基于多特征融合多核学习支持向量机的液压泵故障识别方法

Fault Identification Method for Hydraulic Pumps Based on Multi-feature Fusion and Multiple Kernel Learning SVM

提出基于多特征融合多核学习支持向量机的液压泵故障识别方法。该方法首先对原始信号进行集总经验模态分解,然后分别用AR模型和奇异值分解两种特征提取方法提取故障特征,最后将不同类型的特征分别用相应的核函数进行映射,用多核学习支持向量机来识别液压泵的工作状态和故障类型。实验结果表明该方法显著地提高了故障诊断的准确性。

A hydraulic pump fault identification method was put forward based on multiple feature fusion and multiple kernel learning SVM. Firstly, the original signals were processed by the ensemble empirical mode decomposition. Then, the feature vectors of hydraulic pump faults were obtained by using the autoregressive model and the singular value decomposition. Through different types of features mapped by corresponding different kernel functions, the hydraulic pump working conditions and fault types might be finally identified by multiple kernel learning SVM. The experimental results show that the approach improves the accuracy of fault diagnosis significantly.