基于多特征参数融合降维的主轴承故障识别方法

Main bearing fault recognition method based on multi-feature parame⁃ters fusion and dimensionality reduction

针对航空发动机主轴承故障信号传输路径复杂、不稳定和故障特征提取困难的特点,提出了一种基于时域特征参数、频域特征参数和本征模态函数(intrinsic mode function,IMF)能量矩特征参数融合降维的故障识别方法。首先,分别选取60组轴承滚动体故障、内圈故障、外圈故障和正常轴承数据,提取时域特征、频域特征及能量矩特征。由于3种参数组成的融合向量维度过大、数据量庞大和信息冗余,利用主成分分析方法(principal component analysis,PCA)对3种数据进行融合降维,根据主成分累积贡献率提取有效的主成分分量。最后,将降维后的特征向量输入支持向量机(support vector machine,SVM)中进行模式识别,诊断不同类型的轴承故障。结果表明,相对于使用单一特征参数等模型的故障识别正确率,该方法能够在复杂的信号中提取出有效的故障特征向量,之后运用故障特征向量准确地对故障类型进行识别分类,故障识别率达到98.75%。

In response to the complexities of fault signal transmission path,instability and difficulties in extracting fault feature for aircraft engine main bearing,a fault recognition method was proposed based on the fusion of time-domain feature parameters,frequency-domain feature parameters and intrinsic mode function(IMF)energy moment feature parameters for dimensionality reduction.Firstly,60 groups of bearing rolling element fault,inner ring fault,outer ring fault and bearing without fault data were selected respectively then time-domain,frequency-domain and energy moment features were extracted from these instances.Addressing the issue of high dimensionality,extensive data and redundant information of the fusion vector composed of three parameters,principal component analysis(PCA)was employed to reduce the dimensionality of these data and effective principal components were ex‐tracted based on cumulative contribution rates of principal components.Finally,the dimensionality re‐duction feature vectors were input into the support vector machine(SVM)for pattern recognition to di‐agnose the types of bearing faults.The results demonstrate that compared to models employing single feature parameters,this method effectively extracts fault feature vectors from complex signals.Subse‐quently,it accurately identifies and classifies fault types using these feature vectors,achieving a fault recognition rate of 98.75%.