为了解决模拟电路故障识别困难的问题,提出一种基于主成分分析和概率神经网络的模拟电路故障诊断方法。该方法对采集到的模拟电路故障信息进行特征提取,将提取的故障特征归一化处理后输入概率神经网络,进行训练和故障模式的分类识别。实验结果表明,该方法是有效的,具有较高的故障诊断率。 In order to solve the problem of analog circuit fault identification, a method of fault diagnosis of analog circuit based on principal component analysis and probabilistic neural network is proposed. The method extracts the feature information of the analog circuit fault information collected, normalizes the extracted fault features and inputs them into the probabilistic neural network to classify and identify the training and fault modes. Experimental results show that this method is effective and has a high fault diagnosis rate.