Weak Fault Diagnosis of Rolling Bearing Based on Improved Stochastic Resonance

Stochastic resonance can use noise to enhance weak signals,effectively reducing the effect of noise signals on feature extraction.In order to improve the early fault recognition rate of rolling bearings,and to overcome the shortcomings of lack of interaction in the selection of SR(Stochastic Resonance)method parameters and the lack of validation of the extracted features,an adaptive genetic random resonance early fault diagnosis method for rolling bearings was proposed.compared with the existing methods,the AGSR(Adaptive Genetic Stochastic Resonance)method uses genetic algorithms to optimize the system parameters,and further optimizes the parameters while considering the interaction between the parameters.This method can effectively extract the weak fault features of the bearing.In order to verify the effect of feature extraction,the feature signal extracted by AGSR method was input into the Fully connected neural network for fault diagnosis.the practicality of the algorithm is verified by simulation data and rolling bearing experimental data.the results show that the proposed method can effectively detect the early weak features of rolling bearings,and the fault diagnosis effect is better than the existing methods.

Weak thruster fault detection for AUV based on stochastic resonance and wavelet reconstruction

When the bi-stable stochastic resonance method was applied to enhance weak thruster fault for autonomous underwater vehicle(AUV), the enhancement performance could not satisfy the detection requirement of weak thruster fault. As for this problem, a fault feature enhancement method based on mono-stable stochastic resonance was proposed. In the method, in order to improve the enhancement performance of weak thruster fault feature, the conventional bi-stable potential function was changed to mono-stable potential function which was more suitable for aperiodic signals. Furthermore, when particle swarm optimization was adopted to adjust the parameters of mono-stable stochastic resonance system, the global convergent time would be long. An improved particle swarm optimization method was developed by changing the linear inertial weighted function as nonlinear function with cosine function, so as to reduce the global convergent time. In addition, when the conventional wavelet reconstruction method was adopted to detect the weak thruster fault, undetected fault or false alarm may occur. In order to successfully detect the weak thruster fault, a weak thruster detection method was proposed based on the integration of stochastic resonance and wavelet reconstruction. In the method, the optimal reconstruction scale was determined by comparing wavelet entropies corresponding to each decomposition scale. Finally, pool-experiments were performed on AUV with thruster fault. The effectiveness of the proposed mono-stable stochastic resonance method in enhancing fault feature and reducing the global convergent time was demonstrated in comparison with particle swarm optimization based bi-stochastic resonance method. Furthermore, the effectiveness of the proposed fault detection method was illustrated in comparison with the conventional wavelet reconstruction.

Enhanced Detection of Rolling Element Bearing Fault Based on Stochastic Resonance

Early bearing faults can generate a series of weak impacts. All the influence factors in measurement may degrade the vibration signal. Currently, bearing fault enhanced detection method based on stochastic resonance（SR） is implemented by expensive computation and demands high sampling rate, which requires high quality software and hardware for fault diagnosis. In order to extract bearing characteristic frequencies component, SR normalized scale transform procedures are presented and a circuit module is designed based on parameter-tuning bistable SR. In the simulation test, discrete and analog sinusoidal signals under heavy noise are enhanced by SR normalized scale transform and circuit module respectively. Two bearing fault enhanced detection strategies are proposed. One is realized by pure computation with normalized scale transform for sampled vibration signal, and the other is carried out by designed SR hardware with circuit module for analog vibration signal directly. The first strategy is flexible for discrete signal processing, and the second strategy demands much lower sampling frequency and less computational cost. The application results of the two strategies on bearing inner race fault detection of a test rig show that the local signal to noise ratio of the characteristic components obtained by the proposed methods are enhanced by about 50% compared with the band pass envelope analysis for the bearing with weaker fault. In addition, helicopter transmission bearing fault detection validates the effectiveness of the enhanced detection strategy with hardware. The combination of SR normalized scale transform and circuit module can meet the need of different application fields or conditions, thus providing a practical scheme for enhanced detection of bearing fault.

Weak signal detection method based on novel composite multistable stochastic resonance

The weak signal detection method based on stochastic resonance is usually used to extract and identify the weak characteristic signal submerged in strong noise by using the noise energy transfer mechanism.We propose a novel composite multistable stochastic-resonance(NCMSR)model combining the Gaussian potential model and an improved bistable model.Compared with the traditional multistable stochastic resonance method,all the parameters in the novel model have no symmetry,the output signal-to-noise ratio can be optimized and the output amplitude can be improved by adjusting the system parameters.The model retains the advantages of continuity and constraint of the Gaussian potential model and the advantages of the improved bistable model without output saturation,the NCMSR model has a higher utilization of noise.Taking the output signal-to-noise ratio as the index,weak periodic signal is detected based on the NCMSR model in Gaussian noise andαnoise environment respectively,and the detection effect is good.The application of NCMSR to the actual detection of bearing fault signals can realize the fault detection of bearing inner race and outer race.The outstanding advantages of this method in weak signal detection are verified,which provides a theoretical basis for industrial practical applications.

Multi-scale bistable stochastic resonance array: A novel weak signal detection method and application in machine fault diagnosis

Weak signal detection based on stochastic resonance (SR) can hardly succeed when noise intensity exceeds the optimal value of SR. This paper explores a novel parallel bistable SR array mechanism by decomposed multi-scale noises from input signal. A smoother output with lower noise is obtained from the combination of colored noise SR effect and parallel bistable SR array. The influence of noise intensity and array size on the SR effect and output noise intensity is analyzed through numerical simulation. A signal detection method based on the new SR mechanism and normalized scale transform is proposed for the case of heavy background noise. Simulation is conducted to confirm the effectiveness of parameter tuning and amplitude tuning of normalized scale transform on the proposed SR model. The proposed method has three advantages: the input noise intensity of each unit is reduced by wavelet decomposition; the output noise level decreases due to array ensemble average; the SR effect of each unit is optimized by normalized scale transform for high frequency signal. Experiment on bearing inner and outer race fault diagnosis has verified the effectiveness and advantages of the proposed SR model in comparison with traditional SR method and kurtogram.

CVRgram for Demodulation Band Determination in Bearing Fault Diagnosis under Strong Gear Interference

Fault-related resonance frequency band extraction-based demodulation methods are widely used for bearing diagnostics.However,due to the high peaks of strong gear meshing interference,the classical band selection methods have poor performance and cannot work well for bearing fault type detection.As such,the CVRgram-based bearing fault diagnosis method is proposed in this paper.In the proposed method,inspired by the conditional variance(CV)index and root mean square(RMS),a novel index,named the CV/root mean square(CVR),is first proposed.The CVR index has high robustness for the interference of non-Gaussian or Gaussian noise and has the ability to determine the center frequency of the weak bearing fault-related resonance frequency band under strong interference.Secondly,motived by the Kurtogram,the CVRgram algorithm is developed for adaptively determining the optimal filtering parameters.Finally,the CVRgram-based bearing fault diagnosis method under strong gear meshing interference is proposed.The performance of the CVRgram-based method is verified by both the simulation signal and the experiment signal.The comparison analysis with the Kurtogram,Protrugram,and CVgram-based method shows that the proposed technique has a much better ability for bearing fault detection under strong noise interference.

Research on Remote Monitoring and Fault Diagnosis Technology of Numerical Control Machine

Based on the internet technology,it has become possible to complete remote monitoring and fault diagnosis for the numerical control machine.In order to capture the micro-shock signal induced by the incipient fault on the rotating parts,the reso- nance demodulation technology is utilized in the system.As a subsystem of the remote monitoring system,the embedded data acquisi- tion instrument not only integrates the demodulation board but also complete the collection and preprocess of monitoring data from different machines.Furthermore,through connecting to the internet,the data can be transferred to the remote diagnosis center and data reading and writing function can be finished in the database.At the same time,the problem of the IP address floating in the dial-up of web server is solved by the dynamic DNS technology.Finally,the remote diagnosis software developed on the Lab VIEW platform can analyze the monitoring data from manufacturing field.The research results have indicated that the equipment status can be monitored by the system effectively.

Fault diagnosis for gearboxes based on Fourier decomposition method and resonance demodulation

Condition monitoring and fault diagnosis of gearboxes play an important role in the maintenance of mechanical systems.The vibration signal of gearboxes is characterized by complex spectral structure and strong time variability,which brings challenges to fault feature extraction.To address this issue,a new demodulation technique,based on the Fourier decomposition method and resonance demodulation,is proposed to extract fault-related information.First,the Fourier decomposition method decomposes the vibration signal into Fourier intrinsic band functions(FIBFs)adaptively in the frequency domain.Then,the original signal is segmented into short-time vectors to construct double-row matrices and the maximum singular value ratio method is employed to estimate the resonance frequency.Then,the resonance frequency is used as a criterion to guide the selection of the most relevant FIBF for demodulation analysis.Finally,for the optimal FIBF,envelope demodulation is conducted to identify the fault characteristic frequency.The main contributions are that the proposed method describes how to obtain the resonance frequency effectively and how to select the optimal FIBF after decomposition in order to extract the fault characteristic frequency.Both numerical and experimental studies are conducted to investigate the performance of the proposed method.It is demonstrated that the proposed method can effectively demodulate the fault information from the original signal.

A local spectrum enhancement-based method and its application in incipient fault diagnosis of rotating machinery

Incipient faults of gears and rolling bearings in rotating machineries are very difficult to identify using traditional envelope analysis methods.To address this challenge,this paper proposes an effective local spectrum enhancement‐based diagnostic method that can identify weak fault frequencies in the original complicated raw signals.For this purpose,a traversal frequency band segmentation technique is first proposed for dividing the raw signal into a series of subfrequency bands.Then,the proposed synthetic quantitative index is constructed for selecting the most informative local frequency band(ILFB)containing fault features from the divided subfrequency bands.Furthermore,an improved grasshopper optimization algorithmbased stochastic resonance(SR)system is developed for enhancing weak fault features contained in the selected most ILFB with less computation cost.Finally,the enhanced weak fault frequencies are extracted from the output of the SR system using a common spectrum analysis.Two experiments on a laboratory planetary gearbox and an open bearing data set are used to verify the effectuality of the proposed method.The diagnostic results demonstrate that the proposed method can identify incipient faults of gears and bearings in an effective and accurate manner.Furthermore,the advantages of the proposed method are highlighted by comparison with other methods.

Effect of scale-varying fractional-order stochastic resonance by simulation and its application in bearing diagnosis

Bearing is among the most widely used components in rotating machinery.Its failure can cause serious economic losses or even disasters.However,the fault-induced impulses are weak especially for the early failure.As to the bearing fault diagnosis,a novel bearing diagnosis method based on scale-varying fractional-order stochastic resonance(SFrSR)is proposed.Signal-to-noise ratio of the SFrSR output is regarded as the criterion for evaluating the stochastic resonance(SR)output.In the proposed method,by selecting the proper parameters(integration step H,amplitude gain K and fractional-orderα)of SFrSR,the weak fault-induced impulses,the noise and the potential can be matched with each other.An optimal fractional-order dynamic system can be generated.To verify the proposed SFrSR,numerical tests and application verification are conducted in comparison with the traditional scale-varying first-order SR(SFiSR).The results prove that the parameters H,K andαaffect the SFrSR effect seriously and the proposed SFrSR can enhance the weak signal while suppressing the noise.The SFrSR is more effective for bearing fault diagnosis than SFiSR.

Fault diagnosis of wind turbine bearing based on stochastic subspace identification and multi-kernel support vector machine

In order to accurately identify a bearing fault on a wind turbine, a novel fault diagnosis method based on stochastic subspace identification(SSI) and multi-kernel support vector machine(MSVM) is proposed. Firstly, the collected vibration signal of the wind turbine bearing is processed by the SSI method to extract fault feature vectors. Then, the MSVM is constructed based on Gauss kernel support vector machine(SVM) and polynomial kernel SVM. Finally, fault feature vectors which indicate the condition of the wind turbine bearing are inputted to the MSVM for fault pattern recognition. The results indicate that the SSI-MSVM method is effective in fault diagnosis for a wind turbine bearing and can successfully identify fault types of bearing and achieve higher diagnostic accuracy than that of K-means clustering, fuzzy means clustering and traditional SVM.

Fault Diagnosis for Singular Stochastic Systems

This paper studies the fault diagnosis of singular stochastic systems.The probability distribution of output is measured by probability density functions(PDFs),which are modeled by a square root B-spline expansion.An adaptive nonlinear observer is proposed to estimate the size of the fault occurring in systems. Furthermore,the linear matrix inequality(LMI) approach is applied to establish sufficient conditions for the existence of the observer.Finally,the simulation results are given to indicate the method for diagnosing the fault.

Bearing Incipient Fault Detection Method Based on Stochastic Resonance with Triple-Well Potential System

Bearing incipient fault characteristics are always submerged in strong background noise with weak fault characteristics, so that the incipient fault is hard to detect. Stochastic resonance (SR) is accepted to be an effective way to detect the incipient;however, output saturation may occur if bistable SR is adopted. In this paper, a bearing incipient fault detection method is proposed based on triple-well potential system and SR mechanism. The achievement of SR highly replays on the nonlinear system which is adopted a triple-well potential function in this paper. Therefore, the parameters in the nonlinear system are optimized by particle swarm optimization algorithm, and the objective of optimization is to maximize the signal-to-noise ratio of the fault signal. After optimization, the optimal system parameters are obtained thereby the resonance effect is generated and the bearing incipient fault characteristic is enhanced. The proposed method is validated by simulation verification and engineering application. The results show that the method is effective to detect an incipient signal from heavy background noise and can obtain better outputs compared with bistable SR.

Detecting and diagnosing faults in dynamic stochastic distributions using a rational B-splines approximation to output PDFs

This paper presents a novel approach to detect and diagnose faults in the dynamic part of a class of stochastic systems . the Such a group of systems are subjected to a set of crisp inputs but the outputs considered are the measurable probability density functions (PDFs) of the system output, rather than the system output alone. A new approximation model is developed for the output probability density functions so that the dynamic part of the system is decoupled from the output probability density functions. A nonlinear adaptive observer is constructed to detect and diagnose the fault in the dynamic part of the system. Conver-gency analysis is performed for the error dynamics raised from the fault detection and diagnosis phase and an applicability study on the detection and diagnosis of the unexpected changes in the 2D grammage distributions in a paper forming process is included.

基于改进多稳态系统随机共振的轴承微弱故障诊断

针对传统随机共振方法在强噪声背景下对轴承微弱故障诊断中存在严重的边频干扰问题,提出了一种应用改进多稳态随机共振模型进行轴承微弱故障诊断的方法.在高斯白噪声和周期性激励作用下,推导得到了改进多稳态系统的平均首次穿越时间和功率谱放大因子的解析表达式.研究发现,存在一组最优的参数使得改进多稳态系统的随机共振效应最大化.将改进的多稳态随机共振模型应用于轴承内外圈的微弱故障诊断,并利用量子粒子群优化算法对系统参数和阻尼系数进行优化.研究结果表明,所提方法能够在强噪声背景下有效识别出微弱故障特征频率,且与传统多稳态随机共振方法相比,该方法解决了严重的边频干扰问题,输出信号特征频率处的频谱峰值更高,大大提高了轴承微弱故障诊断的性能.

拖拉机底盘振动故障诊断与优化——基于模态识别模型

拖拉机是农业生产中非常重要的工具之一,被广泛用于耕种、播种、收割、运输和其他农业活动中。但是,由于农业生产环境恶劣、工况复杂多变,农业拖拉机底盘结构在运行过程中会发生各类故障,进而影响拖拉机工作可靠性,降低农业生产效率。为了精确地识别拖拉机底盘系统早期故障,融合了改进后的平均相关子空间方法,提出了一种以系统响应信号为特征输入的模态识别算法,并采用多次平均后的相关函数信号作为模型输入,通过测定拖拉机底盘不同位置振动信号验证算法的可行性。

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。

基于随机子空间法的滑动轴承运行模态参数识别

滑动轴承的运行模态参数是其状态监测和早期故障诊断的重要指标,利用随机子空间法识别滑动轴承运行模态参数时,环境噪声和阶数过估计引起的虚假模态会影响真实模态参数的识别。为减少虚假模态的干扰,首先对振动信号利用互补集合经验模态分解和小波变换相结合的方法进行降噪处理,然后将预处理后的信号分段并分别进行模态参数识别,通过对比同阶极点获得更清晰的稳定图,最后采用谱聚类算法实现模态参数的自动选择。通过数值仿真和相关试验验证该方法的有效性。

基于多目标异权重回归的冷水机组故障诊断显式模型

针对冷水机组中常见的7种故障,本文基于交叉熵损失函数和随机梯度下降算法建立了多目标异权重回归模型,进行故障诊断。该模型较常规的机器学习分类模型简单,无需迭代,计算速度快,且为显式模型(非黑箱),可直观分析各参数对每类故障的重要程度。与传统的单目标回归模型相比,故障诊断性能优势显著,在不同特征集合下,性能最低提升40.50%。对比不同文献中特征集合在本模型中的效果,并提出了新的特征集合,正常运行及7类故障的总体诊断准确率可达89.83%,局部故障的诊断准确率达到98%以上。通过可视化诊断模型中的参数权重,发现过冷度和供油温度参数对诊断制冷剂泄漏、制冷剂过充和润滑油过量3种系统性故障最为重要;供油压力、冷凝器趋近温度、蒸发器与冷凝器的水流量参数对诊断4种局部故障最为重要。

一种选取最优解调频带新方法——Multigram

针对Fast-Kurtogram易受非高斯噪声干扰的不足,提出一种基于多层滑动滤波器组,找寻最优解调频带的新方法——Multigram。首先,借鉴Protrugram滑动分割频带思想,构建多层、多滤波中心和带宽的滤波组。然后,根据各层不同滤波中心和带宽依次进行带通滤波,对滤波信号进行包络自相关谱分析,在容差范围内计算谱峭度,以选取最优解调频带。最后,采用最优滤波中心和带宽进行带通滤波和包络谱分析。将方法应用于滚动轴承故障诊断,基于机匣测点的模拟故障轴承试验和自然故障轴承试验结果表明:该方法可有效选取适宜的解调频带,相比于Fast-Kurtogram,Protrugram,Autogram和Infogram,诊断结果更具优势。