Iterative Learning Fault Diagnosis Algorithm for Non-uniform Sampling Hybrid System

For a class of non-uniform output sampling hybrid system with actuator faults and bounded disturbances,an iterative learning fault diagnosis algorithm is proposed.Firstly,in order to measure the impact of fault on system between every consecutive output sampling instants,the actual fault function is transformed to obtain an equivalent fault model by using the integral mean value theorem,then the non-uniform sampling hybrid system is converted to continuous systems with timevarying delay based on the output delay method.Afterwards,an observer-based fault diagnosis filter with virtual fault is designed to estimate the equivalent fault,and the iterative learning regulation algorithm is chosen to update the virtual fault repeatedly to make it approximate the actual equivalent fault after some iterative learning trials,so the algorithm can detect and estimate the system faults adaptively.Simulation results of an electro-mechanical control system model with different types of faults illustrate the feasibility and effectiveness of this algorithm.

Aircraft Engine Gas Path Fault Diagnosis Based on Hybrid PSO-TWSVM

Twin support vector machine(TWSVM)is a new development of support vector machine(SVM)algorithm.It has the smaller computation scale and the stronger ability to cope with unbalanced problems.In this paper,TWSVM is introduced into aircraft engine gas path fault diagnosis.The generalization capacity of Gauss kernel function usually used in TWSVM is relatively weak.So a mixed kernel function is used to improve performance to ensure that the TWSVM algorithm can better balance a strong generalization ability and a good learning ability.Experimental results prove that the cross validation training accuracy of TWSVM using the mixed kernel function averagely increases 2%.Grid search is usually applied in parameter optimization of TWSVM,but it heavily depends on experience.Therefore,the hybrid particle swarm algorithm is introduced.It can intelligently and rapidly find the global optimum.Experiments prove that its training accuracy is better than that of the classical particle swarm algorithm by 5%.

Fault Diagnosis of Nonlinear Systems Using Structured Augmented State Models

This paper presents an internal model approach for modeling and diagnostic functionality design for nonlinear systems operating subject to single- and multiple-faults. We therefore provide the framework of structured augmented state models. Fault characteristics are considered to be generated by dynamical exosystems that are switched via equality constraints to overcome the augmented state observability limiting the number of diagnosable faults. Based on the proposed model, the fault diagnosis problem is specified as an optimal hybrid augmented state estimation problem. Sub-optimal solutions are motivated and exemplified for the fault diagnosis of the well-known three-tank benchmark. As the considered class of fault diagnosis problems is large, the suggested approach is not only of theoretical interest but also of high practical relevance.

Aeroengine Fault Diagnosis Method Based on Optimized Supervised Kohonen Network

To diagnose the aeroengine faults accurately,the supervised Kohonen(S-Kohonen)network is proposed for fault diagnosis.Via adding the output layer behind competitive layer,the network was modified from the unsupervised structure to the supervised structure.Meanwhile,the hybrid particle swarm optimization(H-PSO)was used to optimize the connection weights,after using adaptive inheritance mode(AIM)based on the elite strategy,and adaptive detecting response mechanism(ADRM),HPSO could guide the particles adaptively jumping out of the local solution space,and ensure obtaining the global optimal solution with higher probability.So the optimized S-Kohonen network could overcome the problems of non-identifiability for recognizing the unknown samples,and the non-uniqueness for classification results existing in traditional Kohonen(T-Kohonen)network.The comparison study on the GE90 engine borescope image texture feature recognition is carried out,the research results show that:the optimized S-Kohonen network has a strong ability of practical application in the classification fault diagnosis;the classification accuracy is higher than the common neural network model.

Application of complete ensemble intrinsic time-scale decomposition and least-square SVM optimized using hybrid DE and PSO to fault diagnosis of diesel engines

Targeting the mode-mixing problem of intrinsic time-scale decomposition （ITD） and the parameter optimization problem of least-square support vector machine （LSSVM）, we propose a novel approach based on complete ensemble intrinsic time-scale decomposition （CEITD） and LSSVM optimized by the hybrid differential evolution and particle swarm optimization （HDEPSO） algorithm for the identification of the fault in a diesel engine. The approach consists mainly of three stages. First, to solve the mode-mixing problem of ITD, a novel CEITD method is proposed. Then the CEITD method is used to decompose the nonstationary vibration signal into a set of stationary proper rotation components （PRCs） and a residual signal. Second, three typical types of time-frequency features, namely singular values, PRCs energy and energy entropy, and AR model parameters, are extracted from the first several PRCs and used as the fault feature vectors. Finally, a HDEPSO algorithm is proposed for the parameter optimization of LSSVM, and the fault diagnosis results can be obtained by inputting the fault feature vectors into the HDEPSO-LSSVM classifier. Simulation and experimental results demonstrate that the proposed fault diagnosis approach can overcome the mode-mixing problem of ITD and accurately identify the fault patterns of diesel engines.

Fault Diagnosis with Wavelet Packet Transform and Principal Component Analysis for Multi-terminal Hybrid HVDC Network

In view of the fact that the wavelet packet transform(WPT) can only weakly detect the occurrence of fault, this paper applies a fault diagnosis algorithm including wavelet packet transform and principal component analysis(PCA) to the inverter-side fault diagnosis of multi-terminal hybrid highvoltage direct current(HVDC) network, which can significantly improve the speed and accuracy of fault diagnosis. Firstly, current amplitude and current slope are used to sample the data,and the WPT is used to extract the energy spectrum of the signal. Secondly, an energy matrix is constructed, and the PCA method is used to calculate whether the squared prediction error(SPE) statistics of various signals that can reflect the degree of deviation of the measured value from the principal component model at a certain time exceed the limit to judge the occurrence of the fault. Further, its maximum value is compared to determine the fault types. Finally, based on a large number of MATLAB/Simulink simulation results, it is shown that the PCA method using the current slope as the sampled data can detect the occurrence of a ground fault with small transition resistance within 2 ms, and identify the fault types within 10 ms,without being affected by the sampling frequency.

Study on Fault Diagnosis of Rotating Machinery with Hybrid Neural Networks

With the help of the feedforward neural network diagnostic method, the hybrid diagnostic networks corresponding to information in multiple symptom domains are built and the comprehensive judgment is carried out with weighted average method. Meanwhile, this method has the ability of self learning and self adaptation in order to adapt both the complexity of vibrations produced practically and the pluralistic potent of vibration symptoms induced really for large rotating machinery, especially for turbogenerators. The reliability and precision of diagnosis with this method is heightened. It seems that the method can take more practical value in engineering applications.

The Research on Hybrid Intelligent Fault-diagnosisSystem of CNC Machine Tools

After analyzing the structure and characteristics of the hybrid intelligent diagnosis system of CNC machine toolsCNC-HIDS), we describe the intelligent hybrid mechanism of the CNC-HIDS, and present the evaluation and the running instance of the system. Through tryout and validation, we attain satisfactory results.

Stator Winding Turn Faults Diagnosis for Induction Motor by Immune Memory Dynamic Clonal Strategy Algorithm

Quick detection of a small initial fault is important for an induction motor to prevent a consequent large fault.The mathematical model with basic motor equations among voltages,currents,and fluxes is analyzed and the motor model equations are described.The fault related features are extracted.An immune memory dynamic clonal strategy(IMDCS)system is applied to detecting the stator faults of induction motor.Four features are obtained from the induction motor,and then these features are given to the IMDCS system.After the motor condition has been learned by the IMDCS system,the memory set obtained in the training stage can be used to detect any fault.The proposed method is experimentally implemented on the induction motor,and the experimental results show the applicability and effectiveness of the proposed method to the diagnosis of stator winding turn faults in induction motors.

多策略改进黏菌算法阶段优化HSVM变压器故障辨识

为解决变压器故障诊断精度较低的问题,提出了一种多策略改进黏菌算法(ISMA)阶段优化混合核支持向量机(HSVM)的变压器故障诊断新方法。首先,利用主成分分析(PCA)来消除变量之间的信息冗余并降低数据集维度。其次,引入黏菌算法(SMA),并结合Logistic混沌映射、二次插值、自适应权重多策略改进SMA,以提高SMA算法收敛速度和局部搜索能力;然后,与原始SMA、WHO和GWO算法进行寻优测试,对比验证改进后SMA算法的优越性;最后,使用改进SMA算法分阶段对混合核支持向量机参数寻优,构建ISMA-HSVM变压器故障诊断模型。将降维后的特征数据输入HSVM模型与BPPN、ELM和SVM进行比较,HSVM模型的诊断准确性分别提高了5.55%、8.89%、5.55%。使用ISMA优化HSVM模型参数,与WHO、GWO、SMA算法优化效果比较,结果准确性提高了13.33%、12.22%、5.55%。其中,ISMA-HSVM模型的诊断精度为93.33%。实验结果表明,所提模型有效提升故障诊断分类性能,且具有较高的故障诊断精度。

基于Adaboost-INGO-HKELM的变压器故障辨识

针对目前变压器故障诊断准确率低的问题,提出一种多策略集成模型。首先通过等度量映射(isometric mapping, Isomap)对高维非线性不可分的变压器故障数据进行降维处理。其次,利用混合核极限学习机(hybrid kernel based extreme learning machine, HKELM)进行训练学习,考虑到HKELM模型易受参数影响,所以利用北方苍鹰优化算法(northern goshawk optimization, NGO)对其参数进行寻优。但由于NGO收敛速度较慢,易陷入局部最优,引入切比雪夫混沌映射、择优学习、自适应t分布联合策略对其进行改进。同时为了提高模型整体的准确率,通过结合Adaboost集成算法,构建Adaboost-INGO-HKELM变压器故障辨识模型。最后,将提出的Adaboost-INGO-HKELM模型与未进行降维处理的INGO-HKELM模型、Isomap-INGO-KELM模型、Adaboost-Isomap-GWO-SVM等7种模型的测试准确率进行对比。提出的Adaboost-INGO-HKELM模型的准确率可达96%,均高于其他模型,验证了该模型对变压器故障辨识具有很好的效果。

基于多模式分解和多支路并行残差网络的特高压三端混合直流输电线路故障区域诊断

特高压三端混合直流输电线路发生接地故障时,故障电气量变化存在很强的随机性和非线性,在噪声干扰下其规律性更弱,很难快速、准确地提取故障特征以诊断故障区域。鉴于此,提出一种集电流波形特征提取和故障区域诊断为一体的诊断模型。分析不同区域故障时的电流波形特点,利用数学机理不同的3种算法同时分解故障电流,避免一些容易混叠的模态子序列在单一分解方法中逃逸。利用多支路并行残差网络迅速地挖掘分解分量的多尺度空间耦合交互特征,并结合门控循环单元网络模块,进一步提取故障电流的时间耦合特征,使得特征得到显著增强。利用麻雀搜索算法优化该模型的关键参数,构建充分适应电网故障诊断的网络结构,实现故障区域的快速诊断。仿真结果表明,该方案有着较高的灵敏性、较强的抗干扰能力,满足直流保护的可靠性和速动性要求。

基于HMFDE和t-SNE的旋转机械故障诊断方法

针对旋转机械的故障特征提取较难,以及单一类型的特征无法全面反映故障特性的问题,提出了一种基于混合多尺度波动散布熵(HMFDE)、t分布-随机邻域嵌入(t-SNE)和郊狼优化算法(COA)优化极限学习机(ELM)的旋转机械故障诊断方法。首先,采用特征加权提出了混合多尺度波动散布熵方法,并将其用于提取旋转机械振动信号的故障特征;随后,采用t-SNE方法对混合故障特征进行了特征降维,挑选出了最能够反映故障特性的特征子集,构建了敏感特征样本;最后,采用郊狼优化算法对极限学习机的输入权重和隐含层阈值进行了优化,完成了旋转机械的故障识别和分类;以齿轮箱和滚动轴承故障数据集为对象,对基于HMFDE、t-SNE和COA-ELM的故障诊断方法进行了实验,验证了方法的有效性。研究结果表明:采用HMFDE-t-SNE-CAO-ELM故障诊断方法可以取得100%的故障识别准确率,该方法能够有效地诊断旋转机械的不同故障类型和损伤;相较于基于单一类型特征的故障诊断方法,其准确率分别可以提高0.68%、22.42%、29.18%(齿轮箱)和1.43%、8.23%、23.67%(滚动轴承),虽然牺牲了一定的计算效率,但准确率得到了明显的提高;相较于其他常规故障分类器,COA-ELM的故障识别准确率具有明显的优势。

电动汽车PMSM驱动系统车载诊断技术研究

驱动电机是电动汽车驱动系统的核心,车载诊断和失效保护技术是提高其可靠性的有效技术手段。介绍了汽车随车诊断系统对电驱动系统的各种故障判定方法,并运用案例分析了汽车PMSM驱动控制系统中最常见的故障之一驱动电机抖动故障,呈现出了车载诊断系统判定电机位置传感器不良的典型情况;对电机位置传感器故障进行了simulink仿真并讨论了无位置传感器容错控制方案及发展趋势。

基于混合故障字典的高速公路机电设备故障定位方法研究

针对传统的高速公路机电设备故障定位方法存在故障诊断时间较长,虚警率、误检率和漏检率难以达到用户要求的问题,提出基于混合故障字典的高速公路机电设备故障定位方法。通过多维度传感器无线射频识别技术建立高速公路机电设备器件故障射频波束信息模型,获取高速公路机电设备故障数据。建立两部字典,利用第一部故障字典估算高速公路机电设备故障信息数据与各种故障模式类型之间的中心距离,按照距离远近判断要估计的决策函数类型,根据预定的设计算法,运用第二部故障字典的决策机制精确定位高速公路机电设备故障。试验结果表明,基于混合故障字典的高速公路机电设备故障定位方法能够确保虚警率为0,误检率和漏检率低于1%,比传统检测时间缩短了50%以上。

基于混合式特征选择的滚动轴承故障诊断方法

为降低滚动轴承故障特征集的维数,提升诊断精度,提出一种混合式特征选择方法。该方法由两个阶段构成,首先通过费舍尔分值法对原始特征集进行预排序,根据特征的费舍尔得分按照降序排序,利用得分曲线的拐点确定预选子集的范围,去除原始特征集中的无关特征;然后将遗传算法嵌入Wrapper阶段中,利用分类器的识别精度作为评价标准,从预选子集中去除冗余特征,确定最优子集。通过实验证明,该方法可以有效地用于滚动轴承不同故障类型和不同故障程度的诊断,最优子集在仅保留了关键特征的同时,识别精度得到提升。

基于ICEEMDAN多尺度熵与NGO-HKELM的转子故障诊断

针对电机转子故障信号非平稳、敏感的故障特征不能有效提取,传统分类器参数智能优化算法存在优化速度慢、调整参数多、易陷入局部最优等问题提出基于ICEEMDAN-MSE-KPCA与NGO-HKELM优化的转子故障诊断方法。首先,采用改进的自适应噪声完全集合经验模态分解(improved complete empirical mode decomposition with adaptive noise,ICEEMDAN)方法对转子振动信号进行分解和重构;计算重构信号的多尺度样本熵(multiscale sample entropy,MSE),形成特征向量,通过核主成分分析(kernel principal component analysis,KPCA)方法对高维的特征向量进行降维;最后,将降维后的特征向量输入北方苍鹰算法(northern goshawk optimization,NGO)优化的混合核极限学习机(hybrid extreme learning machine,HKELM)进行转子故障分类。研究结果表明,基于ICEEMDAN-MSE-KPCA与NGO-HKELM优化的转子故障诊断模型,平均识别准确率可达97.7273%,平均寻优时间为1.0681 s,收敛速度快、准确率高以及分类效果好。

基于特征基的GMC卷积稀疏机械故障特征解析方法

在机械设备的复杂工况下,监测信号易受多振动源及环境噪声干扰,导致故障特征微弱且呈现强耦合特性,这给设备故障诊断带来极大挑战。因此,提出了一种基于振动特性基的GMC增强卷积稀疏机械故障特征解析方法,实现微弱耦合故障特征解析。首先,构造了一种自适应单边衰减小波匹配算法以获取最优特征原子,将最优特征原子升维同时匹配故障周期,以得到具有周期特征的振动特征基。其次,提出基于GMC增强的卷积稀疏编码,结合振动特征基优化求解稀疏系数。此外,提出了一种基于平均峭度与谐波能量比的过程参数优化选择方法,克服了优化过程中关键参数难选取的问题。最后,提取包络谱主要特征与理论故障特征频率对比判断故障类型。通过仿真分析和试验台信号验证,并对比分析了基于谱峭度分解和可调变Q因子小波变换GMC稀疏增强等两种传统方法。实验结果表明,相较于上述两种传统方法,本文提出的方法可以有效地分离不同类型的故障特征信号,并实现故障特征的增强。

基于监督对比学习和混合注意力残差网络的隔膜泵单向阀故障诊断

由于工业生产环境中的强噪声和其他环境激励,隔膜泵单向阀不同故障的特征呈现一定的相似性,导致传统深度学习方法对单向阀的故障状态难以准确识别。为解决这一问题,提出了一种结合监督对比学习和混合注意力残差神经网络(HA-ResNet)的隔膜泵单向阀故障诊断方法。首先,将注意力机制引入了残差神经网络以提升网络的学习能力,自适应调节了重要但微弱特征权重,并以恒等变换减少了有效信息被抑制现象;其次,提出了加权“监督对比损失(SCL)+交叉熵(CE)损失”,调节单向阀不同故障状态数据之间的距离,明确了单向阀不同故障状态的分类边界与降低噪声或环境激励的干扰;最后,通过工程实测数据,对监督对比学习和HA-ResNet融合方法的有效性和稳定性进行了验证。研究结果表明:监督对比学习和HA-ResNet融合方法在隔膜泵单向阀验证集上的平均准确率达到了99.3%;与其他故障诊断方法相比,其在诊断精度和稳定性上都具有一定的优势,验证了该方法在噪声干扰条件下故障诊断的可靠性。

基站叠光系统故障诊断方法

叠光技术已在通信基站开展规模应用,但由于基站位置分布分散,光伏设备对维护人员专业技能要求较高,基站叠光系统定期巡检上站成本高、维护难度大。在调研基站叠光系统常见故障类型的基础上,开展基站实地故障模拟试验,建立基站叠光系统典型故障特征模型,提出同站址光伏组件之间发电数据横向比较、历史发电数据纵向比较的故障诊断方法。利用现网叠光基站发电数据进行算法验证,其中周期性固定物阴影遮挡诊断正确率达到88%。该方法可以有效定位基站叠光系统故障光伏组件和故障原因,降低定期上站巡检成本和维护人员技能要求,提高了运营维护效率,具有良好应用前景。