滚动轴承故障诊断的多重超阶分析方法

Multifractal super order analysis method for rolling bearing fault diagnosis

多重分形去趋势波动分析(MF-DFA)可以获得能够表征信号内在动力学机制的多重分形谱,但是在提取滚动轴承振动信号故障特征时存在参数接近、状态混叠等问题,导致分析结果易受信号噪声等因素干扰,影响分类精度。为解决此问题,提出了多重超阶分析(MF-SOA)的方法。该方法将极值增量方法引入了多重去趋势波动分析中,对时间序列进行取极值操作;然后计算并分析获得的极值增量序列的重分形特征,通过MF-SOA方法获得的特征可以更清晰地表现出序列的内部动力学机制。最后将所提出的方法应用于滚动轴承的故障诊断中。试验数据分析结果表明,该方法对于信号的不规则程度十分敏感,并且有效改善了MF-DFA方法的缺陷,对于模式相近的故障类型有更优的区分度,提高了滚动轴承故障诊断的精度。

Multifractal de-trend fluctuation analysis(MF-DFA)can acquire multifractal spectrum being able to characterize intrinsic dynamic mechanism of a signal,but it has problems of parameters close and state aliasing when extracting fault features in rolling bearing vibration signals to leads to analysis results being easy to be interfered by signal noise and classification results being affected.Here,to solve this problem,the multifractal super order analysis(MF-SOA)method was proposed.Firstly,the extreme value increment method was introduced into MF-DFA,and extreme value operations were done for time series.Then,multifractal features of extreme value increment sequence obtained were calculated and analyzed.Features obtained with MF-SOA method could more clearly reveal internal dynamic mechanism of sequence.Finally,the proposed method was applied in fault diagnosis of rolling bearings.The test data analysis results showed that the proposed method is very sensitive to irregular degree of a signal,and can effectively improve defects of the MF-DFA method;it has a better discrimination degree for fault types with similar modes,and improves the accuracy of rolling bearing fault diagnosis.