基于变量预测模型的模式识别方法在滚动轴承故障诊断中的应用  

Application of Pattern Recognition Approach Based on VPMCD in Roller Bearing Fault Diagnosis

作　　者：杨宇[1] 王欢欢[1] 曾鸣[1] 程军圣[1] 

机构地区：[1]湖南大学汽车车身先进设计制造国家重点实验室,湖南长沙410082

出　　处：《湖南大学学报（自然科学版）》2013年第3期36-40,共5页Journal of Hunan University:Natural Sciences

基　　金：国家自然科学基金资助项目(51175158;51075131);湖南省自然科学基金资助项目(11JJ2026);中央高校基本科研业务费专项基金资助项目(531107040301);湖南大学汽车车身先进设计制造国家重点实验室自主课题资助项目(61075002)

摘　　要：将基于变量预测模型(Variable Predictive Model based Class Discriminate,VPMCD)的方法引入滚动轴承的故障诊断,提出了基于EMD(Empirical Mode Decomposi-tion,EMD)和VPMCD的滚动轴承故障诊断方法.采用EMD方法提取滚动轴承振动信号特征向量后,以VPMCD作为模式识别方法对滚动轴承的工作状态和故障类型进行分类.对正常状态、外圈故障、内圈故障3种不同类别下的滚动轴承振动信号进行了分析,结果表明了该方法在滚动轴承故障诊断中的有效性.同时,与人工神经网络(Artificial neural net-work,ANN)算法的对比分析表明,VMPCD算法分类性能的稳定性以及计算效率均要高于ANN算法.Variable predictive model based class discriminate （VPMCD） method was introduced to roll- er bearing fault diagnosis, and a roller bearing fault diagnosis approach based on empirical mode decompo- sition （EMD） and VPMCD was put forward. Firstly, different feature vectors were extracted with EMD. Then, different working conditions and failures of roller bearing were distinguished by using VPMCD. A- nalysis results of vibration signals from roller bearing＇s normal condition, outer ring fault and inner ring fault show the effectiveness of the proposed approach in roller bearing fault diagnosis. What＇s more, com- parative analysis results demonstrate that VPMCD algorithm gains more stable classification performance and better computational efficiency than artificial neural network （ANN） algorithm.

关 键 词：模式识别 故障诊断 变量预测模型 滚动轴承 

分 类 号：TH165.3[机械工程—机械制造及自动化]