基于粒子滤波器的移动机器人故障诊断和预测方法  

Particle Filter Based Fault Diagnosis and Prediction Method of Mobile Robot

作　　者：柳玉甜[1] 蒋静坪[2] 

机构地区：[1]浙江万里学院电子信息学院,浙江宁波315100 [2]浙江大学电气工程学院,浙江杭州310027

出　　处：《机床与液压》2009年第11期241-245,共5页Machine Tool & Hydraulics

基　　金：国防科技预研基金资助项目(00J16.6.3.JW0401)

摘　　要：针对移动机器人存在的8种故障模式(1种正常模式和7种故障模式),引入粒子滤波器算法,用于解决移动机器人系统(包括离散故障状态和连续状态)故障诊断和预测问题。基于粒子滤波器的故障诊断和预测算法通过一组带权值的粒子来估计系统的状态,并计算故障状态的分布情况和故障发生的概率,以此判断是否发生故障以及所发生的故障类型。仿真结果表明,该方法能有效地诊断和预测移动机器人的故障模式。Eight fault modes for mobile robots were discussed. An improved particle filter based approach was proposed for the diagnosis and prediction of the fault modes of mobile robots. Particle filter is an algorithm that uses swarms of weighted particles in state space to approximate the probability density function of the state. According to the probability distribution of the state, the proba- bility of fault diagnosis and fault prediction can be obtained. The proposed approach was implemented on a mobile robot and the simulation results show the effectiveness of the method.

关 键 词：粒子滤波器 故障诊断 故障预测 移动机器人 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]