基于DeviceNet的网络式电机保护器节点的设计

基于DeviceNet现场总线的网络式电机保护器节点集总线通信、电流监控和过载、三相不平衡、接地故障等多种故障报警、保护功能为一体,以均方根电流为判据,采用DN1022芯片作为现场总线节点的网络式电机保护器。实验结果表明,基于DeviceNet的网络式电机保护器可实时、高效地保护电动机,可作为节点挂接在DeviceNet总线上,与主站进行通信。     

铁路信号电缆网络故障在线检测系统设计

实现铁路信号电缆网络在线管理与故障自动诊断，可提高信号电缆的工作可靠性，减少电缆故障的人工排查工作量，提高铁路运营的自动化程度。设计基于同一硬件平台的多种故障检测方法相结合的铁路车站信号电缆网络故障在线检测系统，实现对车站信号电缆网络的实时在线监测和故障自动定位。该系统以DSP＋CPLD模块为核心电路，利用DDS芯片发生任意信号波形，运用新型高速A／D芯片进行采样，通过485总线实现各功能模块之间的通讯。可组成分布式检测网络，利用SSTDR检测技术实现信号电缆的实时在线监测，在线预测电缆低阻故障，再利用TFDR检测技术进行离线故障精确定位和类型判断。     

基于递归神经网络的旋转机械故障诊断方法

为实现对旋转机械的在线故障诊断,对10类故障情况下的振动信号进行频谱分析。发现旋转机械振动信号的频谱中含有丰富的故障信息,以此为故障特征向量建立了诊断模型。在现有神经网络故障诊断方法基础上,提出了一种基于带有偏差单元递归神经网络的在线故障诊断方法,设计了相应的故障样本和故障编码。仿真结果表明,该方法在收敛速度、非线性能力及精度方面明显优于一般方法。对故障模式的回想结果及实际运行结果证明,本方法切实可行,适合于旋转机械的在线故障诊断。     

基于小波和自组织网络的电缆故障识别

为实现电力电缆早期故障在线识别的目的，提出了一种基于小波能量函数和自组织网络的识别方法。首先，提取在线电缆早期故障状态与正常状态的零序电流差的小波能量函数作为输入特征，用自组织神经网络实现故障识别。用欧式距离比较了自组织特征映射神经网络与反向传播（Back Propagation，简称BP）神经网络对电缆故障识别的稳定性。仿真试验结果表明，该识别方法对在线电缆早期故障类型的识别正确可靠，系统具有较好的稳定性。这为电力电缆早期故障的在线诊断提供了理论支持。     

新型自动气象站(DZZ1-2)常见故障和维修方法Ⅰ:故障统计分析与传感器故障排查

文章将分为上下篇撰写,上篇先简要地介绍新型自动气象站的组成部分,利用2018年全省的国家级自动气象站的故障记录做统计分析,统计结果发现,传感器的故障次数占总故障次数的43.56%,在传感器故障统计中,能见度的故障次数最多,占总故障次数21.47%,并发现发生故障的原因主要是能见度的电源板和线缆损坏问题,其余传感器则是线缆问题占绝大数。因此文章先介绍各种传感器故障排查方法和解决方法,后续下篇将从其他模块,如供电模块、通信模块等介绍故障排查和解决方法。     

基于人类进化算法的配电网故障定位

人类进化算法是模拟人类进化机制而建立起来的一种高性能的智能优化算法,是由生物进化算法和知识进化算法结合而成的。为提高配电网故障定位的速度和准确度,将人类进化算法应用于配电网故障定位,对复杂配电网进行处理时结合分级处理思想,先对配电网系统进行分区,在各独立区域中分别使用人类进化算法进行故障定位,再对主干支路和有故障的独立区域进行全局寻优,从而大大减少了计算量。实例表明,与求解配电网故障定位问题的其他一些智能算法相比,这种基于人类进化算法的配电网故障定位方法不仅定位准确,而且定位速度更快,它对求解复杂配电网的故障定位问题尤为优越。     

基于自归一化神经网络的电弧故障检测方法

电弧故障是电气火灾的重要原因.低压线路发生串联电弧故障时,回路电流波形的时域特征与正常工作状态类似,采用传统的特征提取方法无法完整表达时域信号的全部数据特征,限制了电弧故障的特征表达能力,导致检测结果的误报率和漏报率较高.针对此问题,提出基于自归一化卷积神经网络的电弧故障检测方法.该方法将采集到的不同种类负载的电流时间...     

Fault diagnosis for manifold absolute pressure sensor(MAP) of diesel engine based on Elman neural network observer

Intake system of diesel engine is a strong nonlinear system, and it is difficult to establish accurate model of intake system; and bias fault and precision degradation fault of MAP of diesel engine can’t be diagnosed easily using model-based methods. Thus, a fault diagnosis method based on Elman neural network observer is proposed. By comparing simulation results of intake pressure based on BP network and Elman neural network, lower sampling error magnitude is gained using Elman neural network, and the error is less volatile. Forecast accuracy is between 0.015-0.017 5 and sample error is controlled within 0-0.07. Considering the output stability and complexity of solving comprehensively, Elman neural network with a single hidden layer and with 44 nodes is presented as intake system observer. By comparing the relations of confidence intervals of the residual value between the measured and predicted values, error variance and failures in various fault types. Then four typical MAP faults of diesel engine can be diagnosed: complete failure fault, bias fault, precision degradation fault and drift fault. The simulation results show: intake pressure is observable and selection of diagnostic strategy parameter reasonably can increase the accuracy of diagnosis;the proposed fault diagnosis method only depends on data and structural parameters of observer, not depends on the nonlinear model of air intake system. A fault diagnosis method is proposed not depending system model to observe intake pressure, and bias fault and precision degradation fault of MAP of diesel engine can be diagnosed based on residuals.     

基于智能分布式馈线自动化的配电网故障快速自愈方法

在分析配电网故障自愈模式的类型及其特点的基础上,重点研究了智能分布式馈线自动化的故障自愈方法,包括各个功能模块及其故障处置逻辑。最后以故障定位为例,应用一种基于智能分布式FA的矩阵方法,对贵州电网某10 kV馈电线路的多种故障情况进行了算例仿真分析,验证了基于智能分布式FA的配电网故障快速自愈方法的可行性。     

Transistor level fault diagnosis in digital circuits using artificial neural network

In the design of digital circuits, transistor level faults occur due to open or shorted connection in the transistor terminals and with the variations in the transistor parameters. In this study fault diagnosis for hard faults in the digital circuits using artificial neural network and virtual instrument is presented. During the diagnosis process the parametric variations in transistors are also taken into account by varying the threshold voltages of the transistors. The output responses of the circuit under test under faulty and fault free conditions are plotted for all the input combinations. The resulting responses are curve fitted using polynomial curve fitting. The polynomial coefficients are used as signatures values to train the back propagation artificial neural network, which in turn is used for fault classification. The virtual instrument is designed to implement the fault diagnosis system. The system is validated with experiments on universal gates and all the proposed faults are correctly diagnosed.     

基于优化分簇贝叶斯网的转子振动故障诊断

针对柴油发动机的充电发电机结构及振动的复杂性导致其转子振动故障具有多层次性、耦合性和随机性,以及故障信息不完整性等特点,提出了一种基于振动频谱分析和贝叶斯网络的转子振动故障诊断方法。该方法将故障源和故障现象根据专家经验数值化表示并离散化,运用改进的优化分簇算法,构建特定振动故障类型的贝叶斯诊断网络,利用贝叶斯网络推理算法诊断出故障概率分布,并利用具体的故障证据、设定值对该方法进行验证。仿真及实验结果表明,该方法能在故障信息不完整情况下,依据不完整证据信息更新各网络节点的概率状态,实现对不确定信息的推理和估计,得到较好的诊断结果,提高了转子振动故障的诊断准确度。     

一种基于流形正则化随机配置网络的化工过程故障识别方法

考虑到化工过程故障数据的复杂非线性特性和样本潜在的根本结构特征,提出了一种基于流形正则化随机配置网络的故障识别方法.该方法在经典随机配置网络的基础上,在嵌入流形约束的监督机制下随机选取隐含参数,逐个添加隐含节点,然后使用流形正则化最小二乘法计算隐含层的输出权值,保留了数据的重要几何特征,避免了信息冗余,有利于更好地识别...     

Practicable model of coaxial cable channel with splitter and tap via state-transition matrix

Due to the impedance mismatch happening at the terminals and ports of components (splitters, taps, etc.), the frequency-selective fading characteristic exists in the coaxial cable channel. In this paper, the transfer characteristics of each component of coaxial cable network is analyzes. Moreover, a new algorithm to calculate the frequency responses is proposed. This algorithm can estimate all responses of any point-to-point channel accurately at one time. The results have been verified successfully by measurement on actual network, the absolute error of attenuation at any frequency point is less than 0.5 dB. This modeling approach can be used to model any coaxial cable network, so long as the construction and dimension are known. It is helpful to analyze the performance of different distribution networks and to identify potential difficulties. It is also useful in the fault diagnosis and location for the further study.     

GSD2可通信电动机保护器

介绍了GSD2系列可通信电动机保护器的主要技术指标及功能。通过对该系列电动机保护器基于DeviceNet现场总线,集总线通信、电流监控和过载、三相不平衡、接地故障等多种故障报警、保护功能的阐述,说明该保护器可实时高效地保护电动机,可作为节点挂接在DeviceNet总线上与主站进行通信。     

基于分布式光纤振动传感原理的电力电缆故障定位技术研究

研究一种基于分布式光纤振动传感原理和电缆局部放电原理的电力电缆故障定位技术.通过在电缆上施加高压脉冲,使得电缆上有故障的位置产生局部放电,从而产生振动信号.并将放电脉冲信号同步传输给分布式光纤振动监测系统.通过分布式光纤振动传感技术来探测电缆沿线放电产生的振动信号,并对振动信号进行定位.将该故障定位技术应用于电力电缆沿线上监测电缆故障的状态分布,并进行试验验证.实验结果表明,该系统可实现监测多回路30 km电缆线路的故障分布状况,并对故障点进行准确定位.     

基于支持向量机和顺序前项选择算法的PNN风电机组液压变桨的故障诊断

针对液压变桨距系统的强耦合、非线性,以及液压变桨距故障发生原因复杂、故障单一造成的定位问题,该文提出基于支持向量机和顺序前项选择算法的概率神经网络诊断方法。首先,选取SCADA数据的特征值为输入,桨距角为输出,利用支持向量机进行模型的回归,得出桨距角输出的预测值;接着,将测量值与预测值带入顺序前项选择算法,挖掘和发现特征与故障之间的关系,评估各特征之间的重要性,并选出最好的一组特征集合;最后,建立变桨距概率诊断模型,将所选的数据送到故障诊断模型进行训练,再用所选数据进行测试,定位出变桨距系统的故障原因。实验分析表明:基于支持向量机和顺序前项选择算法的概率神经网络液压变桨距故障诊断方法可以有效地分辨出不同故障,并且诊断的精确度得到了提高。     

旋转机械局部故障力的模型诊断及瞬时故障力识别

针对旋转机械中出现的大量局部故障现象,采用基于模型的故障诊断方法提取剩余振动量,利用模态扩展推测转子系统各节点瞬态振动,针对模型诊断中等效力出现的发散情况,提出通过最小二乘法利用挠曲线确定单一周期和准周期故障发生位置.提出利用瞬时能量判别瞬时故障力大小的方法,从而诊断出系统中故障严重程度.实现了仅利用少量传感器即可对转子系统进行精确故障位置和故障力大小的诊断.对转子系统的碰摩故障进行数值仿真,并在转子试验台进行试验验证本方法的正确性.     

基于机械振动信号的锂离子电池组连接故障诊断

为满足高电压大容量的实际应用场景和需求,锂离子电池组往往由成百上千的电池单体通过螺栓、焊接等方式串并联组成。电池组单体间的连接故障会导致接触电阻升高和连接处异常发热,严重影响电池组的性能和安全。提出一种基于机械振动信号的锂离子电池组连接故障诊断方法。利用压电陶瓷传感器实现电压信号和振动信号的相互转换,在每种故障模式下采集振动信号;基于稀疏测度指标和熵测度方法在频域和时域提取故障特征以描述锂离子电池组在不同连接故障模式下的故障特性;利用最大相关最小冗余算法降低高维特征空间的冗余度,选择出最重要的特征;在此基础上,建立基于差分进化算法优化的支持向量机诊断模型。结果表明,该方法诊断准确度为0.963,可以准确检测到锂离子电池组的连接故障并明确故障发生的位置。     

Detection and diagnosis of bearing and cutting tool faults using hidden Markov models

Over the last few decades, the research for new fault detection and diagnosis techniques in machining processes and rotating machinery has attracted increasing interest worldwide. This development was mainly stimulated by the rapid advance in industrial technologies and the increase in complexity of machining and machinery systems. In this study, the discrete hidden Markov model (HMM) is applied to detect and diagnose mechanical faults. The technique is tested and validated successfully using two scenarios: tool wear/fracture and bearing faults. In the first case the model correctly detected the state of the tool (i.e., sharp, worn, or broken) whereas in the second application, the model classified the severity of the fault seeded in two different engine bearings. The success rate obtained in our tests for fault severity classification was above 95%. In addition to the fault severity, a location index was developed to determine the fault location. This index has been applied to determine the location (inner race, ball, or outer race) of a bearing fault with an average success rate of 96%. The training time required to develop the HMMs was less than 5 s in both the monitoring cases.     

基于直流比值法的低压电缆故障检测装置设计

为了保证低压电缆运行的安全性和稳定性,提出基于直流比值法的低压电缆故障检测装置设计方法,该方法在检测装置的硬件设计中设计了信号参考与探测通道、电源模块、信号采集模块和磁电处理电路,将AD605线性放大器设置在磁电处理电路中,以此提高信号的信噪比。在软件设计中利用直流比值法,将投切电阻接入装置母线中,通过电压和漏电流的变化量比值,完成低压电缆故障的检测,实现低压电缆故障检测装置的设计。实验结果表明,所提方法可准确完成低压电缆故障的识别与定位。