论文部分内容阅读
针对离心泵振动信号的非平稳特征,提出一种基于经验模式分解(empirical mode decomposition,EMD)复杂度特征和最小二乘支持向量机的离心泵振动故障诊断方法。首先对振动信号进行经验模式分解,将其分解为若干个固有模态函数(intrinsic mode function,IMF),然后对每一个IMF分量提取复杂度特征作为故障特征向量,并以此作为输入参数建立最小二乘支持向量机分类器诊断故障。选用径向基函数(radial basis function,RBF)作为核函数,并采用差分进化算法进行参数选择。应用结果表明,EMD复杂度特征能准确诊断故障,参数优化后的模型具有更高的分类能力。
Aiming at the non-stationary characteristics of centrifugal pump vibration signals, a centrifugal pump vibration fault diagnosis method based on empirical mode decomposition (EMD) complexity features and least squares support vector machine is proposed. First of all, the vibration signal is decomposed into several intrinsic mode functions (IMFs) by empirical mode decomposition. Then the complexity features of each IMF component are extracted as fault eigenvectors and used as the input parameters to establish the minimum Quadratic Support Vector Machine Classifier to Diagnose Faults. Radial basis function (RBF) is chosen as the kernel function, and differential evolution algorithm is used for parameter selection. The application results show that the EMD complexity feature can accurately diagnose the fault and the parameter optimized model has higher classification ability.