摘要
采用小波变换和BP神经网络的辅助式结合,通过小波变换提取故障特征向量作为BP神经网络的输入值,设计并组建了小波神经网络;利用小波变换模极大值分析高压油管燃油压力信号的奇异性,提取故障特征向量;根据故障采集数据并建立学习样本,通过网络训练建立BP神经网络输入和输出间良好的非线性映射,进而通过特征向量输入BP神经网络来诊断故障。实验数据分析表明:该方法具有良好的诊断效果。
A wavelet neural network have been designed and built up.The singularity of fuel pressure signal is analyzed by wavelet transform modulus maxima to extract fault feature vectors.According to the data sampled from diesel engine fuel system working conditions,learning samples are obtained.Accordingly,nonlinear mapping between the neural network inputs and outputs have been well established via network training.Afterwards,fault diagnosis is achieved based on the input of feature vectors.According to the analysis and verification from the experimental data,this method is of good diagnosis effect.
出处
《重庆交通大学学报(自然科学版)》
CAS
北大核心
2012年第2期349-352,共4页
Journal of Chongqing Jiaotong University(Natural Science)
基金
重庆市教育委员会自然科学基金项目(KJ00402)
关键词
小波分析
神经网络
柴油机
燃油系统
故障诊断
wavelet analysis
neural network
diesel engine
fuel system
fault diagnosis