论文部分内容阅读
针对齿轮箱振动信号的非平稳特性和在现实条件下难以获得大量故障样本的实际情况,提出一种经验模态分解和支持向量机相结合的故障诊断方法。运用经验模态分解方法对齿轮箱故障的振动信号进行分析,进行EEMD分解得到相对平稳的本征模态IMF,并计算每个IMF的能量熵,将其作为支持向量机的输入特征向量以判断齿轮箱的工作状态和故障类型。
Aiming at the non-stationary characteristics of gearbox vibration signals and the fact that it is difficult to obtain a large number of fault samples in real conditions, a fault diagnosis method based on empirical mode decomposition and support vector machine is proposed. Empirical mode decomposition method is used to analyze the vibration signal of gearbox fault, and EEMD is used to decompose it to get relatively stable intrinsic mode IMF. The energy entropy of each IMF is calculated and used as the input eigenvector of support vector machine Gearbox work status and fault type.