Vibration-based fault diagnosis of spur bevel gear box using fuzzy technique

To determine the condition of an inaccessible gear in an operating machine the vibration signal of the machine can be continuously monitored by placing a sensor close to the source of the vibrations. These signals can be further processed to extract the features and identify the status of the machine. The vibration signal acquired from the operating machine has been used to effectively diagnose the condition of inaccessible moving components inside the machine. Suitable sensors are kept at various locations to pick up the signals produced by machinery and these signals are very meaningful in condition diagnosis surveillance. To determine the important characteristics and to unravel the significance of these signals, further analysis or processing is required.This paper presents the use of decision tree for selecting best statistical features that will discriminate the fault conditions of the gear box from the signals extracted. These features are extracted from vibration signals. A rule set is formed from the extracted features and fed to a fuzzy classifier. The rule set necessary for building the fuzzy classifier is obtained largely by intuition and domain knowledge. This paper also presents the usage of decision tree to generate the rules automatically from the feature set. The vibration signal from a piezo-electric transducer is captured for the following conditions – good bevel gear, bevel gear with tooth breakage (GTB), bevel gear with crack at root of the tooth (GTC), and bevel gear with face wear of the teeth (TFW) for various loading and lubrication conditions. The statistical features were extracted and good features that discriminate the different fault conditions of the gearbox were selected using decision tree. The rule set for fuzzy classifier is obtained by once using the decision tree again. A fuzzy classifier is built and tested with representative data. The results are found to be encouraging.     

Applying the fuzzy lattice neurocomputing (FLN) classifier model to gear fault diagnosis

Gear faults are among the main causes of rotating machines breakdown in industrial applications. Intelligent condition monitoring for fault diagnosis can be helpful for detecting gear faults in an early stage so as to reduce production loss and, in addition, improve operation safety and reliability. In this work, we present an intelligent gear fault diagnosis scheme based on a novel classification model, namely the fuzzy lattice neurocomputing (FLN) classifier model. Five gear states including one healthy state and four defective states are tested in a two-stage gearbox. Statistical parameters in both the time domain and the frequency domain of vibration signals, acquired from gearbox, are used as features. We conducted experiments on a benchmark dataset as well as on a gear faults dataset to evaluate both the classification performance and the computational cost of the FLN classifier comparatively with alternative classification methods from the literature including artificial neural networks, support vector machines and decision trees. Our study has demonstrated that the FLN model yields better classification performance with smaller computational cost than the aforementioned alternative methods. The FLN classifier can further be used for condition monitoring and fault diagnosis in other mechanical systems.     

Application of an intelligent classification method to mechanical fault diagnosis

A new method for intelligent fault diagnosis of rotating machinery based on wavelet packet transform (WPT), empirical mode decomposition (EMD), dimensionless parameters, a distance evaluation technique and radial basis function (RBF) network is proposed in this paper. In this method, WPT and EMD are, respectively, used to preprocess vibration signals to mine fault characteristic information more accurately. Then, dimensionless parameters in time domain are extracted from each of the original vibration signals and preprocessed signals to form a combined feature set. Moreover, the distance evaluation technique is utilised to calculate evaluation factors of the combined feature set. Finally, according to the evaluation factors, the corresponding sensitive features are selected and input into the RBF network to automatically identify different machine operation conditions. An experiment of rolling element bearings is carried out to test the performance of the proposed method. The experimental result demonstrates that the method combining WPT, EMD, the distance evaluation technique and the RBF network may accurately extract fault information and select sensitive features, and therefore it may correctly diagnose the different fault categories occurring in the bearings. Furthermore, this method is applied to slight rub fault diagnosis of a heavy oil catalytic cracking unit, the actual result shows the method may be applied to fault diagnosis of rotating machinery effectively.     

基于啮合频率调制现象的齿轮振动信号辨识

齿轮是大多数旋转机械设备的核心零部件,也是主要的振动来源.为了评估齿轮箱的健康状态,从机械系统信号中提取齿轮箱的振动成分具有重要意义.齿轮的啮合频率包含了反映其运行状态的丰富信息,是进行齿轮在线监测和故障诊断的前提条件.通过理论分析和试验验证,解释了啮合频率调制现象,也就是当齿轮在重载条件下工作时,啮合频率会以啮合冲击的形式被调制到高频共振区.基于此现象,提出了一种齿轮振动信号辨识方法.在此方法中,通过迭代获得啮合能量比图,以确定啮合共振频带.此方法的性能通过试验台试验和叉车现场试验进行了验证.通过与快速谱峭度方法进行对比,证明所提出的方法适用于齿轮振动信号辨识,尤其是当齿轮处于重载条件时.     

短丝纤维卷绕牵伸齿轮箱故障信号的图像特征提取方法

针对短丝纤维卷绕牵伸齿轮箱故障信号不易提取的问题,提出了基于图像纹理信息的特征提取方法。通过对齿轮箱振动信号进行小波包双谱分析,获得具有稳定纹理信息的振动信号双谱图,采用基于小波变换对双谱图进行图像融合,提高图像的综合纹理特征。采用灰度共生矩阵的四个特征参数对振动信号的双谱图进行加权融合特征提取。在短丝生产线上对齿轮箱常见的齿轮破损和裂纹进行了实验分析,结果表明本文方法的故障识别率达到85%以上。     

基于双树复小波变换—最大熵谱估计和参数优化概率神经网络的齿轮箱故障诊断研究

齿轮振动信号具有非平稳性和非线性的特点。为了准确提取其故障特征并进行故障诊断,提出一种基于双树复小波变换(DTCWT)-最大熵谱估计(MESE)和惯性权重线性递减粒子群优化(LDWPSO)算法-参数优化概率神经网络(PNN)的齿轮故障诊断方法。首先,利用DTCWT把状态已知的齿轮振动信号分解为不同频带的模态分量。其次,采用MESE得到每个分量的最小偏差频谱估计,计算出不同频段的能量熵作为故障特征矩阵。然后利用LDWPSO算法寻找出最优神经网络参数——平滑因子。最后,将故障特征矩阵输入优化后的PNN模型,建立起故障特征和齿轮运行状况之间的数值化映射关系,进而完成齿轮故障诊断模型。经试验数据分析表明,采用提出的DTCWT处理齿轮的振动信号,并引入MESE处理关键分量,可以提取稳定的信号特征并降低噪声干扰。另外,相比于传统的PNN,基于改进的PNN的齿轮故障状态的数值化判别具有更高的诊断精度和稳定性。     

Intelligent diagnosis method for a centrifugal pump using features of vibration signals

In the field of machinery diagnosis, the utilization of vibration signals is effective in the detection of fault, because the signals carry dynamic information about the machine state. However, knowledge of a distinguishing fault is ambiguous because definite relationships between symptoms and fault types cannot be easily identified. This paper presents an intelligent diagnosis method for a centrifugal pump system using features of vibration signals at an early stage. The diagnosis algorithm is derived using wavelet transform, rough sets and a partially linearized neural network (PNN). ReverseBior wavelet function is used to extract fault features from measured vibration signals and to capture hidden fault information across optimum frequency regions. As the input parameters for the neural network, the non-dimensional symptom parameters that can reflect the characteristics of a signal are defined in the amplitude domain. The diagnosis knowledge for the training of the PNN can be acquired by using the rough sets. We also propose a diagnosis method based on the PNN, one which can deal with the ambiguity problem of condition diagnosis, and distinguish fault types on the basis of the possibility distributions of symptom parameters automatically. The decision method of optimum frequency region for extracting feature signals is also discussed using real plant data. Practical examples of diagnosis for a centrifugal pump system are shown in order to verify the efficiency of the method.     

基于信息融合与CNN的齿轮箱故障诊断方法

齿轮箱在实际生产中面临复杂多变的工况,其部件的故障特征随工况发生改变,常规方法在变工况下难以有效识别故障。针对该问题,提出一种基于信息融合和卷积神经网络(IFCNN)的故障诊断方法。IFCNN使用多传感器信息融合和多域特征融合改进卷积神经网络(CNN),首先将不同位置的加速度传感器采集到的振动信号转换成频域、时频域信息,将来自不同传感器的信息融合,然后用CNN对故障信号的频域、时频域信息分别进行特征提取和多域特征融合,结合注意力机制选择重要特征进行故障分类。多组实验结果表明,IFCNN在变工况场景下,可有效提取齿轮箱振动信号的故障特征,12组变工况实验平均识别准确率为98.38%,明显高于所提出的对比方法。     

基于广义多重分形维数算法的汽车变速箱故障诊断研究

提出了一种基于扩展广义多重分形维数算法的汽车变速箱故障诊断方法。该算法是基于传统的G-P关联维数算法扩展而形成的,通过该算法对变速箱上采集的不同工作状态下的振动信号进行处理,提取变速箱齿轮的振动信号的分数维,观察及分析分形维数与变速箱齿轮的磨损规律的关系,发现其反映变速箱齿轮的真实运行状态,故可以此作为齿轮磨损预测和诊断的有效依据。     

基于改进阈值和小波包的轴承故障诊断方法

为了准确有效地确定滚动轴承的故障部位,提出一种轴承故障诊断的新方法。用改进的小波阈值法对轴承振动信号进行降噪处理,对去噪后的信号进行小波包分解与重构,提取各重构子带内的信号特征作为故障诊断的样本,依据各子带信号的能量分布特征判断轴承的故障部位。在MATLAB环境下对SKF6205-2RS轴承的典型故障进行了仿真研究,结果表明改进的阈值法相比于传统去噪方法有较好的去噪效果,小波包能够准确提取信号的故障特征,能够提高轴承故障检测的准确性和有效性。     

A novel fault diagnosis technique for wind turbine gearbox

The gearbox is one of the most important parts of a mechanical equipment. The importance of fault diagnosis in rotating machineries for preventing catastrophic accidents and ensuring adequate maintenance has received considerable attention. In this study, a fault diagnosis method based on gearbox vibration signal monitoring is used to differentiate the signal characteristics of different working conditions and improve the accuracy of diagnosis. The time-domain sequence approximate entropy (ApEn) adaptive strategy is used to propose a wind turbine intelligent fault diagnosis algorithm based on a wavelet packet transform (WPT) filter and a cross-validated particle swarm optimized (CPSO) kernel extreme learning machine (KELM). First, the correlation between the parameter requirements of the intelligent diagnosis system and the system complexity analysis is analyzed. Then, the parameters related to the wavelet filter is determined by calculating the ApEn of the time-domain sequence. Finally, a compact wind turbine gearbox test bench is constructed and tested to validate the proposed ApEn-WPT+CPSO-KELM to identify gearbox-related faults for verification. Results show that the proposed ApEn-WPT+CPSO-KELM method can accurately identify four states of the wind turbine gearbox.     

A rotating machinery fault diagnosis method based on local mean decomposition

Local mean decomposition (LMD) is a novel self-adaptive time–frequency analysis method, which is particularly suitable for the processing of multi-component amplitude-modulated and frequency-modulated (AM–FM) signals. By using LMD, any complicated signal can be decomposed into a number of product functions (PFs), each of which is the product of an envelope signal and a purely frequency modulated signal from which physically meaningful instantaneous frequencies can be obtained. In fact, each PF is just a mono-component AM–FM signal. Therefore, the procedure of LMD may be regarded as the process of demodulation. While fault occurs in gear or roller bearing, the vibration signals picked up would exactly display AM–FM characteristics. So it is possible to diagnose gear and roller bearing fault by LMD. Targeting the modulation features of the gear or roller bearing fault vibration signal, a rotating machinery fault diagnosis method based on LMD is proposed. In this paper, firstly the LMD method is introduced; secondly, the LMD method is compared with another competing time–frequency analysis approach, namely, empirical mode decomposition (EMD) method and the results show the superiority of the LMD method; finally, the LMD method is applied to the gear and roller bearing fault diagnosis. The analysis results from the practical gearbox vibration signal demonstrate that the diagnosis approach based on LMD could identify gear and roller bearing work condition accurately and effectively.     

基于RBF神经网络和小波包的电动机故障诊断研究

针对传统的电动机故障诊断存在很难准确提取故障时的特征信号及对故障作出准确预测的问题,提出了一种基于RBF神经网络和小波包的电动机故障诊断的方法。该方法采用小波包分析技术提取电动机典型轴承故障、转子故障和绝缘故障振动信号的特征频段能量并组成向量作为RBF神经网络的输入,用于诊断电动机的故障。实验和仿真结果表明,使用RBF神经网络对电动机故障诊断是非常有效的,对电动机早期故障的发现及维修有积极意义。     

Fault feature extraction of rolling element bearings based on wavelet packet transform and sparse representation theory

Extracting reliable features from vibration signals is a key problem in machinery fault recognition. This study proposes a novel sparse wavelet reconstruction residual (SWRR) feature for rolling element bearing diagnosis based on wavelet packet transform (WPT) and sparse representation theory. WPT has obtained huge success in machine fault diagnosis, which demonstrates its potential for extracting discriminative features. Sparse representation is an increasingly popular algorithm in signal processing and can find concise, high-level representations of signals that well matches the structure of analyzed data by using a learned dictionary. If sparse coding is conducted with a discriminative dictionary for different type signals, the pattern laying in each class will drive the generation of a unique residual. Inspired by this, sparse representation is introduced to help the feature extraction from WPT-based results in a novel manner: (1) learn a dictionary for each fault-related WPT subband; (2) solve the coefficients of each subband for different classes using the learned dictionaries and (3) calculate the reconstruction residual to form the SWRR feature. The effectiveness and advantages of the SWRR feature are confirmed by the practical fault pattern recognition of two bearing cases.     

基于内禀模态奇异值分解和支持向量机的故障诊断方法

提出了一种基于内禀模态(Intrinsic mode functions,简称IMFs)奇异值分解和支持向量机(Support vector machine,简称SVM)的故障诊断方法.采用经验模态分解(Empirical mode decomposition,简称EMD)方法对旋转机械故障振动信号进行分解,将得到的若干个内禀模态分量自动形成初始特征向量矩阵,然后对该矩阵进行奇异值分解,提取其奇异值作为故障特征向量,并进一步根据支持向量机分类器的输出结果来判断旋转机械的工作状态和故障类型.对齿轮振动信号的分析结果表明,即使在小样本情况下,基于内禀模态奇异值分解和支持向量机的故障诊断方法仍能有效地识别齿轮的工作状态和故障类型.     

Hilbert-小波变换的齿轮箱故障诊断*

采用希尔伯特—小波变换对振动加速度传感器获取的齿轮箱振动响应信号进行特性分析。利用小波变换分解获得振动响应信号的各层高频信号小波系数和低频信号小波系数,对小波系数进行重构获得具有不同特征时间尺度的各高频信号和低频信号;再对分解的信号进行希尔伯特变换获得时频信息谱以提取系统的统计特征信息,实现监测齿轮运转工作状态,及时发现齿轮的早期故障,提高机械运行的安全性。仿真研究结果表明,小波变换分解和希尔伯特边际谱方法在故障信息诊断方面是可行和有效的,提高了故障检测的可靠性。     

A Hybrid Genetic Algorithm and Back-Propagation Classifier for Gearbox Fault Diagnosis

An Artificial Neural Network (ANN) classifier trained by a hybrid GA-BP method for diagnosis of gear faults is presented here that can be incorporated in an online fault diagnostic system of vital gearboxes. The distinctive features obtained from vibration signals of a running gearbox; that was operated in normal and with faults induced conditions were used to feed the GA-BP hybrid classifier. Time domain vibration signals were divided in 40segments. From each segment features such as magnitude of peaks in time domain and spectrum along with statistical features such as central moments and standard deviations were extracted to feed the classifier. Based on the experimental results it was shown that the GA-BP hybrid classifier can successfully identify gear condition. It was also shown that the network trained by GA-BP hybrid method performs much better than ANN that is trained by standard BP or GA individually. Further, it was also shown that if prior to extraction of features; the vibration signals are pre-processed by Discrete Wavelet Transform (DWT) then efficacy of the GA-BP hybrid is significantly enhanced.     

基于径向基神经网络的新型齿轮故障诊断方法

非平稳工况下的齿轮故障检测是一项非常困难的工作,由于齿轮振动信号的复杂性,导致故障特征提取和故障诊断困难.针对这些问题,基于径向基(radial basis function, RBF)神经网络,提出一种在变速条件下齿轮的故障诊断方法 CIHDRFD.首先利用自适应白噪声的完整集成经验模态分解(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN),将原始振动信号分解为多个固有的模态函数(intrinsic mode function, IMF),并通过计算其信息熵(information entropy, IE)筛选出IE最小的4个IMF作为特征IMF;然后利用希尔伯特变换(hilbert transform, HT)处理特征IMF并求出Hilbert包络谱,利用Hilbert包络谱构建故障特征向量;最后利用改进的双RBF神经网络进行故障检测.通过搭建齿轮故障检测平台验证CIHDRFD方法的有效性,实验结果表明, CIHDRFD方法适用于齿轮故障诊断,在速度波动为3%的情况下,诊断准确率...     

基于小波包分析的滚动轴承故障特征提取

简述了小波包分析的基本原理及其用于特征提取的机理,利用小波包对滚动轴承振动加速度信号进行分解,求出各频率段的能量,并以此作为滚动轴承所发生故障的特征向量进行提取,从而识别出滚动轴承的故障,通过对于实测信号的分析证明了该方法的有效性,体现了小波包分析的优良性。     

轴承早期故障特征提取方法研究

针对滚动轴承早期故障信号被背景噪声淹没、故障特征不明显的问题,提出一种基于小波包分解和互补集合经验模态分解(CEEMD)的轴承早期故障信号特征提取方法.利用Matlab软件对采集到的轴承振动信号进行快速谱峭度分析,根据峭度最大化原则确定带通滤波器的中心频率和带宽,设计带通滤波器;对经过带通滤波器滤波后的信号进行小波包分解和CEEMD分解,根据峭度、相关系数筛选出有效本征模态函数(IMF)分量;利用IMF分量重构小波包信号,对重构小波包信号进行包络谱分析,提取轴承早期故障信号特征频率.该方法通过谱峭度分析降低背景噪声干扰,通过小波包分解增强故障冲击信号,并将CEEMD与小波包分解相结合,解决经典EMD分解存在的模态混叠、无效分量问题.仿真结果表明,相较于传统包络解调算法,重构后信号的背景噪声得到抑制,故障特征分量突出,验证了所提方法的可行性和有效性.