基于新型高精度粒子滤波的电机故障诊断  

A New Type and Precise PF Algorithm and Its Application to Fault Diagnosis

作　　者：汪超[1] 赵葵银[1] WANG Chao;ZHAO Kui yin(College of Electrical and Information Engineering, Hunan Institute of Engineering, Xiangtan 411104, China)

机构地区：[1]湖南工程学院电气信息学院,湘潭411104

出　　处：《湖南工程学院学报（自然科学版）》2018年第3期23-27,共5页Journal of Hunan Institute of Engineering(Natural Science Edition)

基　　金：湖南省教育厅科研资助项目(09C263;16K024)

摘　　要：提出了一种新的混合迭代无迹粒子滤波,以解决粒子滤波在故障诊断中的准确性和实时性问题.首先为提高粒子滤波精度,基于统计线性回归方法进行无迹变换(unscented transformation:UT),以降低算法时间复杂度.仿真实验表明,该方法在故障诊断中具有较高的准确性和鲁棒性.According to the accuracy and real time problems of the particle filter algorithm, this paper pro poses a new Hybrid Iterated Unsecnted Particle Filter algorithm（HI UPF）. The new algorithm optimizes unscented transformation by using the statistical linear regression method. In this way, the filtering preci sion is improved, and the time consumption of the proposed algorithm is effectively reduced. Experiments show that the proposed method is reliable and robust in fault diagnosis.

关 键 词：故障诊断 粒子滤波 状态估计 IUKF 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]