基于LCD的自适应小波脊线解调及齿轮故障诊断

针对最佳小波参数的设定和齿轮裂纹故障振动信号频率成分复杂、信噪比低等问题,将遗传优化算法、小波脊线解调与局部特征尺度分解(local characteristic-scale decomposition,简称LCD)相结合,提出了基于LCD的自适应小波脊线解调方法。首先,采用LCD方法将原始信号分解为若干个内禀尺度分量(intrinsic scale component,简称ISC),并通过选择蕴含特征信息的ISC来实现信号降噪;然后,以小波能量熵为目标函数,采用遗传算法优化小波参数,得到自适应小波;最后,通过自适应小波分析提取ISC的小波脊线,从而实现对原始信号的解调分析。通过齿轮裂纹故障诊断实例验证了该方法的有效性和优越性。     

小波一神经网络在齿轮故障诊断中的应用

基于齿轮箱故障齿轮的特征提取,提出了将小波包分析与神经网络结合的齿轮故障诊断方法。对齿轮信号进行3层小波包分解,构造小波包特征向量作为故障样本,用训练好的BP神经网络进行故障诊断,实验结果表明该方法能够有效地诊断出齿轮的故障类型。     

小波-神经网络在齿轮故障诊断中的应用

基于齿轮箱故障齿轮的特征提取,提出了将小波包分析与神经网络结合的齿轮故障诊断方法.对齿轮信号进行3层小波包分解,构造小波包特征向量作为故障样本.用训练好的BP神经网络进行故障诊断,实验结果表明该方法能够有效地诊断出齿轮的故障类型.     

基于小波分析和修正指数分布的齿轮故障诊断方法

提出了基于小波分析和修正指数分布(modifiedexponentialdistribution,MED)的齿轮故障诊断方法,该方法采用小波包将齿轮振动信号分解为若干个频率段,然后选择合适的频率段进行小波包重构,对重构后的信号进行MED分析,得到齿轮振动信号的小波包时-频分布,进而从中提取齿轮振动信号故障的故障特征.对具有裂纹的齿轮振动信号分析结果表明了基于小波分析和MED的齿轮故障诊断方法的有效性.     

基于小波包与改进BP神经网络的齿轮故障诊断

对齿轮振动信号应用小波包分解提取故障特征向量,并以此作为改进BP神经网络的输入,对神经网络进行训练,建立齿轮运行状态分类器,用以诊断齿轮的运行状态。结果表明,该方法对齿轮故障诊断十分有效。     

基于AGA与GCV准则的小波阈值图像去噪研究

本文提出了一种基于AGA（自适应遗传算法）的小波阈值图像去噪研究方法。分别针对高斯噪声和非高斯噪声,在不需要估计噪声能量的情况下。采用GCV准则构造目标函数,用改进的自适应遗传算法求解多尺度小波分解每层系数的最优阈值,通过软阈值法对小波系数处理后进行小波重构。实验结果表明,利用这种方法进行图像去噪是可行的,并且能够达到较高的信噪比,算法的运行速度快,可较好的保留图像的细节信息。     

齿轮剥落故障特征识别方法研究

齿轮在啮合过程中,轮齿表面不可避免地会出现点蚀、剥落等故障,严重影响齿轮传动的稳定性和可靠性。基于齿轮时变啮合刚度模型和6自由度剥落故障齿轮动力学模型,研究了利用Matlab小波工具箱构造与信号对应的自适应小波的方法,阐明了振动信号的时频特征变化规律,并通过试验验证了构建自适应小波方法的正确性和对齿轮表面剥落缺陷识别的有效性,为在黑箱状态下有效识别齿轮缺陷以及分析缺陷尺寸提供了必要的理论基础和实践支撑。     

基于小波能量法的变速箱齿轮故障诊断技术研究

利用小波包分析并结合小波包能量谱尺度图的方法,通过小波包分解利用各频带范围信号能量的改变,进行了变速箱齿轮故障的诊断。按此方法准确地识别了某汽车H型变速箱的故障。研究表明,对变速箱齿轮故障诊断是一种行之有效的方法。     

基于小波神经网络(WNN)的齿轮故障诊断

在研究齿轮故障诊断模型以及齿轮故障诊断策略的基础上,选择基于知识方法的小波神经网络方法用于齿轮故障诊断,提出了学习速率自适应调整的梯度下降法来修正小波神经网络的各个系数;最后通过实验证明,利用小波神经网络技术能够实现准确识别齿轮故障.     

齿轮振动信号特征的小波包频率表示法

通过对信号的小波包分解的研究．提出了信号特征的小波包频率表示方法．表示信号对分解节点和频率的功率谱分布;同时提出以小波包频率表示为依据的特征信号重建方法。齿轮振动信号特征的小波包频率表示表明该表示方法能有效展示齿轮的技术状况的变化。将功率谱集中的相邻的结点上的分解结果重构,得到的时域特征信号也能展示齿轮的技术状况。     

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。     

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.     

An adaptive stochastic resonance method based on grey wolf optimizer algorithm and its application to machinery fault diagnosis

Stochastic resonance (SR) is widely used as an enhanced signal detection method in machinery fault diagnosis. However, the system parameters have significant effects on the output results, which makes it difficult for SR method to achieve satisfactory analysis results. To solve this problem and improve the performance of SR method, this paper proposes an adaptive SR method based on grey wolf optimizer (GWO) algorithm for machinery fault diagnosis. Firstly, the SR system parameters are optimized by the GWO algorithm using a redefined signal-to-noise ratio (SNR) as optimization objective function. Then, the optimal SR output matching the input signal can be adaptively obtained using the optimized parameters. The proposed method is validated on a simulated signal detection and a rolling element bearing test bench, and then applied to the gear fault diagnosis of electric locomotive. Compared with the conventional fixed-parameter SR method, the adaptive SR method based on genetic algorithm (GA-SR) as well as the well-known fast kurtogram method, the proposed method can achieve a greater accuracy. The results indicated that the proposed method has great practical values in engineering.     

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。     

蚁群算法融合BP神经网络的齿轮故障模式识别

为了提高齿轮故障诊断的准确性,引入了一种蚁群算法融合BP神经网络的方法。根据齿轮的故障特征量,建立其神经网络的故障诊断模型。以网络的权值和阈值为自变量,通过蚁群算法的迭代运算,搜索出误差全局最小值,再进行网络的二次学习训练,最终实现对齿轮的故障诊断。实例仿真结果表明,该方法具有较高的故障诊断精度,可减少诊断的不确定性。     

A new fault diagnosis algorithm for helical gears rotating at low speed using an optical encoder

Helical gears are widely used in gearboxes due to its low noise and high load carrying capacity, but it is difficult to diagnose their early faults based on the signals produced by condition monitoring systems, particularly when the gears rotate at low speed. In this paper, a new concept of Root Mean Square (RMS) value calculation using angle domain signals within small angular ranges is proposed. With this concept, a new diagnosis algorithm based on the time pulses of an encoder is developed to overcome the difficulty of fault diagnosis for helical gears at low rotational speeds. In this proposed algorithm, both acceleration signals and encoder impulse signal are acquired at the same time. The sampling rate and data length in angular domain are determined based on the rotational speed and size of the gear. The vibration signals in angular domain are obtained by re-sampling the vibration signal of the gear in the time domain according to the encoder pulse signal. The fault features of the helical gear at low rotational speed are then obtained with reference to the RMS values in small angular ranges and the order tracking spectrum following the Angular Domain Synchronous Average processing (ADSA). The new algorithm is not only able to reduce the noise and improves the signal to noise ratio by the ADSA method, but also extracts the features of helical gear fault from the meshing position of the faulty gear teeth, hence overcoming the difficulty of fault diagnosis of helical gears rotating at low speed. The experimental results have shown that the new algorithm is more effective than traditional diagnosis methods. The paper concludes that the proposed helical gear fault diagnosis method based on time pulses of encoder algorithm provides a new means of helical gear fault detection and diagnosis.     

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.     

基于粗糙集神经网络的刀具磨损监测的研究

针对多传感器刀具磨损监测系统输入维数较多、神经网络结构复杂、收敛速度慢等缺点,提出了粗糙集和遗传算法优化神经网络的模型.该模型首先利用粗糙集理论的属性约简对输入数据进行处理,从而达到减少神经网络输入维数、简化神经网络结构的目的.然后通过遗传算法优化神经网络的初始权值和阈值,以提高神经网络的收敛速度,避免神经网络陷入局部极值点.将该模型应用到刀具磨损监测,通过对声发射信号和电流信号进行处理,提取特征向量值,将特征值先通过自组织神经网络进行连续属性离散化,再通过粗糙集理论进行属性约简,最后通过遗传算法优化的BP神经网络进行识别,取得了很好的效果,证明了此模型的有效性和可行性.     

基于证据理论的齿轮故障诊断

针对传统方法在齿轮故障诊断中可靠性不高的问题,提出了基于证据理论的混合诊断算法.根据齿轮故障特征向量,采用两个并行的BP神经网络进行局部故障诊断,获得彼此独立的证据.再用证据理论对各证据进行融合,最终实现对齿轮的故障诊断.实例结果表明,该方法可充分利用各种故障的冗余和互补信息,有效地提高诊断的可信度.