摘要
旋转机械设备故障诊断主要包括信号采集、特征提取和故障识别,而特征提取是进行故障诊断的基础和保证诊断结果正确的关键,为了提高特征参数对故障的敏感性,提出了基于自适应多小波与综合距离评估指数的旋转机械故障特征提取方法。该方法以综合距离评估指数最大值为目标函数,利用遗传算法从CL3自适应多小波库中选择最优多小波,并将该最优多小波用于转子振动信号的特征提取。通过对正常、不对中、不平衡、碰摩四种设备状态下采集的振动信号进行特征提取,并将所提出的方法和传统特征提取方法提取的特征参数输入到K-最邻近分类器进行分析,结果表明,所提出的方法能够大大增强特征参数对故障的敏感性,获得更高的故障诊断准确率。
The process of rotating machinery fault diagnosis is composed of signal acquisition,feature extraction and fault identification,among them the feature extraction is the foundation of fault diagnosis and the key to obtain correct diagnosis results.To improve the sensitivity of the extracted features to faults,a rotating machinery fault feature extraction method based on adaptive multi-wavelet and synthesis distance evaluation index was proposed here.In order to evaluate the sensitivity of feature parameters,the maximum value of the synthesis distance evaluation index was taken as the objective function,and the optimal multi-wavelets were selected from the library of CL3 adaptive multi-wavelet with genetic algorithm.Then they were used to extract features from vibration signals of a rotor.To prove the effectiveness of the proposed method,K-nearest neighbor classifier was used to analyze the features extracted with the proposed feature extraction method,the synthesis distance evaluation index feature extraction method and the principal component analysis feature extraction method,respectively from vibration signals of a tested rotating machinery under normal,unbalance,misalignment and rotor-to-stator rub conditions,respectively.The results showed that the proposed method can be used to improve the sensitivity of feature parameters and obtain a higher fault recognition rate.
出处
《振动与冲击》
EI
CSCD
北大核心
2014年第12期193-199,210,共8页
Journal of Vibration and Shock
基金
国家自然科学基金项目(51179135
51379160)
中央高校基本科研业务费专项资金资助项目(201120802020004)
关键词
旋转机械
特征提取
故障诊断
CL3自适应多小波
综合距离评估指数
rotating machinery
feature extraction
fault diagnosis
CL3 adaptive multi-wavelet
synthesis distance evaluation index
