互补集合经验模式分解与奇异值能量谱在风电齿轮故障识别中的应用

针对风电机组齿轮系统故障模式的有效识别问题,提出一种互补集合经验模式分解(CEEMD)与奇异值能量谱相结合的故障识别方法。利用CEEMD将齿轮非平稳信号分解为有限个平稳的本征模态函数,并将其组成初始特征向量矩阵,对矩阵进行奇异值分解并求出风电齿轮不同工况下的奇异值能量谱分布,以奇异值能量谱为元素构造特征向量,通过计算不同工况振动信号的灰色关联度来判断齿轮的故障类型。实例表明,该方法能有效应用于风电机组齿轮系统的故障诊断。

APPLICATION OF COMPLEMENTARY ENSEMBLE EMPIRICAL MODE DECOMPOSITION AND SINGULAR VALUE ENERGY SPECTRUM IN WIND POWER GEAR FAULT IDENTIFICATION

Aiming at the problem of effective fault pattern recognition of wind turbine gear system,a fault recognition method based on complementary ensemble empirical mode decomposition and singular value energy spectrum was proposed. The non-stationary signals of gears were decomposed into a finite number of stationary intrinsic mode functions by CEEMD,and the initial feature vector matrix was formed. The singular value decomposition of the matrix was carried out and the singular value energy spectrum distribution of wind power gears under different working conditions was obtained.The feature vector was constructed with the singular value energy spectrum as the element,and the vibration under different working conditions was calculated. The grey relevance degree of dynamic signal was used to judge the fault type of gear. The example showed that the proposed method can be effectively applied to the fault diagnosis of wind turbine gear system.