模拟电路故障诊断的小波包预处理神经网络改进算法

提出了基于小波包预处理的神经网络模拟电路故障诊断方法的两种改进方法:最优小波包变换(OWPT)预处理和不完全小波包变换(IWPT)预处理BP神经网络算法。首先对模拟电路的响应信号用这两种方法进行预处理,然后计算预处理后信号各个频段上的归一化能量,把归一化的能量作为训练样本送给BP网络进行训练,有效减少了BP网络的输入节点和隐层节点的个数,从而减小了神经网络的规模,降低了计算的复杂度,加快了网络的训练和收敛速度。仿真实验表明此方法能够快速有效的对模拟电路的故障进行诊断和定位。

Two improved neural network algorithms of fault diagnosis for analog circuit based on wavelet packet preprocessing

This paper presents two improved BP neural network methods of fault diagnosis for analog circuit,using optimal wavelet packet transform(OWPT)or incomplete wavelet packet transform(IWPT)as preprocessor.At first,the response signal of analog circuit is preprocessed by OWPT or IWPT,and the normalization energy of each frequency band is worked out.The normalization energy is then used to train a BP neural network to diagnose faulty components in an analog circuit.These two algorithms need small network size,while have faster learning and convergence speed.Finally,simulation results illustrate the two methods are effective for fault diagnosis.