针对机械系统状态监测与故障诊断中存在的故障特征维数较高及模式识别导致的耗时较高问题，提出了一种基于自适应局部保持投影(Locality Preserving Projection，LPP)特征降维和改进多变量预测模型(Variable Predictive Model based Class Discriminate，VPMCD)的故障诊断方法。首先，从滚动轴承振动信号中提取时频域特征、能量特征，以及复杂度特征组成高维故障特征数据集;其次，利用自适应LPP方法对高维故障特征数据集进行降维处理，得到低维敏感故障特征;最后，采用改进VPMCD方法对低维敏感故障特征进行分类识别，进而判断故障类型。通过滚动轴承故障诊断试验分析表明，自适应LPP方法克服了传统LPP方法需要人工选取参数的缺陷，在获得低维敏感故障特征的基础上具有较少计算时间，相比主成分分析(Principal Component Analysis，PCA)、局部切空间排列(Local Tangent Space Alignment，LTSA)、线性局部切空间排列(Linear Local Tangent Space Alignment，LLTSA)、等距特征映射(Isometric Mapping，Isomap)，以及局部线性嵌入(Locally Linear Embedding，LLE)等算法具有明显的优势;改进VPMCD方法可克服人工选择模型的偶然性和片面性，在滚动轴承10种故障状态的识别中获得了 99。4％的诊断精度，相比优化参数支持向量机方法提高了故障诊断效率，大大降低了识别时间，具有一定的优越性。
Rolling bearing fault diagnosis method based on adaptive LPP and improved VPMCD
A fault diagnosis method based on adaptive Locality Preserving Projection(LPP)feature dimensionality reduction and improved Variable Predictive Model based Class Discriminate(VPMCD)was proposed to solve the issues of high fault feature di-mensionality and high time consumption caused by pattern recognition in mechanical system condition monitoring and fault diag-nosis.Firstly,time-frequency domain features,energy features,and complexity features were extracted from rolling bearing vibration signals to form a high-dimensional fault feature dataset;secondly,the high-dimensional fault feature set was downgraded by using the adaptive LPP method to obtain the low-dimensional sensitive fault features;lastly,the low-dimensional features were classified and recognized using the improved VPMCD method,and then the type of faults was judged.The analysis of rolling bear-ing fault diagnosis experiments showed that the adaptive LPP method overcomes the defect of manual pardameter selection in the LPP method,and has less computational time on the basis of obtaining low dimensional sensitive fault features.Compared with methods such as PCA,LTSA,LLTSA,Isomap,LLE,etc,it had obvious advantages;the improved VPMCD method can overcome the contingency and one-sided nature of the artificial selection model,and achieve 99.4％diagnostic accuracy in the identification of 10 fault states of rolling bearings.Compared with the optimization parameter support vector machine method,it reduced the identification time and improved the efficiency of fault diagnosis,which has certain advantages.
rolling bearingfault diagnosisfeature dimension reductionpattern recognitionLocality Preserving Projection(LPP)Variable Predictive Model based Class Discriminate(VPMCD)
国家科技期刊平台
NSTL
万方数据
