论文部分内容阅读
为了提高模拟电路故障诊断准确率,提出一种联合选择特征选和分类器参数模型的模拟电路故障诊断方法 (Feature-Classifier)。将模拟电路故障特征子集和分类器参数编码成为粒子,然后粒子根据目标函数通过信息交流和互相协作找到最优特征子集和分类器参数,并根据最优特征子集对样本进行约简;分类器根据最优参数对约简后样本进行训练建立模拟电路故障诊断模型,并通过仿真实例对性能进行测试。结果表明,相对于其他模拟电路故障诊断方法,Feature-Classifier能够较快找到最优特征子集与分类器参数,不仅提高了模拟电路故障诊断准确率,并加快了故障诊断速度。
In order to improve the accuracy of analog circuit fault diagnosis, this paper proposes a feature-classifier (FA) method for the joint selection of feature selection and classifier parameter model. The fault feature subset and the classifier parameters of the analog circuit are encoded as particles, and then the particles find the optimal feature subset and classifier parameters through information exchange and mutual cooperation according to the objective function, and reduce the samples according to the optimal feature subset. The classifier trained the reduced samples according to the optimal parameters to establish the analog circuit fault diagnosis model and tested the performance through simulation examples. The results show that Feature-Classifier can find the optimal feature subset and classifier parameters faster than other analog circuit fault diagnosis methods, which not only improves the accuracy of analog circuit fault diagnosis, but also speeds up the fault diagnosis.