PCA故障检测方法及应用

基于主元分析(PCA)的传感器故障检测方法中T2和SPE统计量是两个重要指标。首先介绍T2统计量超限而SPE没超限故障检测的方法。利用主元相关变量残差统计量代替平方预测误差SPE统计量,并采用累积方差贡献率确定PCA模型的主元数。该方法避免了SPE统计量的保守性。最后将该方法应用于电厂某机组工作过程检测中,通过仿真验证该方法的有效性。     

智能无人驾驶汽车发动机故障检测方法研究

通过对智能无人驾驶汽车的发动机故障检测方法的改进提高对发动机故障的诊断能力。传统方法中对智能无人驾驶汽车发动机故障诊断方法采用机械振动系统信号分析方法,对于智能无人驾驶汽车发动机低噪声、低振动工作条件下故障检测效果不好。提出一种基于多阵元超声换能波束指向性分析的智能无人驾驶汽车的发动机故障检测方法。进行发动机故障检测信号模型构建,提取多阵元超声换能波束指向性特征,计算无人驾驶汽车发动机故障特征的最优分类平面,将故障信号模拟为一个调幅信号,得到多阵元超声换能波束指向性特征的约束函数,实现故障检测。最后在提取故障特征的基础上进行专家系统识别和故障分类诊断,实现诊断决策。仿真结果表明,该方法能准确实现对发动机故障的诊断和判别,检测性能提高明显,展示了较好的应用价值。     

PCA故障重构方法及应用

本文在能够准确进行故障检测的基础上进行研究,首先介绍了PCA的理论知识,然后在已对某一传感器采样数据检测并检测出故障之后,应用主元分析模型,深入研究了PCA方法的传感器故障重构问题,实质上就是控制系统中的容错控制问题。最后将该方法应用于电厂某机组中,通过仿真结果,可以看出,该方法对系统具有很好的故障重构能力。     

基于Elman网络的故障诊断技术研究

研究了将Elman网络应用于某控制系统的故障诊断方法。根据设定的五类故障,应用相关数据对Elman网络进行训练,然后使用满足训练要求的网络对故障数据进行分析,检测该控制系统发生了何类故障。仿真实验结果表明该方法是有效的。     

小经神经网络的信息融合传感器故障诊断方法

本文详细阐述了小波神经网络的结构、原理,提出了基于小波神经网络的信息融合传感器故障诊断新方法。本文通过MATLAB仿真和模拟空调系统温度传感器漂移故障诊断实验表明,在相同的条件下,小波网络在解决传感器故障检测、分离和补偿问题上应用。     

大型机械设备振动系统故障诊断仿真研究

大型机械设备组成结构复杂,容易产生故障,通过对大型机械设备的振动系统故障诊断,提高大型机械设备的稳定运行性能。传统的故障诊断方法采用海量振动样本特征数据聚类分析方法进行故障分类和诊断,诊断性能受到振动数据样本采集和环境的特征的限制,故障检测效果不好。提出一种基于大型机械设备振动系统故障特征专家系统构建的故障诊断模型,并采用abaqus软件进行仿真分析。构建故障诊断专家系统,包括对模糊数据库、模糊知识库和模糊推理机的构建,设计故障诊断的神经网络模糊控制学习算法,通过设计人机结构,实现对大型机械设备振动系统故障的准确推断决策。利用abaqus软件在计算机上建立测试虚拟样机,实现故障诊断在线模型仿真,了解复杂机械系统设计的故障运行性能。仿真结果表明,该系统能有效提高对大型机械设备振动系统的故障诊断能力,实现智能故障诊断控制和自适应故障处理,在机械状态监测等领域具有较好的应用价值。     

Multisim 8在电子电路故障诊断中的应用

描述借助于Multisim 8对实际电路进行电子电路故障诊断的过程,从而得出利用Multisim 8对电子电路进行故障诊断的一般方法,即将故障电路在Multisim 8上仿真,对可疑元件进行故障设置,模拟出与实际电路中相同的故障现象,从而锁定故障元件。对于设计电子电路过程中由于设计者的疏忽造成的故障,也可以利用Multisim 8通过简单的检测分析找出故障元件。随着人们故障诊断水平的提高,相信Multisim 8在电子电路故障诊断中会有更加广阔的应用空间。     

基于SVM的粗糙神经网络的执行器故障诊断方法

由于化工过程对象很难全面获取各种故障数据和故障特征,因此按照化工机理建立过程模拟模型并对实际的故障进行模拟和诊断方法的研究是必要的。本文研究了支持向量机(SVM)的集成诊断方法,并进一步采用改进的粗糙神经网络的故障分类模型,通过分析故障在不同切面的分布诊断故障类型,改进故障诊断性能。针对动态执行器基准平台(DAMADICS)的19种阀门故障模式,与之前较成熟的独立元分析方法进行对比仿真验证,结果表明本文提出的故障诊断方法有效提高了故障诊断效率。     

基于多残差描述的鲁棒故障诊断方法

论文采用自适应阈值、多残差描述故障特征等方法研究鲁棒故障诊断问题。该方法首先采用多层感知机网络建立系统正常工况解析模型,根据不同的故障模式在过程操作单元和控制回路之间故障传播的途径不同,采用多残差描述方法和基于加权移动残差设计各种历史故障特征矩阵,通过与历史故障特征矩阵的匹配度快速诊断故障源。最后利用DAMADICS阀门基准实验平台的19种不同故障模式验证提出的故障检测与诊断方法的有效性。     

煤矿设备中的基于动态模糊与BP神经网络的故障诊断

在煤炭机电设备故障检测过程中,由于涉及到众多的硬件设备,容易出现电压稳定性较差,间接影响故障检测信号不稳定,检测样本数据空间维数大、诊断实时性差等缺点。本文提出了采用动态模糊自学习理论和BP神经网络相结合的方法针对故障进行诊断,首先通过动态模糊自学习方法对设备故障的有效数据,使用BP网络对其进行快速分类诊断。仿真实验表明:本文算法能够有效地提高故障诊断正确率,从而提高诊断的识别与决策能力。     

Modeling and real-time fault identification in transformers

In this paper, a different internal fault modeling and an identification algorithm are presented. There has been an increasing concern about turn-to-turn faults in transformers because of the high costs of unexpected outages. It is not always possible to analyze the transformer behavior under such faults at rated conditions, since the tests are highly destructive. To develop transformer internal fault detection technique, a transformer model to simulate internal faults is required. This paper describes a novel technique and methodology for modeling and identifying transformer internal faults by using transmission line method (TLM) and fuzzy reasoning technique based on dynamic principal component analysis (PCA), respectively. The transformer has been modeled considering non-linearities as hysteresis and saturation. Transformer internal fault currents are successfully discriminated from the rated currents. The degree and priority of transformer internal faults are obtained by the proposed method. It is suited for implementation on computers because of no computation complexity. Hence, the proposed algorithm can be used effectively in real-time fault identification problems.     

RBF神经网络在传感器故障诊断中的应用研究

本文针对传感器在自动化系统中的重要性,指出了传感器故障诊断的必要性、可行性以及实现的基本方法。根据神经网络的原理与特点,阐述了RBF神经网络的基本理论和优点,提出了一种基于RBF神经网络用于传感器故障诊断的思路和方法。     

Prediction model of permeability index for blast furnace based on the improved multi-layer extreme learning machine and wavelet transform

The permeability index of the blast furnace is a significant symbol to measure the smooth operation of the blast furnace. This paper proposes a novel prediction model for permeability index of the blast furnace based on the multi-layer extreme learning machine (ML-ELM), the principal component analysis (PCA) method and wavelet transform (called as W-PCA-ML-ELM prediction model). This modified ML-ELM algorithm is based on the ML-ELM algorithm and the PCA method (named as PCA-ML-ELM). The PCA method is applied on the ML-ELM algorithm to improve the algebraic property of the last hidden layer output matrix which deteriorates its generalization performance due to the high multicollinearity. Because the production data of the blast furnace field contain noises, this paper applies the wavelet transform to remove the noise. Comparing with other prediction models which are based on the ML-ELM, the ELM, the BP and the SVM, simulation results illustrate that the better generalization performance and stability of the proposed W-PCA-ML-ELM prediction model.     

A quantitative causal diagram based optimal sensor allocation strategy considering the propagation of fault risk

Optimal sensor allocation can substantially reduce the life cycle maintenance costs of engineering systems. Considerable effort has been exerted to model the causal relationship between sensors and faults, but without considering the propagation of fault risk. In this paper, a grey relational analysis (GRA) based quantitative causal diagram (QCD) sensor allocation strategy is proposed that can take account of the influence of the propagation of fault risk. QCD is used to describe both the fault-sensor causal relationship and the fault-to-fault causal relationship. A data-driven-based GRA is applied in QCD to calculate the coefficients of the propagation of fault risk. To achieve an accurate relationship between faults and sensors, an improved quantitative analytic hierarchy process is proposed to calculate the coefficients between faults and sensors that is defined as sensor detectability in this paper. An optimal sensor allocation strategy is then developed using an improved particle swarm optimization (IPSO) algorithm under the constraint on sensor detectability to minimize fault unobservability and total cost. The proposed strategy is demonstrated by a case study on a single-phase inverter system. Compared with two other sensor allocation strategies, the results show that the proposed strategy can obtain the lowest fault unobservability of per unit cost (?0.242) for sensor allocation under the propagation of fault risk.     

基于子空间的次分量分析恒模盲多用户检测算法

为了有效的抑制多址干扰,本文提出了一种基于子空间的次分量分析恒模盲多用户检测算法.该方法是将子空间方法与次分量分析恒模算法相结合,有效的消除来自噪声子空间分量的影响.仿真结果表明,在相同的多址干扰情况下,本文建议方法的输出信干噪比比次分量分析恒模算法提高了11dB,比线性约束最小二乘恒模算法提高了17 dB;在不同的多...     

基于因子分析和主成分分析的粗集决策方法

考虑到实际经济管理信息系统中属性的冗余性和决策属性难以获得的困难,将粗集理论引入到因子分析和主成分分析中,首先利用因子分析对指标进行降维,然后利用主成分分析计算综合评价值来构造信息系统的决策属性,进而提出一种基于因子分析和主成分分析的粗集决策方法,并通过粗集理论来获取系统中的有用信息。最终,实证分析验证了本方法的有效性和合理性。     

轿车温度传感器分析

近年来,随着轿车智能化程度愈来愈高,轿车上的电气设备也愈来愈多。轿车上的传感器少至几十个,多至一百多个,豪车上甚至装有几百个传感器。单单一辆车上的温度传感器可能就有四至十个之多。文章从类型、位置与用途、故障分析以及故障检测案例四方面对轿车上常见的温度传感器进行分析。     

A new method for fault prediction of model-unknown nonlinear system

In this paper, the subspace identification based robust fault prediction method which combines optimal track control with adaptive neural network compensation is presented for prediction the fault of unknown nonlinear system. At first, the local approximate linear model based on input-output of unknown system is obtained by subspace identification. The optimal track control is adopted for the approximate model with some unknown uncertainties and external disturbances. An adaptive RBF neural network is added to the track control in order to guarantee the robust tracking ability of the observation system. The effect of the system nonlinearity and the error caused by subspace modeling can be overcome by adaptive tuning of the weights of the RBF neural network online without any requisition of constraint or matching conditions. The stability of the designed closed-loop system is thus proved. A density function estimation method based on state forecasting is then used to judge the fault. The proposed method is applied to fault prediction of model-unknown fighter F-8II of China airforce and the simulation results show that the proposed method can not only predict the fault, but has strong robustness against uncertainties and external disturbances.     

基于Matlab的滚动轴承故障诊断方法的研究

滚动轴承被广泛应用于风力发电、直升机等各类机械设备中,由于其受到复杂的载荷作用并且工作环境较为恶劣,所以轴承较为容易受到损坏。如果不能及时发现轴承故障,则会造成较大的事故,或导致停产与造成经济上的损失。本文通过对轴承故障振动信号的采集,利用Matlab软件对数据进行处理,力求在初期就能够及时发现故障,为维修提供科学依据,节约维修时间和成本。