刀具磨损早期故障智能诊断研究

针对刀具的早期故障监测中因存在强烈的背景噪声而难以提取故障特征的问题,提出了基于二次采样随机共振消噪和B样条神经网络智能识别的故障诊断方法。首先利用在随机共振过程中,噪声增强振动信号的信噪比特性,将刀具振动信号进行随机共振输出,提取有效特征,再输入到B样条神经网络进行智能识别,进而获得刀具的磨损值。同时,为了得到与输入信号最佳匹配的随机共振参数,提出了基于遗传算法的多参数同步优化的自适应随机共振算法,克服了传统随机共振系统只实现单参数优化的缺点。实验结果表明,该方法能实现弱信号检测,能有效地应用于刀具磨损故障诊断中。     

Weak feature enhancement in machinery fault diagnosis using empirical wavelet transform and an improved adaptive bistable stochastic resonance

Machinery vibration signal is a typical multi-component signal and fault features are often submerged by some interference components. To accurately extract fault features, a weak feature enhancement method based on empirical wavelet transform (EWT) and an improved adaptive bistable stochastic resonance (IABSR) is proposed. This method makes full use of the signal decomposition performance of EWT and the signal enhancement of the IABSR to achieve the purpose of fault feature enhancement in low frequency band of FFT spectrum. Firstly, EWT is used as the preprocessing program of bistable stochastic resonance (BSR) to decompose the machinery vibration signal into a set of sub-components. Then, the sensitive component that contains main fault information is further input into BSR system to enhance fault features with the assistance of residual noises. Finally, the fault features are identified from fast Fourier transform (FFT) spectrum of the BSR output. To achieve the optimal BSR output, the IABSR method based on salp swarm algorithm (SSA) is presented. Compared with the tradition adaptive BSR (ABSR), the IABSR optimizes not only the BSR system parameters but also the calculation step size. Two case studies on machinery fault diagnosis demonstrate the effectiveness and superiority of the proposed method. In addition, the proposed method is easy to implement and is robust to noise to some extent.     

基于 VMD 的数控机床旋转机械运行路径偏离故障检测方法

为精准提取数控机床旋转机械设备故障信息,量化数控机床旋转机械运行路径偏离程度,提出一种基于 VMD 的旋转机械运行路径偏离故障检测方法。分析数控机床旋转机械设备运行频率和振动情况,运用突变检测算法优化采集效率,使用自适应脉冲法采样机械信号;创建约束变分模型,利用遗传算法搜索信号变量最优值,通过 VMD 法分离信号频域分量,提取机械信号故障特征;通过聚类法评估路径偏离水平,构建胶囊网络进行路径偏离故障检测,利用 squash 函数挤压处理胶囊矢量并提升矢量维度,运用特征编码和归一化处理获得高精度偏离故障检测输出值。实验结果表明,所提方法检测的数控机床旋转机械运行路径偏离故障效果较好,且检测效率较高。     

A new adaptive cascaded stochastic resonance method for impact features extraction in gear fault diagnosis

Gearboxes are widely used in engineering machinery, but tough operation environments often make them subject to failure. And the emergence of periodic impact components is generally associated with gear failure in vibration analysis. However, effective extraction of weak impact features submerged in strong noise has remained a major challenge. Therefore, the paper presents a new adaptive cascaded stochastic resonance (SR) method for impact features extraction in gear fault diagnosis. Through the multi-filtered procession of cascaded SR, the weak impact features can be further enhanced to be more evident in the time domain. By analyzing the characteristics of non-dimensional index for impact signal detection, new measurement indexes are constructed, and can further promote the extraction capability of SR for impact features by combining the data segmentation algorithm via sliding window. Simulation and application have confirmed the effectiveness and superiority of the proposed method in gear fault diagnosis.     

优化VMD与CNN在齿轮箱故障诊断应用研究

针对齿轮箱的故障诊断的优化问题,提出了一种基于参数优化的变分模态分解（VMD）与卷积神经网络（CNN）相融合的故障诊断方法。该算法首先通过鲸鱼优化算法对VMD算法进行优化,之后通过正交实验法与粒子群优化算法进行了CNN模型中的重要参数进行优化,最后将分解后得到的固有模态分量输入CNN模型中进行训练学习。诊断完成后得到训练与检测结果,其中经过算法优化后CNN模型的训练与检测准确率可达98.7%与95.7%,优于未优化的准确率94.3%与91.8%。通过对结果的分析验证出该算法的可行性以及在诊断成功率方面的优越性,实现了故障特征信息的自适应性提取,并将故障类型进行分类,最终实现齿轮箱故障诊断的智能化。     

变风速条件下风力机轴承故障特征提取

针对风速变化条件下风力发电机轴承故障特征的检测问题,提出了一种基于灰狼优化( GWO )和双稳态杜芬振荡器的随机共振( SR )的故障特征提取方法.首先,根据风速估计故障特征信号的频率,通过合适的采样频率采集风力发电机的振动信号并对采集的信号做归一化处理.随后,根据风速尺度引入变换系数对频率 时间尺度进行变换.此外,利用灰狼算法方法将杜芬振子的阻尼比和系统参数调整到最优值.最后,通过杜芬系统和尺度恢复获得可识别信号.结果表明,所提出的方法能提取原始信号中的故障特征信号.     

基于多稳态随机共振的轴承微弱故障信号检测

针对双稳态随机共振模型无法有效处理调制信号的缺点,提出了一种以包络信号为输入信号的自适应多稳态级联随机共振(adaptive multi-stable cascaded stochastic resonance,简称AMCSR)信号强化方法。首先,对振动信号进行包络解调,依据包络信号分布特点,选用与信号分布相匹配的多稳态随机共振模型;然后,以故障特征频率的频谱幅值为指标,采用蚁群算法自适应地优化随机共振模型参数;最后,以噪声为强化源和驱动信号,通过级联随机共振方法对包络信号中的故障特征频率进行逐级强化,获得故障特征成分的强化信号。对实测轴承振动信号的验证结果表明,该方法能够增强故障特征频率成分,有效地提取被其他频率成分淹没的微弱故障信号。     

QPSO匹配的FIE随机共振轴承故障诊断

针对随机共振(stochastic resonance,简称SR)系统处理复杂信号的局限性以及参数选择的盲目性,提出了一种基于频域信息交换(frequency information exchange,简称FIE)的量子粒子群自适应参数匹配随机共振方法。首先,采用FIE将高频特征信号的频域幅值信息交换到对应的基准低频处;然后,根据基准频率特征采用量子粒子群优化(quantum particle swarm optimization,简称QPSO)算法优化SR系统参数;最后,对振动信号进行随机共振处理。滚动轴承实测信号的分析表明,该方法可以消除随机共振对频段的局限性,避免系统参数选择的盲目性,使随机共振更适用于强噪声背景下较高频段的故障信号检测。     

基于PSO优化的RBF网络液压泵故障诊断研究

提出了以小包分解和粒子群优化的径向基神经网络(RBFNN)为基础的液压泵故障诊断方法。通过小波包分解对振动信号做降噪处理并提取相应的故障信号的特征能量值,将此特征能量值作为神经网络的输入,再采用粒子群算法对神经网络的数据中心和宽度、输出权值和阈值进行优化,并将其分别与基于传统神经网络和基于遗传算法优化的故障诊断方法进行对比分析。对比结果表明,该方法具有很好的诊断效果。     

基于加权排列熵和DE-ELM的滚动轴承故障诊断

针对滚动轴承振动信号非平稳非线性的特征,提出一种基于加权排列熵和差分进化算法优化极限学习机(DE-ELM)的滚动轴承故障诊断方法。首先利用自适应噪声的完全集合经验模态分解处理轴承振动信号得到固有模态函数(IMF),然后计算主要IMF分量的加权排列熵组成故障特征向量,最后利用差分优化算法(DE)优化极限学习机隐含层输入权值和偏置,并将故障特征向量作为DE-ELM的输入。实验证明,加权排列熵能够精确提取故障特征,DE-ELM算法能有效提高故障分类精度。与多种方法相比,该方法更加准确可靠。     

基于自适应随机共振和稀疏编码收缩算法的齿轮故障诊断方法

针对强背景噪声下齿轮故障冲击特征提取问题,提出了一种基于自适应随机共振和稀疏编码收缩算法的齿轮故障诊断方法。该方法选用相关峭度作为随机共振检测周期性冲击分量的测度函数,借助遗传算法实现信号中周期性冲击特征的自适应提取;在此基础上,利用稀疏编码收缩算法对随机共振检测结果做进一步降噪处理,从而凸显冲击特征,提高故障识别精度。试验和工程实例分析结果表明,该方法可实现齿轮故障冲击特征的增强提取,为齿轮故障诊断提供依据。     

基于优化自适应阈值的非线性机电系统传感器 故障检测和主动容错控制

针对具有参数不确定性和传感器故障的非线性机电系统,提出一种基于优化自适应阈值和故障重构策略的主动容错控制方法。首先,利用线性分式变换理论对存在参数不确定性的非线性机电系统进行建模,并提出基于粒子群优化算法的优化自适应阈值以提高参数不确定条件下的故障检测性能。其次,通过解析冗余关系推导出系统的动力学方程,并提出一种基于递归终端滑模的跟踪控制策略,以实现系统健康状态下的负载位置跟踪。当系统发生故障时,构建自适应滑模观测器进行传感器故障重构,根据重构结果设计自适应主动容错控制律,并利用故障检测结果进行控制律的实时切换。实验结果表明,所提出的故障检测和主动容错控制方法能在0.06 s内准确的实现传感器故障检测和容错控制,验证了该方法的可行性。     

Impact fault detection of gearbox based on variational mode decomposition and coupled underdamped stochastic resonance

In the gear fault diagnosis, the emergence of periodic impulse components in vibration signals is an important symptom of gear failure. However, heavy background noise makes it difficult to extract the weak periodic impulse features. Therefore, the paper presents an impact fault detection method of gearbox by combining variational mode decomposition (VMD) with coupled underdamped stochastic resonance (CUSR) to extract the periodic impulse features. First, the adaptive VMD is presented to decompose the vibration signal into several intrinsic mode functions (IMFs), which can automatically determine the appropriate mode number according to the correlation kurtosis (CK) of decomposition results and extract the sensitive IMF component containing the main fault information. Next, the adaptive CUSR method is developed to analyze the selected sensitive IMF component, and the optimal system parameters are obtained by the genetic algorithm using the CK index as optimization objective function. Finally, the periodic impulse features are extracted by the output signal of CUSR system accurately. Experiments and engineering application verify the effectiveness and superiority of the proposed adaptive VMD-CUSR method for extracting the periodic impulse features in gear fault diagnosis compared to other methods.     

Weak fault feature extraction of rolling bearing under strong poisson noise and variable speed conditions

Fault feature extraction of the rolling bearing under strong background noise is always a difficult problem in bearing fault diagnosis. At present, most of the research focuses on weak signal extraction under Gaussian white noise and has certain practical significance. However, the noise in engineering is often complex and changeable, Gaussian white noise cannot fully simulate the actual strong background noise. Poisson white noise is a type of typical non-Gaussian noise, which widely exists in complex mechanical impact. It is of great significance to study the weak fault feature extraction of a faulty bearing under this type of noise. At the same time, variable speed conditions occupy most rotating machinery speed conditions. Non-stationary vibration signals make it difficult to extract fault features, and the frequency spectrum ambiguity will occur because of speed fluctuation. To solve the above problems, a method of weak feature extraction of a faulty bearing based on computed order analysis (COA) and adaptive stochastic resonance (SR) is proposed. Firstly, by numerical simulation, the non-stationary fault characteristic signal corrupted with strong Poisson noise is transformed into a stationary signal in the angle domain by COA. Secondly, the influence of the parameters of the pulse arrival rate and noise intensity of Poisson white noise on the optimal SR response in the angle domain are studied, and the influence of the parameters of Poisson white noise on the fault feature extraction is given. Then, adaptive SR method is used to extract and enhance fault feature information. Finally, the effectiveness of this method in weak fault characteristic signal extraction under strong Poisson noise is verified by experiments. Numerical simulation and experimental results verify the effectiveness of the proposed method in bearing fault diagnosis under strong Poisson noise and variable speed conditions.

     

Adaptive wavelet transform for vibration signal modelling and application in fault diagnosis of water hydraulic motor

There has been an increasing application of water hydraulics in industries due to growing concern on the environmental, health and safety issues. The fault diagnosis of water hydraulic motor is important for improving water hydraulic system reliability and performance. In this paper, fault diagnosis of water hydraulic motor in water hydraulic system is investigated based on adaptive wavelet analysis. A novel method for modelling the vibration signal based on the adaptive wavelet transform (AWT) is proposed. The linear combination of wavelets is introduced as wavelet itself and adapted for the particular vibration signal, which goes beyond adapting parameters of a fixed-shape wavelet. The AWT procedure based on the parametric optimisation by genetic algorithm (GA) is developed. The model-based method by AWT is applied to extract the features in the fault diagnosis of the water hydraulic motor. This technique for de-noising the corrupted simulation signal shows that it can improve the signal-to-noise ratio of the vibration signal. The results of the experimental signal demonstrate the characteristic vibration signal details in fine resolution. The magnitude plots of the continuous wavelet transform (CWT) show the characteristic signal's energy in time and frequency domain which can be used as feature values for fault diagnosis of water hydraulic motor.     

基于多稳随机共振的机电设备故障诊断研究

针对机械轴承早期故障诊断提出了多稳随机共振检测方法。分析了系统参数对多稳系统结构的影响,研究了高斯噪声背景下基于多稳随机共振的微弱信号检测方法。采用平均输出信噪比作为衡量指标,以多频微弱信号为待测信号进行数值仿真,并将其应用于滚动轴承故障信号检测中,实验结果均表明,该方法对早期故障振动信号具备准确的诊断能力,为其应用于工程实践奠定了基础。     

一种面向旋转机械的基于 Transformer 特征提取的域自适应故障诊断

针对基于深度学习的旋转机械故障诊断方法在新工作条件下缺乏标注数据、跨域诊断精度较低的问题,提出了一种基 于 Transformer 的域自适应故障诊断方法。 采用 Transformer 的变体 VOLO 构造特征提取器以获取细粒度更佳的故障特征表示。 利用源域数据进行监督学习对源域和目标域数据的特征提取器进行预训练,并且冻结源域提取器参数以获取固定的源域特征。 利用域对抗自适应策略和局部最大平均差异结合目标域未标注数据训练目标域特征提取器,实现源域特征与目标域特征的边 缘分布、条件分布对齐。 通过两个多工况实验对所提出的故障诊断算法进行了验证,结果表明提出的基于 Transformer 特征提 取的域自适应故障诊断方法相比 5 种传统域自适应方法,在齿轮和轴承数据集上分别平均提升了 22. 15% 和 11. 67% 的诊断精 度,证明所提出方法对于跨域诊断精度具有提升作用。     

CMWPE结合SaE-ELM的轮对轴承故障诊断方法

针对DF4型内燃机车轮对轴承不同故障状态的判别问题,提出了一种基于复合多尺度加权排列熵(Composit multiscale weighted permutation entropy, CMWPE)和自适应进化极限学习机(Self-adaptive evolutionary extreme learning machine, SaE-ELM)的机车轮对轴承故障识别方法。CMWPE基于复合粗粒化和加权排列熵的思想,能很好地区分信号的不同模式。SaE-ELM通过自适应进化算法对极限学习机的输入权重、隐含层参数和输出权重进行优化,解决了ELM随机选取网络参数的局限性,提高了网络的泛化性能。计算机车轮对轴承不同健康状态下振动信号的CMWPE,利用SaE-ELM识别轴承所属故障类型及故障程度。在机务段的JL-501轴承检测台上采集了7种不同健康状态的轮对轴承试件的振动信号数据。结果表明：CMWPE特征提取效果优于MPE和MWPE;SaE-ELM模式识别效果优于参数不经优化的ELM。所提方法能够有效诊断机车轮对轴承的不同故障,且故障识别率达到100%。     

Intelligent diagnosis method for machinery by sequential auto-reorganization of histogram

This paper proposes an intelligent sequential diagnosis method for plant machinery using statistical filter (SF), signal histogram and genetic programming (GP). The SF is used to cancel noise from the measured vibration signal for raising the accuracy of fault diagnosis. Since the vibration signal measured for the condition diagnosis conforms to various probability distributions, histograms are used to reflect the signal features instead of the conventional symptom parameters (SPs). Then, the genetic programming (GP) is used to generate new variables termed “integrated symptom parameters” (GP-ISPs) from the histogram. GP-ISPs obtained by the auto-reorganized histogram can reflect features and raise the sensitivity of the fault diagnosis by the greatest amount possible. Furthermore, a sequential diagnosis algorithm using GP-ISPs is also proposed to realize precise diagnosis for distinguishing fault types. Finally, the effectiveness of the proposed method is verified by applying it to the fault diagnosis of a centrifugal blower. The proposed method has wide applicability and is practical in the field of machinery fault diagnosis.     

Adaptive multiwavelets via two-scale similarity transforms for rotating machinery fault diagnosis

Fault diagnosis of rotating machinery is very important and critical to avoid serious accidents. However, the complex and non-stationary vibration signals with a large amount of noise make the fault detection to be challenging, especially at the early stage. Based on the inner product principle, fault detection using wavelet transforms is to match fault features most correlative to basis functions, and its effectiveness is determined by the construction and choice of wavelet basis function. In this paper, a new method based on adaptive multiwavelets via two-scale similarity transforms (TSTs) is proposed. Multiwavelets can offer multiple wavelet basis functions and so have the possibility of matching various fault features preferably. TSTs are simple and straightforward methods to design a series of new biorthogonal multiwavelets with some desirable properties. Using TSTs, a changeable and adaptive multiwavelet library is established so as to provide various ascendant multiple basis functions for inner product operation. By the rule of kurtosis maximization principle, optimal multiwavelets most similar to the fault features of a given signal are searched for. The applications to a rolling bearing of outer-race fault and a flue gas turbine unit of rub-impact fault show that the proposed method is an effective approach to detecting the impulse feature components hidden in vibration signals and performs well for rotating machinery fault diagnosis.