基于粒子滤波的电力机械设备状态在线监测  

On-line Monitoring of the State of Electric Machinery Equipment Based on Particle Filter

作　　者：吴威 高骏 田祥雨 WU Wei;GAO Jun;TIAN Xiangyu(State Grid Jiangsu Electric Power Co.,Ltd.,Nanjing 210024,China)

机构地区：[1]国网江苏省电力有限公司,江苏南京210024

出　　处：《机械与电子》2023年第2期51-55,共5页Machinery & Electronics

摘　　要：为提升电力机械设备状态在线监测的效果,提出基于粒子滤波的电力机械设备状态在线监测方法。通过人工萤火虫群算法改进粒子滤波算法后,借助随机子空间算法构建改进粒子滤波算法所需状态方程。利用该状态方程获取电力机械设备正状态观测矩阵和输出矩阵数值,并将其看作模态参数,依据该模态参数计算粒子滤波状态序列和电力机械设备振动状态变量数值后,构建粒子滤波器,使用该滤波器去除电力机械设备振动信号内干扰噪声后,对电力机械设备振动信号实施归一化处理,得到粒子权重概率和改进粒子滤波监测数值。通过设置振动信号监测步长和阈值,计算监测信号与采集信号差值,使其与所设阈值进行对比,获取电力机械设备状态在线监测结果。实验结果表明,该方法监测的电力机械设备信号最大偏差数值仅为0.003 dB,具备较好的信号跟踪能力,且具备较好电力机械设备振动监测能力。In order to improve the effect of online monitoring of power mechanical equipment status, the online monitoring of power mechanical equipment based on particle filtering is proposed.After the particle filtering algorithm is improved by artificial firefly swarm algorithm, the state equation required by the improved particle filter algorithm is constructed by using random subspace algorithm.The state equation is used to obtain the values of the positive state observation matrix and output matrix of the power mechanical equipment, which is regarded as the modal parameters.After the particle filter state sequence and the vibration state variable of the power mechanical equipment are calculated based on the modal parameters, the particle filter is constructed.After the filter is used to remove the interference noise in the vibration signal of the power mechanical equipment, the vibration signal of electric machinery equipment is normalized to obtain the particle weight probability and the improved particle filter monitoring value.By setting the vibration signal monitoring step and threshold, the difference between the monitoring signal and the collected signal is calculated and compared with the set threshold, so as to obtain the online monitoring results of the state of electric machinery equipment.The experimental results show that the maximum deviation value of the signal monitored by this method is only 0.003 dB,which has a good signal tracking ability and good vibration monitoring ability of power machinery equipment.

关 键 词：粒子滤波 电力机械 设备状态 在线监测 人工萤火虫群 噪声方差 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]