小波变换具有时频局部化、多尺度分析等特性,而神经网络具有非线性映射、学习推理等优点,将二者结合起来,提出基于小波-神经网络的模拟电路故障诊断方法。采用正弦信号仿真模拟电路,应用小波变换对模拟电路响应的采样信号进行故障特征提取,建立故障字典,然后利用神经网络对各种状态下的特征向量进行分类决策,实现模拟电路的故障诊断。对标准电路仿真结果表明:该方法能够实现故障检测及定位,具有准确率高的特点。 The wavelet transform has the characteristics of time-frequency localization and multi-scale analysis. The neural network has the advantages of nonlinear mapping, learning reasoning and so on. Combining the two, a method of fault diagnosis of analog circuits based on wavelet neural network is proposed. Using the sinusoidal signal simulation circuit, the wavelet transform is used to extract the fault feature of the sampled signal responding to the analog circuit, and the fault dictionary is established. Then the neural network is used to classify the feature vectors in various states to realize the fault diagnosis of the analog circuit. The simulation results of the standard circuit show that this method can detect and locate faults with high accuracy.