摘要
为了提高电机轴承故障诊断的准确率,提出了基于粒子群优化的支持向量机(SVM)故障诊断的方法。文章采用局部均值分解(LMD)提取电机轴承振动信号特征作为支持向量机的特征向量;采用粒子群优化算法(PSO)优化支持向量机的核函数参数和惩罚参数,以此建立分类器用于识别电机轴承故障类型。通过仿真实验验证该方法能够有效的识别电机轴承故障状态。
In order to improve the accuracy of the motor bearing fault diagnosis,a newmethod for fault diagnosis was proposed based on support vector machine optimized by Particle swarm opti- mization algorithm.This paper combined it with local mean decomposition（ LMD） to extract the characteristics of the vibration signals of the motor bearing as feature vector to support vector machine. The Particle swarm optimization（ PSO） algorithm optimized support vector machine parameter of kernel function parameter and penalty parameter is proposed to establish the class- ifier for the identification of motor bearing fault type. The simulation experiment shows that proved proposed method is effective to diagnose motor roller bearings fault.
出处
《组合机床与自动化加工技术》
北大核心
2016年第8期81-84,共4页
Modular Machine Tool & Automatic Manufacturing Technique
基金
国家自然基金(51274011)
安徽省科技攻关项目(1501021027)
关键词
轴承
故障诊断
支持向量机
局部均值分解
粒子群优化算法
motor bearing
fault diagnosis
support vector machine
local mean decomposition
particle swarm optimization algorithm
