为提高模拟电路的软故障诊断能力,提出了一种基于KSLPP特征 提取和ELM的集成诊断方法.它首先利用KSLPP良好的特征提取能力,构建故 障样本集的特征集;然后,利用ELM解决复杂非线性问题的优势,建立提取特征 集的故障识别模型;最后,再由所建模型对各种故障模式进行诊断判定.椭圆滤波器的 仿真测试表明,该集成方法诊断的总正确率达到98.8\%,且11种故障状态中的8 种达到100\%正确率,从而验证了其可行性和有效性.

To improve the ability of soft fault diagnosis of analog circuits, an integrated diagnosis method based on KSLPP feature extraction and ELM is proposed. First the good feature extraction ability of KSLPP is used to construct the principal element feature set of fault sample set; then the advantages of ELM on solving the complicated nonlinearity problems is applied to establish the fault identification model based on principal element feature set; Finally each failure mode is diagnosed and determined by the built model. The simulation experiment of Elliptic Filter shows that, the total correct rate obtained by the integrated method is 98.8\% with 100\% correct rate of 8 fault states in 11 fault states, which verifies its feasibility and effectiveness.