摘要
针对电机轴承故障振动信号的强噪声背景,以及电机轴承故障是一个内圈故障、外圈故障和滚动体故障多级分类问题的情况,提出了一种基于柔性形态滤波和遗传规划的电机轴承故障诊断方法.该方法首先对电机轴承故障原始信号进行柔性形态滤波,然后提取滤波后信号的故障特征频率的归一化能量以及时域统计特征量作为遗传规划中的终止符,通过复制、交叉、突变以及适应度计算等操作,使个体逐渐逼近问题的最优解,得到电机轴承故障模式分类的最优模型,试验结果表明了该方法的有效性.
Based on soft morphological filtering and genetic programming(GP), a motor rolling bearing fault diagnosis method is proposed. It is very difficult to filtrate the fault vibration signals from the strong noise background because the roller bearing fault diagnosis is a problem of multi-class classification of inner ring fault, outer ring fault and ball fault. Firstly, vibration signals are filtrated by soft morphological filters. Secondly, the normalized energy in different characteristic frequencies is utilized to identify the fault features of feature terminals of GP. An optimal motor rollingbeating fault classification model is obtained by reproducing, mutating and over-crossing. Experiment results demonstrate that this modeling is correct and precise.
出处
《控制理论与应用》
EI
CAS
CSCD
北大核心
2009年第9期953-957,共5页
Control Theory & Applications
基金
国家杰出青年科学基金资助项目(50425516)
国家自然科学基金重点资助项目(10732060)
国家“863”高技术研究发展计划资助项目(2006AA04Z438)
关键词
柔性形态滤波
遗传规划
特征提取
故障诊断
soft morphological filters
genetic programming
feature extraction
fault diagnosis