基于粒子群优化的小波神经网络及其在齿轮箱故障诊断中的应用  

WAVELET NEURAL NETWORK BASED ON PARTICLE SWARM OPTIMIZATION ALGORITHM AND ITS APPLICATION IN FAULT DIAGNOSIS OF GEAR-BOX

作　　者：毛鸿伟[1] 潘宏侠[1] 刘文礼[1] 

机构地区：[1]中北大学机械工程与自动化学院,太原030051

出　　处：《振动与冲击》2007年第5期133-136,共4页Journal of Vibration and Shock

基　　金：国家自然科学基金资助(项目编号:50575214)

摘　　要：用粒子群算法(PS0)取代传统的梯度下降法,优化小波神经网络中的各个参数。将经过PS0训练的小波神经网络应用于齿轮箱故障诊断,实验结果表明,基于PS0算法的小波神经网络训练方法是有效的神经网络训练算法,同时也是解决故障诊断问题的有效途径。A particle swarm optimization(PSO)algorithm is proposed instead of the traditional stochastic-gradient algorithm to optimize parameters of a wavelet neuralnetwork.Then,the PSO trained wavelet neuralnetwork is applied to a gear-box fault diagnosis experiment.The experimental result indicates that the wavelet neural network training method based on the PSO algorithm is an effective training algorithm,and meanwhile it is also an available approach to solve fault diagnosis problems.

关 键 词：粒子群算法 小波神经网络 故障诊断 

分 类 号：TH132[机械工程—机械制造及自动化] U226.81[交通运输工程—道路与铁道工程]