当前位置>主页 > 期刊在线 > 智能制造 >

智能制造2019年12期

基于改进粒子群优化SVM 的轴承故障识别研究
曹进华
(厦门大学嘉庚学院,福建 漳州 363105)

摘  要:为了提高轴承故障严重程度识别的准确率,本文提出基于改进粒子群算法优化SVM 的轴承故障识别方法。针对粒子群算法易陷入局部最优的不足,引入Levy 飞行方式改进粒子群算法的寻优过程。在运算过程中,该方法通过粒子群的进化程度,将粒子种群动态的划分为较优子群和较差子群;较差子群以PSO 算法为指导进行全局搜索,较优子群中引入Levy 飞行方式,粒子围绕最优个体进行精细化的寻优过程;两个子群通过种群之间个体的重组和全局最优个体的更新实现信息交换。通过实验数据分析的结果表明:基于LPSO 优化SVM 参数提高了轴承故障识别的准确率,效果优于其他几种方法。


关键词:粒子群算法;支持向量机;故障识别;滚动轴承



中图分类号:TH133;TP181         文献标识码:A         文章编号:2096-4706(2019)12-0148-04


Research of Bearing Fault Diagnosis Method Based onImprovement PSO Optimized SVM

CAO Jinhua

(Xiamen University Tan Kah Kee College,Zhangzhou 363105,China)

Abstract:In order to improve the recognition accuracy of bearing fault severity identification. In view of the problem,a bearingfault recognition based on improvement PSO algorithm optimized SVM is proposed. Due to the demerits of PSO optimization algorithm,such as easily relapsing into local optimum,introducing Levy flight strategy to improve PSO algorithm. In the process of computation,the method divides the dynamics of particle population into better subgroups and worse subgroups by the evolutionary degree of particleswarm. The worse subgroups are searched globally under the guidance of PSO algorithm. Levy flight mode is introduced into the bettersubgroups,and the particles are refined around the optimal individuals. The information exchange between the two sub-populations isrealized by the reorganization of individuals and the updating of the globally optimal individuals. The results of experimental data analysisshow that optimization of SVM parameters based on LPSO improves the accuracy of bearing fault identification,and the effect is betterthan other methods.

Keywords:PSO;SVM;fault recognition;rolling bearing


参考文献:

[1] 张超,陈建军,郭迅. 基于EMD 能量熵和支持向量机的齿轮故障诊断方法 [J]. 振动与冲击,2010,29(10):216-220+261.

[2] Moura M D C,Zio E,Lins I D,et al. Failure and reliability prediction by support vector machines regression of time series data [J].Reliability Engineering and System Safety,2011,96(11):1527-1534.

[3] 翟永杰,毛继珮,于丽敏,等. 分级聚类支持向量机在汽轮机故障诊断中的应用 [J]. 华北电力大学学报,2003(6):25-29.

[4] 付阳,李昆仑. 支持向量机模型参数选择方法综述 [J]. 电脑知识与技术,2010,6(28):8081-8082+8085.

[5] 韩世军,朱菊,毛吉贵,等. 基于粒子群优化支持向量机的变压器故障诊断 [J]. 电测与仪表,2014,51(11):71-75+90.

[6] 刘耀年,尹洪全,张伟,等. 基于改进粒子群算法的配电网状态估计 [J]. 电测与仪表,2012,49(9):24-27+51.

[7] 和麟,梁丽嫒,黄潇瑶,等. 基于粒子群优化SVM 的飞机发电机故障诊断 [J]. 计算机测量与控制,2013,21(12):3237-3239.


作者简介:曹进华(1979.12-),男,汉族,福建武夷山人,副教授,博士研究生,研究方向:机械性能检测与故障诊断。