首页 | 本学科首页   官方微博 | 高级检索  
     

改进PSO-BP网络在故障诊断中的应用
引用本文:段向军,韩满林. 改进PSO-BP网络在故障诊断中的应用[J]. 机床与液压, 2011, 39(1). DOI: 10.3969/j.issn.1001-3881.2011.01.041
作者姓名:段向军  韩满林
作者单位:南京信息职业技术学院机电分院,江苏南京,210046
摘    要:针对油田抽油机井故障诊断方法较落后的问题,提出一种基于改进PSO-BP网络的故障诊断系统.神经网络权值的训练采用改进的PSO算法,克服了BP学习算法收敛速度慢、易陷入局部极值的缺点.将该网络用于抽油机井的故障诊断,并与传统BP模型的故障诊断结果进行比较.结果表明:基于改进PSO-BP的故障诊断方法正确率达96%以上,可以在更短的时间内、用更少的迭代次数达到精度要求,为设备检修提供了可靠的依据.

关 键 词:BP神经网络  抽油机  故障诊断

Application of BP Network Based on Improved PSO in Fault Diagnosis
DUAN Xiangjun,HAN Manlin. Application of BP Network Based on Improved PSO in Fault Diagnosis[J]. Machine Tool & Hydraulics, 2011, 39(1). DOI: 10.3969/j.issn.1001-3881.2011.01.041
Authors:DUAN Xiangjun  HAN Manlin
Affiliation:DUAN Xiangjun,HAN Manlin(Mechanical and Electrical Institute,Nanjing College of Information Technology,Nanjing Jiangsu 210046,China)
Abstract:A BP neural network fault diagnosis system was proposed based on a kind of improved particle swarm optimization(PSO) algorithm by aiming at the problem of pump-jack fault diagnosis method backward.The improved PSO algorithm was used to train the BP neural network weight values.The shortcomings of slow convergence and trapped easily in the local extreme values by BP learning algorithm could be overcome.The system was used to diagnose the faults of pump-jacks in oil field and compared with traditional BP mode...
Keywords:PSO
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号