论文部分内容阅读
介绍了应用小波变换法与BP神经网络相结合实现模拟电路故障诊断的方法。应用小波变换法作为故障信号的预处理器,提取故障特征量,减小了BP神经网络的规模。该方法提高了神经网络收敛的速度以及故障类别识别的准确度,具有一定的应用价值。
The method of fault diagnosis of analog circuits based on wavelet transform and BP neural network is introduced. Applying the wavelet transform method as the preprocessor of the fault signal, the fault feature is extracted and the scale of the BP neural network is reduced. This method improves the speed of neural network convergence and the accuracy of fault category identification and has certain application value.