基于主元分析与KNN算法的旋转机械故障识别方法

发布时间：2018-04-10 20:09

本文选题：主元分析 + K近邻　；参考：《机械设计与制造》2017年06期

【摘要】：针对旋转机械高维故障数据难以被准确辨识的情况,提出了一种基于主元分析(principal component analysis,PCA)和K近邻(K-nearest neighbour,KNN)算法的旋转机械故障识别方法。合理选取出各状态信号的时域、频域特征指标构造成高维特征空间,输入给主元分析算法进行降维处理,提取出低维敏感特征,将约简后的状态样本输入给KNN算法进行故障识别。滚动轴承和转子的实验结果表明,该方法能够很好的约简高维故障样本特征,在实现样本数据可视化的同时准确识别出各故障样本。与传统方法相比,该方法具有结构简单、识别率高等优点,对机械故障诊断研究具有一定的工程意义。
[Abstract]:In view of the difficulty of accurate identification of high dimensional fault data of rotating machinery, a fault identification method for rotating machinery based on principal component analysis (PCA) and K-nearest neighbor KNN (K-nearest neighbor KNN) algorithm is proposed.The time-domain and frequency-domain characteristic indexes of each state signal are reasonably selected and constructed into a high-dimensional feature space, which is input to the principal component analysis algorithm for dimensionality reduction, and the low-dimensional sensitive feature is extracted.The reduced state samples are input to the KNN algorithm for fault identification.The experimental results of rolling bearings and rotors show that the proposed method can well approximate the features of the fault samples in the high dimension and realize the visualization of the sample data and accurately identify the fault samples at the same time.Compared with the traditional method, this method has the advantages of simple structure and high recognition rate, and has certain engineering significance for the research of mechanical fault diagnosis.
【作者单位】：沈阳化工大学机械工程学院;
【基金】：国家自然科学基金(51275315)
【分类号】：TH17

【相似文献】