有助于提高故障分类准确率;相比于传统的LSTM算法,经WOA优化后的LSTM算法分类准确率可达98.3%,能可靠地实现不同程度匝间短路故障的诊断。

含主动限流控制的MMC-HVDC电网直流短路故障电流解析计算

传统的MMC-HVDC电网直流短路故障电流计算一般采用等效RLC电路方法。但是该方法没有考虑主动限流控制(ACLC)对等效电路RLC参数的影响,因此无法直接用于含ACLC的MMC-HVDC电网的直流短路故障电流的解析计算问题。该文通过将ACLC的控制效果等效为虚拟阻抗产生的压降,建立了体现ACLC的控制影响的等效RLC电路,以包含电流变化率限流环节的典型ACLC算法为例,推导了直流双极短路故障条件下ACLC的控制参数与虚拟阻抗的映射关系以及相应的直流故障电流解析表达式。最后,以基于含ACLC的半桥型四端MMC-HVDC电网为例,建立PSCAD/EMTDC仿真模型,对采用ACLC的直流双极短路故障电流解析计算结果进行了验证。结果表明:故障后10ms内直流短路故障电流的PSCAD仿真结果与所提出的含ACLC的等效RLC电路解析计算结果的平均误差在8.29%以内,最大误差在10.99%。因此,使用所提出的方法具有工程实用性。

基于MMC主动限流的VSC-HVDC双极短路故障控保协同策略

直流故障保护是柔性直流输电系统发展面临的主要挑战之一,利用模块化多电平换流器(MMC)的灵活控制实现限流已成为当前研究的热点。MMC的主动限流降低了故障电流变化率和故障电流幅值,易引起故障判断以及保护选择困难。文中以对称单极接线的柔性直流系统为研究对象,采用控保协同思想,将主动限流控制与故障识别相结合,提出了基于主动限流因子的故障区域识别与区分方法实现双极短路故障的区域识别与切除。首先,通过在MMC电流内环控制器中附加故障电流目标预设控制器,在故障发生后可快速跟踪故障电流的变化,自适应地调整MMC输出的直流电压将故障电流控制在预设目标参考值附近;其次,根据不同故障位置时故障电流目标预设控制器输出的限流因子快速确定故障区域。最后,在PSCAD/EMTDC中对四端柔性直流输电系统的不同故障场景进行了仿真分析,验证了所提控保协同策略的可行性和有效性。

基于d-q理论的双馈异步电机定子匝间短路故障诊断方法

为实现双馈异步电机定子绕组匝间短路的早期故障诊断,提出一种基于转子电流特征频率分量的故障诊断方法 .首先,通过分析故障后电机的电磁特性,得到故障后转子电流中会产生特征频率分量的结论 .然后,通过对转子单相电流进行特殊的相移构造出三相电流,并对该组电流进行d-q变换,利用理论推导证明d-q变换后的直流分量幅值能够反映特征谐波的大小,将直流分量作为故障特征量进行双馈异步电机匝间短路故障的诊断.最后,依据有限元法建立故障前后电机的仿真模型,对不同工况下故障特征量的变化进行研究.结果表明:基于d-q理论提取的故障特征量与定子绕组的短路匝数呈正相关,且在转速变化和电压不平衡时也可有效诊断出匝间短路故障;通过设置合理的故障阈值可实现对双馈异步电机定子绕组匝间短路故障的精确辨识.研究结果可以为电机绕组匝间短路故障诊断提供参考.

改进2D-CNN的永磁同步电机故障诊断分析

针对卷积神经网络在噪声环境中特征提取能力不足,导致永磁同步电机故障诊断出现准确率低、泛化能力差的问题,提出了一种改进二维卷积神经网络与混合注意力机制的故障诊断方法。该方法首先将采集的一维时序信号转换为二维灰度图;其次,改进多尺度特征提取模块,将该模块部分普通卷积替换为空洞卷积,以最大程度地提取到数据信号中的有效信息;然后引入混合注意力机制动态更新权重参数,强化故障特征,抑制噪声的干扰;最后使用分类器进行匝间短路故障诊断。实验结果表明:与其他方法相比,文中模型具有更好的准确性和鲁棒性;在各噪声背景下,本模型的准确率均在96%以上,表明所提方法具有较强的抗噪性能和泛化能力。

Reducing the Short Circuit Levels in Kuwait Transmission Network

This paper describes the study analysis performed to evaluate the available and potential solutions to control the highly increasing short circuit （SC） levels in Kuwait power system. The real Kuwait High Voltage （HV） network was simulated to examine different measures at both 275 kV and 132 kV stations. The simulation results show that the short circuit currents exceed the permissible levels （40 kA in the 132 kV network and 63 kA in the 275 kV network） in some specific points. The examined measures include the a study on changing the neutral point policy, changing some lines from alternating current （AC） to direct current （DC）, dividing specific bus bars in some generating stations and applying current limiters. The paper also presents a new plan for the transmission network in order to manage the expected increase in short circuit levels in the future.

基于参数优化VMD和多尺度模糊熵的星-三角接法FS-PMM匝间短路故障诊断方法

星-三角(Y-Δ)接法多层绕组结构可以抑制分数槽永磁电机电枢磁场的低次谐波磁动势,提高电机运行效率。但其结构较常规Y接法双层绕组结构更为复杂,发生匝间短路的风险更高。首先,建立Y-Δ接法分数槽永磁电机(FS-PMM)发生匝间短路的电路模型,推导出故障发生后电机三相电流,分析出三相故障电流会受匝间短路位置的影响。其次,利用自适应权重和柯西-高斯变异策略对鲸鱼捕食优化算法进行改进,用于优化变分模态分解参数,提出一种参数优化的变分模态分解算法对电流信号进行处理。最后,通过计算电流和电磁转矩的多尺度模糊熵,提出Y-Δ接法FS-PMM匝间短路故障诊断方法。该方法故障诊断准确率达到95%以上,并可以对Y接法部分和Δ接法部分的匝间短路故障进行有效区分。

fault500 kV变电站35 kV串联电抗器故障分析及建议

某500kV变电站主变35kV侧发生一起电容器组串联电抗器短路故障,通过对事故现场检查,结合故障录波器记录,对本次事故发生的过程进行了分析并得出结论。针对本次故障暴露出的问题,从串联电抗器安装位置、在线监测等方面提出了事故防范措施,对于变电站电容器组安全运行具有一定参考价值。

3#循环水551-K-01A冷却塔风机故障分析

根据型号为YAKK355-4WF1的电机在运行过程中内部引线与绕组焊接部位发生短路故障,对此进行深入剖析,得出故障原因并提出了解决措施,为今后电机的运行维护提供宝贵经验。

用于MMC-HVDC直流故障保护的新型拓扑及重合闸控制策略

针对柔性直流架空输电线路频发的瞬时性直流故障,提出了模块化多电平改进子模块结构和混合级联拓扑以及MMC系统重合闸控制策略。新型子模块及混合级联结构具有直流故障自动闭锁和迅速恢复的能力,能进一步降低造价及损耗,并能继承已有成熟的控制方法。系统重合闸控制可以使柔性直流系统在小电流情况下判断直流故障是否消除并恢复系统运行,能有效应对永久性、瞬时性直流双极短路故障。文章构建了等效电路来分析直流双极短路故障及重合闸过程,并通过PSCAD/EMTDC仿真对所提方案进行了有效性验证。

基于功率损失和U-I特性综合考虑的光伏组件故障诊断方法

分析了光伏组件常见故障下的功率损失及其内部U-I输出特性,提出了一种综合考虑功率损失和内部U-I特性的光伏组件在线实时故障诊断方法。通过仿真功率与实测功率的对比,判断组件是否发生异常功率损失。再根据输出电压变化,判断是否发生短路故障并大致估算短路电池块数。进一步,利用填充因子值判断老化故障,得出组件剩余使用年限。仿真和试验结果验证了该方法可以有效地检测出组件阴影遮蔽、短路及老化等常见故障。

单向功率混合型MMC及其启动/直流短路故障穿越控制

单向功率传输场景下,挖掘桥臂内部全桥及半桥子模块的协调控制空间,提出可节省器件的类半桥子模块及由其与全桥子模块构成的新型单向功率混合型模块化多电平换流器(MMC)。针对启动阶段和直流短路故障穿越期间潜在的电容电压不均衡及电压、电流应力问题,提出适用于该拓扑的启动策略。基于直流环流注入控制实现直流短路故障穿越,保证设备在整个运行区域可靠运行。在MATLAB/Simulink中搭建仿真模型,验证所提控制策略的可行性和有效性。相比现有的混合型MMC,所提拓扑在保证直流短路故障穿越能力的前提下,节省半桥子模块内部的一个开关器件,具有较好的成本优势。