摘要
针对电厂风机滚动轴承的故障诊断问题,提出一种基于运行参数与振动信号特征融合的故障诊断方法。首先,提取滚动轴承振动信号的时域及频域特征;其次,采用线性局部切空间排列对振动信号特征参数和转速、负荷等机组运行参数进行融合与降维;最后将融合后的特征向量作为极限学习机的输入,得到故障的识别模型。理论分析和实验结果表明:特征融合的故障诊断方法对不同滚动轴承故障具有明显的辨识度,能有效地实现风机滚动轴承故障的自动判别。
Aiming at the problem of fault diagnosis of fans in power plant,a fault diagnosis method for fan rolling bearing based on the combination of operating parameters and vibration signals is proposed in this paper.Firstly,the time domain and frequency domain features of the rolling bearing vibration signals are extracted.Secondly,the Linear Local Tangent Space Arrangement is utilised to combine the extracted vibration signal features and the operating parameters such as speed and torque,etc.The eigenvectors for multi-feature fusion are employed as the input of the Extreme Learning Machine to obtain the fault recognition model.
出处
《工业控制计算机》
2019年第4期10-12,共3页
Industrial Control Computer
基金
国家能源集团总部科技项目(GJNY-18-01)
关键词
滚动轴承
特征融合
流行学习
故障诊断
rolling bearings
feature fusion
popular learning
fault diagnosis