摘要
为了提高轴承故障诊断的准确性与快速性,提出一种集合经验模态分解(EEMD)、BP神经网络与改进引力搜索算法(IGSA)相结合的故障诊断方法。以电机轴承故障诊断为例,对电机轴承的故障信号采用EEMD分解,利用经过IGSA优化BP神经网络的权值、阈值对故障特征进行诊断。试验结果表明所提方法具有更快的诊断速度和更高的诊断率,能够有效地对电机轴承故障进行诊断。
To improve the quickness and accuracy of bearing fault diagnosis,a kind of ensemble empirical mode decomposition（ EEMD） and combing the gravitational search algorithm（IGSA） and BP are proposed. In the case of motor bearing fault diagnosis,first of all,the characteristic signal of motor bearing is extracted by ensemble empirical mode decomposition.Using the BP neural network to diagnose the fault characteristics,penalty parameter and kernel function have been optimized by improving gravitational search algorithm. Experimental results show that the proposed method has faster diagnosis speed and higher diagnostic rate,which can be effectively to motor bearing fault diagnosis.
出处
《沈阳理工大学学报》
CAS
2016年第6期66-71,共6页
Journal of Shenyang Ligong University
基金
辽宁省教育厅科学技术研究项目(L2015467)
辽宁省教育厅科学技术研究项目(L2014083)
