基于粒子滤波的机械设备故障振动信号识别研究  

Research on vibration signal identification of mechanical equipment fault based on particle filter

作　　者：陈运胜 CHEN Yunsheng(Guangzhou Huali Science and Technology Vocational College,Guangzhou 511325,China)

机构地区：[1]广州华立科技职业学院,广东广州511325

出　　处：《中国高新科技》2022年第14期95-97,共3页

摘　　要：针对目前机械设备故障振动信号识别精准度低的问题,文章提出了基于粒子滤波的机械设备故障振动信号识别研究。设计信号识别流程,对频带内信号能量分析,以能量为元素构造特征向量获取特征向量矩阵和归一化的特征向量,提取机械设备故障振动信号。结合小波包重构方法分析电机断条故障,使用粒子滤波分析轴承故障,利用非线性时间序列方法分析齿轮故障,以齿轮正常独立分量与齿轮断齿分量的相关系数为依据识别振动信号。由实验结果可知,该方法在不同故障情况下,信号波动频率与实际情况相差最小,具有精准识别效果。Aiming at the problem of low recognition accuracy of mechanical equipment fault vibration signal at present,a research on mechanical equipment fault vibration signal recognition based on particle filter is proposed.Design the signal identification process,analyze the signal energy in the frequency band,construct the eigenvector with the energy as the element,obtain the eigenvector matrix and the normalized eigenvector,and extract the mechanical equipment fault vibration signal.Combined with the wavelet packet reconstruction method to analyze the motor broken bar fault,particle filter is used to analyze the bearing fault,and the nonlinear time series method is used to analyze the gear fault.It can be seen from the experimental results that the method has the smallest difference between the signal fluctuation frequency and the actual situation under different fault conditions,and has an accurate identification effect.

关 键 词：粒子滤波 机械设备故障 振动信号 

分 类 号：TM595[电气工程—电器]