摘要
文章提出了一种基于小波神经网络的模拟电路故障诊断方法。这种方法采用正弦信号作为被测电路的输入激励,在时域中对输出信号采样来构造神经网络的训练和测试样本,将自适应学习率及附加动量BP算法训练后的小波神经网络应用于某装备可更换电路单元故障诊断中。仿真试验表明,该方法减少了故障诊断时间和提高了网络的平均诊断正确率。
A method of analog circuit fault diagnosis based on wavelet neural network is presented. This method excites analog circuit with sinusoidal signal and samples its output to collect training and test data for the neural network in timedomain. The wavelet neural network is trained by the back propagation arithmetic which adopt momentum and self-adaptive learning arithmetic. This paper applies the WNN in fault diagnosis of Changeable Circuit Unit Modules. Experimentation indicates that the method can decrease fault diagnosis time and enhance network of average diagnosis accurate ratio.
出处
《国外电子测量技术》
2010年第8期29-32,共4页
Foreign Electronic Measurement Technology
