Soft fault diagnosis has been validated as a very challenging problem in analog circuits. In order to improve the generalization ability and close to the practical application of fault diagnosis models, a novel method for obtaining a large number of training samples in soft fault interval is proposed in the present work. Training samples are randomly generated in the interval of soft fault to adapt the continuously change of component parameters. Limits of experimental conditions, lead to the limited number of samples labeled by experts, so that training samples are classified using the semi-supervised support vector machine (S3VM) algorithm. Manifold learning algorithm has been used for the feature extraction and the dimension reduction of soft fault time domain response data in analog circuits. Then the semi-supervised Gaussian mixture model (SGMM) is applied to cluster decision trees. Finally, the S3VM classification is used for the soft fault diagnosis in analog circuits. Experimental results show that the proposed method can be utilized in the single and double soft fault diagnosis of analog circuits. It is observed that the S3VM method is extremely significant as a guide in actual engineering applications, although the diagnosis rate is slightly less than the fixed-parameter offset soft faults.

软故障诊断已被证明是模拟电路中一个非常具有挑战性的问题。为了提高泛化能力并接近故障诊断模型的实际应用，本文提出了一种在软故障区间内获取大量训练样本的新方法。在软故障间隔内随机生成训练样本，以适应组件参数的不断变化。由于实验条件的局限性，导致专家标记的样本数量有限，因此使用半监督支持向量机（S3VM）算法对训练样本进行分类。流形学习算法已用于模拟电路中软故障时域响应数据的特征提取和降维。然后将半监督高斯混合模型（SGMM）应用于聚类决策树。最后，将S3VM分类用于模拟电路中的软故障诊断。实验结果表明，该方法可用于模拟电路的单，双软故障诊断。可以观察到，尽管诊断率比固定参数偏移软故障略低，但S3VM方法在实际工程应用中具有非常重要的指导意义。