支持向量机在压缩机气阀故障诊断中的应用

Application of Support Vector Machine in Fault Diagnosis of Compressor Valve

由于结构复杂且缺乏故障样本等原因,往复式压缩机的故障样本及诊断结果存在很强的不确定性。针对典型压缩机气阀振动信号的特点及不同故障机理,研究气阀振动信号的特征参数提取方法。提取工作循环有效值RMS1、气阀关闭段有效值RMS2,以及经两层小波包分解得到的各频带能量比系数E1、E2、E3、E4,组成6维特征向量,并将其作为支持向量机的输入。利用支持向量机适合处理高维数据且在有限样本下具有最优泛化能力的特点,对3种不同气阀状态下的振动信号经时域波形分析和小波包分解后提取的特征参数进行支持向量机学习;建立气阀故障诊断的支持向量机分类模型;利用Libsvm软件包对故障样本进行随机分类测试,并与其他智能诊断方法进行对比。对比结果表明,将支持向量机方法应用于往复式压缩机的气阀故障诊断中具有可行性;在小样本条件下,支持向量机较其他智能诊断方法具有更大的优势。

Due to the complexity of structure and lack of fault samples,strong uncertainty exists in fault samples and diagnosis results of the reciprocating compressors. According to the characteristics of the vibration signal of typical compressor air valve and the different fault mechanism,the extraction methods of characteristic parameters of valve vibration signal are studied. The working cycle effective value RMS1,and the effective value of the valve closed section RMS2 are extracted,and decomposed by two-layer wavelet to obtain energy ratio coefficients of E1,E2,E3 and E4,and to build up the six dimensional eigenvector and used as the input of the support vector machine（ SVM）. Taking the features of SVM,such as suitable for dealing with high-dimensional data and the optimal generalization ability under finite samples,through time domain analysis and wavelet packet decomposition of the vibration signals under three of different valve states,the feature parameters are extracted for conducting SVM learning; and the SVM classification model of valve fault diagnosis is established. The random classification test of the fault sample is conducted using Libsvm software package,and compared with other intelligent diagnostic methods. The comparison results show that it is feasible to apply SVM method in the valve fault diagnosis for reciprocating compressor,and the SVM has more advantages than other intelligent diagnosis methods under small sample condition.