[关键词]
[摘要]
为提高滚动轴承故障诊断的精度,提出了一种能够对其故障位置及严重程度进行诊断的方法:首先利用小波分解得到的不同频段的能量作为监测指标向量,并对所有故障的监测指标向量进行归一化处理,采用K-means方法从监测指标向量中提取特征向量,然后利用隐马尔科夫模型对故障进行建模和诊断,在此基础上建立故障定位矩阵,确定故障位置。以美国凯斯西楚轴承实验室的数据为基础,用上述方法能够识别不同故障严重程度,且对故障位置的判定准确率超过90%。
[Key word]
[Abstract]
In order to improve the accuracy of fault diagnosis of rolling bearing,a method is proposed to diagnose the fault severity and fault location.In this method,the energy of different frequency bands obtained by wavelet decomposition is used as the monitoring index vector,and the MIVs of all faults are normalized,and the feature vector is extracted from MIVs by K-Means method.Then the Hidden Markov Model (HMM) is used to model and diagnose the faults,the Fault Localization Matrix(FLM) is established based on HMM,and the FLM is used to determine the fault location.According to the data of Case Western Reserve University Bearing Data Center,the accuracy of the fault severity and fault location determined by the above method is high,which provides a new method for fault diagnosis of rolling bearing.
[中图分类号]
TK263.6+4
[基金项目]
中央高校基本科研业务费专项基金