基于LabVIEW的轴承和齿轮故障诊断系统设计

发布时间：2018-10-20 08:45

【摘要】：自动化水平的不断提高增加了机械设备的复杂程度,滚动轴承和齿轮作为机械设备中必不可少的器件,其故障的发生将造成生产上重大的损失,更易危及操作人员的人身安全。为此,研究一种有效诊断轴承进而齿轮故障的诊断系统具有重要的实际意义。本文通过对轴承和齿轮故障信号进行时域特征分析发现,有量纲参数中均方根以及无量纲参数中的峭度因子、峰值因子、裕度因子、波形因子、脉冲因子对故障信号敏感度较好,因此可将这几种参数作为滚动轴承和齿轮的时域特征参数。通过对故障信号进行傅里叶变换和自功率谱分析,可以确定故障信号的固有频率和边频的频带范围,为后续滤波以及特征频率的提取提供依据。对于非平稳的振动信号,时频分析是处理该种信号的有效手段。因此本文应用小波包的共振解调方法对故障信号进行小波包分解,选取低频小波包系数进行重构,对重构信号进行共振解调分析。实验分析表明,该方法更准确找到其特征频率。同时采用BP神经网络进行故障诊断,将提取的故障信号时域特征以及故障特征频率作为神经网络的输入,自动识别并确定轴承和齿轮的故障类型。通过实验表明,该方法的识别效果较好。本文基于LabVIEW虚拟仪器技术开发了一套旋转机械故障诊断系统。诊断系统主要包括信号回放模块、时域特征参数提取模块、频域特征分析模块、基于小波包的共振解调特征提取模块以及基于BP神经网络的故障诊断系统模块。系统能够识别和诊断故障信号,具有实用性和可移植性。并且通过实验验证故障诊断系统的准确性和稳定性。
[Abstract]:The continuous improvement of automation level increases the complexity of mechanical equipment. Rolling bearings and gears are indispensable devices in mechanical equipment. The failure of rolling bearings and gears will cause great losses in production and endanger the personal safety of operators more easily. Therefore, it is of great practical significance to study an effective fault diagnosis system for bearing and gear. Based on the time-domain characteristic analysis of bearing and gear fault signals, it is found that the kurtosis factor, peak factor, margin factor, waveform factor in dimensionless parameters and the root mean square in dimensionless parameters are found in this paper. The pulse factor is sensitive to the fault signal, so these parameters can be used as the time domain characteristic parameters of the rolling bearing and gear. Through Fourier transform and self-power spectrum analysis of the fault signal, the frequency range of the natural frequency and the edge frequency of the fault signal can be determined, which provides the basis for the subsequent filtering and the extraction of the characteristic frequency. For non-stationary vibration signal, time-frequency analysis is an effective means to process the signal. Therefore, this paper applies the method of wavelet packet resonance demodulation to decompose the fault signal, select the low frequency wavelet packet coefficient to reconstruct, and analyze the resonance demodulation of the reconstructed signal. The experimental results show that the method can find the characteristic frequency more accurately. At the same time, BP neural network is used for fault diagnosis. The time domain feature and fault feature frequency of the extracted fault signal are taken as the input of the neural network to identify and determine the fault types of bearing and gear automatically. Experiments show that the method is effective. A rotating machinery fault diagnosis system based on LabVIEW virtual instrument technology is developed in this paper. The diagnosis system mainly includes signal playback module, time domain feature extraction module, frequency domain feature analysis module, resonance demodulation feature extraction module based on wavelet packet and fault diagnosis system module based on BP neural network. The system can identify and diagnose fault signals, and has practicability and portability. The accuracy and stability of the fault diagnosis system are verified by experiments.
【学位授予单位】：东北石油大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TH133.3;TH132.41

【参考文献】