Design and implementation of an expert system for remote fault diagnosis in ship lift

In this paper an expert system for remote fault diagnosis in the ship lift was developed by analysis of the fault tree and combination with VPN. The fault tree was constructed based on the operation condition of the ship lift. The diagnosis model was constructed by hierarchical classification of the fault tree structu~, and the inference mechanism was given. Logical structure of the fault diagnosis in the ship lift was proposed. The implementation of the expert system for remote fault diagnosis in the ship lift was discussed, and the expert system developed was realized on the VPN virtual network. The system was applied to the Gaobaozhou ship lift project, and it ran successfully.     

二维联合模糊的液压系统故障诊断专家系统

提出了基于二维联合模糊评判的液压系统故障在线诊断方法;用MATLAB小波分析与模糊评判相结合的双重故障诊断模式,运用联合权重分配法构建故障诊断专家系统模糊矩阵;采用复杂样本方差估计,得出一个客观合理的故障征兆向量,实现了液压系统故障诊断的实时性,精确性;建立了起重机液压系统故障诊断专家系统。     

输油泵机组状态监测分析诊断系统的设计

介绍了一个输油泵机组状态监测分析诊断系统, 研制该系统的目的是为了实时掌握输油泵机组的运行状态, 为针对性的维护提供依据和手段． 文中阐述了系统的构成, 各参量监测原理,着重讨论了状态监测分析诊断系统软件的设计和系统的实施． 系统软件基于 Ｗｉｎｄｏｗｓ Ｎ Ｔ 网络平台, 具有友好的图形用户界面, 实现了数据动态显示、事故自动报警、定时报表打印、领域专门知识帮助与故障诊断等多项功能．     

Transformer Fault Analysis Based on Bayesian Networks and Importance Measures

Complex environment stresses bring many uncertainties to transformer fault. The Bayesian network(BN) can represent prior knowledge in the form of probability which makes it an effective tool to deal with the uncertain problems. This paper established a BN model for the transformer fault diagnosis with practical operation dataset and expert knowledge. Then importance measures are introduced to indentify the key attributes which affect the results of transformer diagnosis most. Moreover, a strategy was proposed to reduce the number of attribute in transformer fault detection and the resource cost was saved. At last, a diagnosis case of practical transformer was implemented to verify the effectiveness of this method.     

模糊神经网络专家系统在故障诊断中的应用

针对汽车电控发动机故障多,具有模糊性和复杂性的事实,结合模糊逻辑、神经网络、专家系统各自的特点,建立了基于模糊神经网络专家系统的发动机的故障诊断系统;采用面向对象的Visual Basic 6.0、MATLAB 7.0和Ac-cess数据库等软件来实现系统结构,对系统的整个流程,尤其是关键点和重难点进行了研究。结果表明:该诊断系统能对电控发动机故障进行快速准确诊断。     

遗传算法优化的模糊神经网络在故障诊断中的应用

本文针对船舶柴油机故障诊断系统提出了一种基于遗传算法优化训练的模糊神经网络诊断方法,介绍了这种模糊神经网络故障诊断系统的结构及其参数形式,通过遗传优化算法对它的权值和阈值进行了学习优化训练。这种方法可以有效地避免通常所选BP算法训练易陷于局部极值的问题,最后将该遗传算法优化训练的模糊神经网络系统应用到船舶柴油机的故障诊断中,通过仿真研究,说明了该方法的有效性。     

基于Sugeno模糊模型的CNC机床故障诊断方法

通过将Sugeno模糊模型用于数控机床故障诊断系统的方式,实现了对各个诊断专家诊断结果的模糊综合,消除了诊断专家诊断结论的随意性,保证诊断结论的准确.利用此方法基于诊断专家系统技术可以实现对数控机床的自动诊断,诊断结果准确可靠.     

Fault Diagnosis and Reliability Analysis Using Fuzzy Logic Method

A new fuzzy logic fault diagnosis method is proposed. In this method, fuzzy equations are employed to estimate the component state of a system based on the measured system performance and the relationship between component state and system performance which is called as “performance-parameter” knowledge base and constructed by expert. Compared with the traditional fault diagnosis method, this fuzzy logic method can use human＇s intuitive knowledge and dose not need a precise mapping between system performance and component state. Simulation proves its effectiveness in fault diagnosis. Then, the reliability analysis is performed based on the fuzzy logic method.     

SDG故障诊断决策表的粒约简算法

为了减少故障特征集的维数,降低流程系统故障诊断知识库的复杂程度,本文将基于二进制粒矩阵的粒约简算法引入到基于SDG模型的故障诊断中.以离心泵与液位系统为例,用粒语言来描述和表达SDG故障诊断模型中的元素,建立反映故障-征兆因果关系的决策表,进而对冗余属性及属性值进行约简,有效地约简了SDG诊断规则,提高了故障诊断的效率.     

基于神经网络和D—S证据理论的汽车电控系统故障诊断方法研究

鉴于目前广泛使用的OBDII标准的车载自诊断系统的诊断精度和准确度都有待于进一步的提高．以电控发动机怠速不稳征兆为例,可提出一种将神经网络和D—S证据理论融合的多传感器故障诊断方法,并用于车栽自诊断系统诊断数据的融合处理和分析。实验结果表明,该方法能够充分利用各种故障的冗余和互补信息,从而显著提高故障的识别能力。     

Primary Research on Real-Time Fault Diagnosis Platform for Fuel Tank System of an Aircraft

Sub-tanks in fuel tank systems of aircrafts transfer fuel to engines in certain order. These sub-tanks and attached tank-accessories affect each other, and make fault diagnosis in such systems rather difficult. Without real measured data, this paper analyzes fault modes and fault effects of the fuel tank system, including its tankaccessories, of a given aircraft. Fault model of the system is built theoretically, and fault diagnosis criteria are deduced. Such criteria are then quantified to train a back propagation neural network(BPNN) as fault diagnosis model. To realize fault diagnosis of the real fuel tank system, a real-time fault diagnosis platform based on Lab View and Vx Works to perform this diagnosis method is discussed. This platform is a technical groundwork for fault diagnosis in real fuel tank systems.     

基于FTA的电喷汽油机燃烧故障分析

故障树是一种倒置的图形演绎分析方法.笔者在文中建立了电喷汽油发动机燃烧故障树模型,确定出引发系统故障原因的各种可能的组合方式和系统发生故障的概率.为进一步研究实用的电喷汽油机故障自诊断系统提供了一种可行方法.     

故障诊断专家系统应用研究

提出了直流斩波电路故障诊断专家系统的理论根据及设计方法。知识库设计为多元故障树，诊断数据来源于对被诊断对象的测试与知识推理，依据特征向量实现故障定位。采用功能级故障诊断模型比依据网络理论建立的数学模型更为简便。     

具有VME总线的车载安全计算机MVB通信板卡

在研究多功能车辆总线MVB、轨道交通车载ATP安全计算机系统的基础上,开发了基于VME总线接口、2乘3取2冗余结构的MVB网络通信控制板,可靠地实现车载ATP安全计算机系统中MVB接口通信功能.在对比了几种冗余结构的基础上,建立数学模型,分析了系统的可靠性和安全性,并详述了VME总线Slave接口的设计及在3取2表决中的同步和容错技术,最后对通信板卡进行了安全测试,在满足IEC61375-1标准的同时,也实现了冗余容错机制,为车载安全计算机控制网络的进一步研究奠定基础.     

基于案例推理和神经网络的车辆故障诊断研究

将人工神经网络和基于案例的推理技术相结合,应用于车辆故障诊断系统中,建立了应急故障诊断模型;基于此模型,研究了车辆维修案例的表示方法并设计了CB神经网络的学习规则,通过系统的仿真训练和仿真诊断,该模型有效地提高了故障诊断的效能,满足车辆应急故障诊断的需求。     

小波包-神经网络在摆式列车倾摆控制系统故障诊断中的应用

针对摆式列车倾摆控制系统故障的特点，研究了神经网络结合小波包分析进行故障诊断的方法，采用小波包分解和信号重构的方法，将在摆式列车试验台上采集到的振动信号分解到不同的频带以提取有关的故障信息，并将振动信号各频带内的能量特征作为训练样本输入前向神经网络，用优于改进梯度下降法的Levenberg—Marquardt优化方法对网络进行训练，对倾摆控制系统的常见故障进行识别和诊断。实践表明，该方法对摆式列车倾摆系统故障的诊断是可靠的。     

船舶压缩制冷装置故障诊断专家系统的设计

随着船舶压缩制冷装置的集成化程度和自动化程度的不断提高,如何减少装置在使用过程中故障的发生并提高排除故障的效率,成为轮机管理工作迫切需要解决的课题。本文结合领域专家的经验和先进的计算机编程技术,提出了船舶制冷装置故障诊断专家的设计思路。借此以提高故障诊断的效率,并提供维修建议。     

船舶电力系统中交流配电网零线故障的诊断

船舶电力系统中采用的三相四线制交流配电网中零线故障时有发生,为了保证船舶电力系统的供电连续性及最大可能地缩短船舶停电时间,本文结合一起零线故障的实际情况,运用电路理论分析了零线故障产生的机理及其危害性,指出三相四线制交流配电网零线接地的重要性,并提出了防止此类事故的基本措施和具体方法。     

基于小波网络的船舶柴油机燃油系统故障诊断

采用小波变换和BP神经网络的辅助式结合,通过小波变换提取故障特征向量作为BP神经网络的输入值,设计并组建了小波神经网络;利用小波变换模极大值分析高压油管燃油压力信号的奇异性,提取故障特征向量;根据故障采集数据并建立学习样本,通过网络训练建立BP神经网络输入和输出间良好的非线性映射,进而通过特征向量输入BP神经网络来诊断故障。实验数据分析表明:该方法具有良好的诊断效果。     

Fault diagnosis for wind turbine based on improved extreme learning machine

A fault diagnosis method based on improved extreme learning machine (IELM) is proposed to solve the weakness (weak generalization ability, low diagnostic rate) of traditional fault diagnosis with feedforward neural network algorithm. This method fuses signal feature vectors, extracts six parameters as the principal component analysis (PCA) variables, and calculates correlation coefficient matrix among the variables. The weight values of control parameters in the extreme learning model are dynamically adjusted according to the test samples’ constantly changing. Consequently, the weight fixed drawback in the original model can be remedied. A fault simulation experiment platform for wind turbine drive system is built, eight kinds of fault modes are diagnosed by the improved extreme learning model, and the result is compared with that of other machine learning methods. The experiment indicates that the method can enhance the accuracy and generalization ability of diagnosis, and increase the computing speed. It is convenient for engineering application.