摘要
本文提出了一个基于改进粒子群优化算法的BP神经网络优化模型来进行轴承故障诊断,此模型融合粒子群优化算法的全局寻优能力和BP神经网络算法的局部搜索的优势,有效地防止了网络陷入局部极小值,同时又保证了诊断结果的精确性。仿真结果表明机车滚动轴承故障得到了有效诊断。相比于常规的BP神经网络模型,此方法不仅改进网络的收敛速度并且提高了预测准确性。
In this paper,a BP neural network model based on improved PSO was presented and applied it for bearing fault diagnosis,combined with PSO Algorithm for global optimization ability and BP neural network advantages of local search,the model effectively prevented the network into a local minimum,at the same,time guaranteed the accuracy of diagnosis.Simulation results showed that the locomotive rolling bearings was effectively diagnosed.Compared with the conventional BP neural network model,this method not only improvesd the convergence speed,but also improved the prediction accuracy.
出处
《铁路计算机应用》
2012年第2期9-12,16,共5页
Railway Computer Application
