噪声与振动控制

›› 2011, Vol. 31 ›› Issue (2): 94-98.DOI: 10.3969/j.issn.1006-1355-2011.02.023

• 6.信号处理与故障诊断 • 上一篇    下一篇

改进的BP神经网络在风机故障诊断中的应用

米江,纪国宜   

  1. ( 南京航空航天大学 振动工程研究所， 南京 210016 )
  • 收稿日期:2010-08-26 修回日期:2010-09-14 出版日期:2011-04-18 发布日期:2011-04-18
  • 通讯作者: 米江

Application of Improved BP Neural Network in Fault Diagnosis of Fans

MI Jiang ，JI Guo-yi   

  1. （ Institute of Vibration Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China ）
  • Received:2010-08-26 Revised:2010-09-14 Online:2011-04-18 Published:2011-04-18

摘要： 采用动量法和学习速率自适应的改进BP神经网络建立风机故障诊断系统。在网络训练过程中分别采用标准训练样本和含有白噪声的训练样本来训练网络，使网络具有一定的容错性。最后通过仿真实验和风机的故障诊断实例表明：改进的BP神经网络减少训练次数，提高了学习效率，而且有效地抑制网络陷于局部极小，是风机故障诊断的有效方法。

关键词: 振动与波, 风机, 故障诊断, 改进的BP神经网络

Abstract: An improved BP neural network with the methods of momentum and adaptive learning rate is applied to build the fault diagnosis system of the fans. In the process of training, standard training samples and samples with white noise are employed to train the neural network so that the neural network has some ability of fault tolerance. Results of the simulation and the fault diagnosis of a fan show that the improved BP neural network needs less training times, the learning efficiency is raised, and the phenomenon of trapping in the local minimum for the network is effectively repressed. This method is effective for the fault diagnosis of fans.

Key words: vibration and wave, fan, fault diagnosis, improved BP neural network

中图分类号: