This paper reports a novel method for parametric fault diagnosis in linear analog electronic circuits using distance weighted cosine K-Nearest Neighbours (K-NN) algorithm that performs data classification on the basis of cosine similarity between data features or attributes. In this approach the analog electronic Circuit Under Test (CUT) is represented in the form of a transfer function model and natural response specifications of the system such as damping ratio, natural frequency and static gain of the system are extracted as features from this model. For experimentation purpose a second order Sallen-Key band pass filter and a fourth order Chebychev Type 1 low pass filter is considered, the corresponding fault classes are created for each of the circuit. The parameter values of the passive components in the system have been varied to derive the features, and each component whose tolerance varied is labelled with a corresponding fault class. The proposed methodology classifies faulty classes with accuracy greater than 95%.

本文报道了一种使用距离加权余弦K最近邻（K-NN）算法在线性模拟电子电路中进行参数故障诊断的新方法，该算法根据数据特征或属性之间的余弦相似度执行数据分类。在这种方法中，模拟电子被测电路（CUT）以传递函数模型的形式表示，并且从该模型中提取系统的自然响应规范（例如阻尼比，系统的固有频率和静态增益）作为特征。为了实验目的，考虑了二阶Sallen-Key带通滤波器和四阶Chebychev Type 1低通滤波器，为每个电路创建了相应的故障类别。已更改系统中无源组件的参数值以得出特征，并且其容差变化的每个组件都用相应的故障类别标记。所提出的方法对故障类别进行分类，其准确度大于95％。