Fault Feature Extraction of Diesel Engine Based on Bispectrum Image Fractal Dimension

Fault feature extraction has a positive effect on accurate diagnosis of diesel engine. Currently, studies of fault feature extraction have focused on the time domain or the frequency domain of signals. However, early fault signals are mostly weak energy signals, and time domain or frequency domain features will be overwhelmed by strong back?ground noise. In order consistent features to be extracted that accurately represent the state of the engine, bispectrum estimation is used to analyze the nonlinearity, non?Gaussianity and quadratic phase coupling(QPC) information of the engine vibration signals under different conditions. Digital image processing and fractal theory is used to extract the fractal features of the bispectrum pictures. The outcomes demonstrate that the diesel engine vibration signal bispectrum under different working conditions shows an obvious differences and the most complicated bispectrum is in the normal state. The fractal dimension of various invalid signs is novel and diverse fractal parameters were utilized to separate and characterize them. The value of the fractal dimension is consistent with the non?Gaussian intensity of the signal, so it can be used as an eigenvalue of fault diagnosis, and also be used as a non?Gaussian signal strength indicator. Consequently, a symptomatic approach in view of the hypothetical outcome is inferred and checked by the examination of vibration signals from the diesel motor. The proposed research provides the basis for on?line monitoring and diagnosis of valve train faults.     

Fault diagnosis of motor drives using stator current signal analysis based on dynamic time warping

Electrical motor stator current signals have been widely used to monitor the condition of induction machines and their downstream mechanical equipment. The key technique used for current signal analysis is based on Fourier transform (FT) to extract weak fault sideband components from signals predominated with supply frequency component and its higher order harmonics. However, the FT based method has limitations such as spectral leakage and aliasing, leading to significant errors in estimating the sideband components. Therefore, this paper presents the use of dynamic time warping (DTW) to process the motor current signals for detecting and quantifying common faults in a downstream two-stage reciprocating compressor. DTW is a time domain based method and its algorithm is simple and easy to be embedded into real-time devices. In this study DTW is used to suppress the supply frequency component and highlight the sideband components based on the introduction of a reference signal which has the same frequency component as that of the supply power. Moreover, a sliding window is designed to process the raw signal using DTW frame by frame for effective calculation. Based on the proposed method, the stator current signals measured from the compressor induced with different common faults and under different loads are analysed for fault diagnosis. Results show that DTW based on residual signal analysis through the introduction of a reference signal allows the supply components to be suppressed well so that the fault related sideband components are highlighted for obtaining accurate fault detection and diagnosis results. In particular, the root mean square (RMS) values of the residual signal can indicate the differences between the healthy case and different faults under varying discharge pressures. It provides an effective and easy approach to the analysis of motor current signals for better fault diagnosis of the downstream mechanical equipment of motor drives in the time domain in comparison with conventional FT based methods.     

Induction machine condition monitoring using notch-filtered motor current

This paper presents a new approach to induction motor condition monitoring using notch-filtered motor current signature analysis (NFMCSA). Unlike most of the previous work utilizing motor current signature analysis (MCSA) using spectral methods to extract required features for detecting motor fault conditions, here NFMCSA is performed in time-domain to extract features of energy, sample extrema, and third and fourth cumulants evaluated from data within sliding time window. Six identical three-phase induction motors were used for the experimental verification of the proposed method. One healthy machine was used as a reference, while other five with different synthetic faults were used for condition detection and classification. Extracted features obtained from NFMCSA of all motors were employed in three different and popular classifiers. The proposed motor current analysis and the performance of the features used for fault detection and classification are examined at various motor load levels and it is shown that a successful induction motor condition monitoring system is developed. Developed system is also able to indicate the load level and the type of a fault in multi-dimensional feature space representation. In order to test the generality and applicability of the developed method to other induction motors, data acquired from another healthy induction motor with different number of poles and rated power is also incorporated into the system. In spite of the above difference, the proposed feature set successfully locates the healthy motor within the classification cluster of “healthy motors” on the feature space.     

基于MCSA和SVM的异步电机转子故障诊断

本文提出一种基于电机电流信号频谱分析和支持向量机的异步电机转子故障诊断方法，该方法可以利用支持向量机对电机电流频谱信号的特征信息和故障模式进行关联。对电机定子电流采样后，其信号经FFT变换后提取故障特征量作为支持向量机的输入，基于1对1算法构造了感应电机转子故障多类分类器。实验结果表明，该方法具有很好的分类和泛化能力，可以提高电机故障诊断的准确性。     

An approach for automated fault diagnosis based on a fuzzy decision tree and boundary analysis of a reconstructed phase space

Although reconstructed phase space is one of the most powerful methods for analyzing a time series, it can fail in fault diagnosis of an induction motor when the appropriate pre-processing is not performed. Therefore, boundary analysis based a new feature extraction method in phase space is proposed for diagnosis of induction motor faults. The proposed approach requires the measurement of one phase current signal to construct the phase space representation. Each phase space is converted into an image, and the boundary of each image is extracted by a boundary detection algorithm. A fuzzy decision tree has been designed to detect broken rotor bars and broken connector faults. The results indicate that the proposed approach has a higher recognition rate than other methods on the same dataset.     

应用EMD和双谱分析的故障特征提取方法

针对传统双谱分析从理论上仅能抑制高斯噪声,但对非高斯噪声无能为力的不足,提出了一种利用经验模式分解(empirical mode decomposition,简称EMD)和双谱分析的故障特征提取方法,并应用于滚动轴承故障诊断中。首先,对信号进行EMD分解;其次,利用能量相关法去除EMD分解过程中出现的伪本征模态分量(intrinsic mode function,简称IMF);最后,对得到的真实IMF进行双谱分析提取故障特征。仿真和实验结果表明,所提出的方法优于功率谱分析和传统双谱分析,能够更有效地提取强噪声背景下的机械故障特征信息,为滚动轴承的故障特征提取提供了一种新的方法。     

齿轮裂纹故障仿真计算与诊断

提出了一种利用仿真信号对齿轮裂纹故障进行诊断的方法。从齿轮的单自由度振动模型出发,将裂纹故障等效为模型中轮齿刚度的削减,运用差分算法对模型进行求解,得到齿轮的振动位移、速度以及加速度响应,利用傅立叶变换和双谱分析对仿真结果进行处理,成功地提取了齿轮裂纹的故障信息。     

双谱分析及其在机械诊断中的应用

提出基于双谱分析的机械故障诊断方法。分析双谱的性质和物理意义 ,探讨双谱抑制噪声和提取故障信息的能力。利用双谱分析 2种典型的机械故障 ,结果显示 ,双谱分析与传统的基于 FFT的频谱分析方法相比 ,能更加有效地提取故障征兆。     

基于自编码器和支持向量机的气压传动系统气缸泄漏故障诊断

气压传动系统在制造领域应用广泛,对智能化故障诊断与节能有较大需求。泄漏是气动系统最常见的故障类型及能量浪费的最主要因素之一。以最具代表性的执行元件气缸为研究对象,通过对其上游压力与流量信号进行处理分析,实现对下游气缸常见的内外泄漏故障的有效诊断。信号特征提取通过栈式自编码器完成,提取的特征进行聚类处理评估后送入支持向量机(Support Vector Machine, SVM)分类器进行分类,从而对气缸泄漏故障进行分类和定位。结果表明：通过分析上游信号来确定下游元器件故障状态是可行的;且对于泄漏故障实验,在同等条件下,基于流量信号的平均分类准确率可达到96%,基于压力信号的平均分类准确率为87%。     

变转速工况下基于多传感器信号深度特征 融合的电机故障诊断研究

本文提出一种利用多传感器信号深度特征融合的方法实现电机变转速工况下的故障诊断。首先从多传感器节点同步采集电机的多通道振动、声音和漏磁信号。对漏磁信号进行处理获取电机转子的累积转角曲线,随后利用累积转角曲线对振动和声音信号进行阶比分析处理。最后利用双层双向长短期记忆网络从经过预处理的多传感器信号中提取和融合特征以诊断电机故障。实验结果表明,通过提取和融合8通道的电机振动和声音信号,本文提出的方法能够有效识别电机的高阻接触、偏心、霍尔断线、相间短路、轴承等10类运行状态,分类准确率达到99.86%。该方法有望部署在物联网边缘计算节点中,实现电机的远程在线状态监测和故障诊断。     

基于神经网络和高阶统计量的滚动轴承故障分类

提出一种基于高阶统计量特征和BP神经网络相结合的滚动轴承故障分类方法。以滚动轴承的高阶统计量(双谱、三阶累积量)以及一些常见的无量纲指标作为轴承故障特征输入,以BP神经网络作为分类器,成功地对滚动轴承4种不同的故障进行了分类。对比RBF神经网络,尽管BP神经网络的训练速度不快,但分类效果良好。研究表明,高阶统计量和BP神经网络相结合的滚动轴承分类方法是有效的。     

鼠笼电机转子断条故障的定子电流信号平方解调分析诊断方法

受基频频谱泄露影响,经典MCSA方法诊断鼠笼电机转子断条故障时的诊断能力严重依赖于电机负载大小。针对这一问题,提出了基于定子电流信号平方解调制分析诊断方法。首先采用硬件方式对定子电流信号作基于平方解调制的信号预处理,以此消除制约诊断能力的基频频谱泄露,继而对解调后的信号作快速傅里叶变换,然后根据频谱中是否存在特征频率成分判断转子断条故障发生与否。在3 k W电机实验平台上对所提出的方法进行实验验证。实验结果表明,即使鼠笼电机在轻载或空载条件下运行时所提出的方法仍然能够诊断出转子断条故障,从而有效提高了诊断能力。     

基于最小熵解卷积-变分模态分解和优化支持向量机的滚动轴承故障诊断方法

提出了一种基于最小熵解卷积和变分模态分解以及模糊近似熵的故障特征提取方法,并采用优化支持向量机对故障进行识别分类。首先利用最小熵解卷积方法降低噪声干扰并增强故障信号中故障特征信息,进而对降噪后的信号进行变分模态分解,并利用模糊近似熵量化变分模态分解后包含故障特征信息的模态分量以构建特征向量,之后通过采用扩展粒子群算法优化惩罚因子和核函数参数的支持向量机,对故障样本训练并完成故障识别分类。将所提方法应用于滚动轴承不同损伤程度、不同故障部位的实验数据,验证了该方法的有效性。与基于局部均值分解的特征提取方法相对比,结果表明所提方法可以更精确地提取出滚动轴承故障特征,并能够更准确地完成不同故障的识别;通过与基于网格寻优算法优化的支持向量机方法和基于扩展粒子群优化的最小二乘支持向量机方法相对比,结果表明所提方法具有更好的分类性能,能达到更好的诊断效果。     

Bispectrum of stator phase current for fault detection of induction motor

A number of research studies has shown that faults in a stator or rotor generally show sideband frequencies around the mains frequency (50 Hz) and at higher harmonics in the spectrum of the Motor Current Signature Analysis (MCSA). However in the present experimental studies such observations have not been seen, but any fault either in the stator or the rotor may distort the sinusoidal response of the motor RPM and the mains frequency so the MCSA response may contain a number of harmonics of the motor RPM and the mains frequency. Hence the use of a higher order spectrum (HOS), namely the bispectrum of the MCSA has been proposed here because it relates both amplitude and phase of number of the harmonics in a signal. It has been observed that it not only detects early faults but also indicates the severity of the fault to some extent.     

基于LSTM-RNN的滚动轴承故障多标签分类方法

为了提高长短时记忆神经网络模型(long short-term memory recurrent neural network, 简称LSTM-RNN)对滚动轴承故障分类的正确率并减少训练样本量,提出一种基于多标签LSTM-RNN的滚动轴承故障分类方法。首先,建立滚动轴承故障信号仿真模型,分析滚动轴承故障仿真信号频谱特征及其故障分类特点;其次,结合多标签LSTM-RNN模型结构特点,对滚动轴承频谱特征向量进行编码,并利用仿真故障信号验证多标签LSTM-RNN分类方法的有效性;最后,搭建滚动轴承故障模拟试验台,采集3类转速不同故障类型滚动轴承故障振动信号,并采用3种特征提取方法得到共9组试验数据,基于该数据对多标签LSTM-RNN分类方法和单标签LSTM-RNN分类方法进行对比试验。试验结果表明：多标签LSTM-RNN分类方法相比于单标签LSTM-RNN分类方法,平均分类正确率从69.07%提高到99.21%;在保证两种分类方法正确率相近情况下,多标签LSTM-RNN分类方法训练所需样本量比单标签LSTM-RNN分类方法平均减少69.55%。多标签LSTM-RNN分类方法适用于复杂振动信号分类,对于实现快速准确的旋转机械故障诊断具有应用价值。     

Symmetrical component filter based on line condition monitoring instrumentation system for mine winder motor

As the capital investment in underground coal mining is huge enough by the standards of any conventional industry hence coal production process has to be very efficient to make commercially viable. In a situation of intensive and massive investment, the economics of production would primarily depend on machine utilization indicated by machine availability. Thus machine available time i.e. the time that a machine is available to do productive work, has to be maximized, for best returns on capital invested and utilization of manpower.In this present research work an online condition monitoring instrumentation system has been developed for condition monitoring of mine winder motor. The instrumentation system has been developed based on current monitoring technique. The symmetrical current component present in the unbalanced motor current is sensed with the help of current transformer, current to voltage converter, all pass filters and adders. Any electrical fault in mine winder motor will produce unbalancing in the motor circuit and will cause for the development of symmetrical current component. The type of electrical fault can be determined by sensing the symmetrical current component. One important advantage of this condition monitoring technique is that the instrument can be made hand held and the same hand held instrument may be used for the fault diagnosis of other motors also.A novel condition monitoring instrumentation system based on symmetrical component filter has been developed for on-line condition monitoring of mine winder motor. The instrumentation system would be able to diagnose various incipient faults of mine winder motor and will increase the safety as well as availability of mine winder.The result obtained from symmetrical current component filter based motor diagnostic technique has been verified with the result obtained by axial leakage flux based motor diagnostic technique for similar simulated motor fault condition to pinpoint the exact faulty of condition of the model mine winder motor.     

基于LMD和平滑Teager能量算子解调的电机滚动轴承故障特征提取

作为电机转子的支撑元件,电机轴承故障在电机故障中占有很大比例。针对电机滚动轴承振动信号多分量调幅调频的特点,提出一种基于局域均值分解(LMD)和平滑Teager能量算子的电机轴承故障特征提取方法。该方法首先通过LMD将多分量调制信号分解为若干个单分量调制信号,再运用平滑Teager能量算子对包含主要故障信息的分量进行解调,从而准确地分析出轴承的故障特征。模拟和实例证明了该方法的有效性。     

基于电机电流分析的万能式断路器机械故障诊断

电机电流信号常用于分析电动机本身的故障问题,但对其应用于与电机相连机构的故障分析的研究较少。提出一种基于储能电机电流分析的万能式断路器操作机构故障诊断方法。首先采用Hilbert幅值解调法和改进的小波包阈值法相结合获取交流电流信号的包络线,以解决随机噪声干扰造成的所提取包络线粗糙的问题;然后通过包络线提取电流信号的时间量、电流量以及峭度作为不同故障状态电流波形的特征参数;最后融合模糊聚类和量子粒子群优化的相关向量机实现对断路器正常状态、传动齿轮卡涩、储能弹簧卡涩以及脱落的4种状态的辨识。构建了基于电流分析的万能式断路器故障诊断系统,在不同工况下进行了验证,结果表明该方法能有效提取操作机构储能相关部件的故障特征,实现了对操作机构储能相关部件的故障诊断。     

变频供电异步电动机转子断条故障诊断

异步电机转子断条故障发生时,定子电流（变频器输出侧电流）中会出现对称频率（1±2s）f1（f1为定子电流频率）的故障特征附加电流信号。以此为依据,定子电流特征频谱分析（MCSA）发展为经典转子断条故障在线检测方法。在工程实际过程中,变频供电异步电动机容易采集到的信号是开关柜二次侧供电电流（变频器输入侧电流）．因此要实现变频异步电动机转子断条故障诊断,必须清楚供电电流中是否也含有断条故障特征信息。首次对变频异步电动机供电电流进行分析．得出供电电流中也包括转子断条故障特征信息的结论,以此为基础。利用连续细化傅立叶和自适应滤波相结合的方法,实现了变频异步电动机转子断条故障诊断。     

基于自注意力机制的深度学习模拟电路故障诊断

模拟电路是集成电路中的重要组成部分,基于深度学习技术对模拟电路发生的故障进行检测,并精准识别故障的类型是当前集成电路测试领域的研究热点。针对模拟集成电路故障检测存在困难的问题,利用人工智能在图像识别领域、语音分类领域的先进技术,提出了基于自注意力机制检测Sallen-Key型低通滤波电路故障的深度学习模拟电路故障检测方案,将输出信号采样成音频信号,并将其输入到自注意力变换网络的音频分类模型中进行训练、测试和优化。结果表明,通过自注意力变换网络音频分类在9种不同的故障类型诊断中,平均准确率达93.1%,最高准确率达98.1%。该模型收敛速度更快,具有较强的模拟电路故障检测能力。