轴承复合故障欠定盲提取算法研究

Underdetermined Blind Separation for Bearings Faults Based on Improved Morphological Filter

针对实际工业现场强背景噪声、干扰源多、源数目未知等问题,提出一种基于多尺寸多结构元素的闭-开平均组合形态滤波和SCA相结合的(C-OACMF-SCA)故障特征盲提取方法.首先使用C-OACMF滤除背景噪声信号,提取观测信号的特征信号,然后使用模拟退火遗传算法的模糊C-均值聚类算法估计混合矩阵,最后通过线性规划估计源信号,实现故障特征提取.通过计算机仿真及实际环境下轴承复合故障振动信号欠定盲分离实验验证该算法的有效性.

Aiming at the condition of strong background noises,various interference sources and unknown number of sources in the actual industrial field,a method based on multi-scale multi-structure close-open average combination morphological filtering（ C-OACMF） and sparse component analysis（ SCA） is proposed to deal with the blind source separation problem of rotation machines. First,the C-OACMF is used to filter out background noise signals and to extract the characteristic signal of observation signals. The simulated annealing genetic algorithm of fuzzy C-average clustering algorithm is then employed to estimate the mixing matrix. At last,the linear programming is applied to the estimation of source signals. The results of computer simulation and real rolling bearing signals analysis show that the proposed method is quite effective.