模拟电路免疫记忆网络故障诊断新方法

提出了一种基于免疫记忆网络理论与$k$近邻算法的模拟电路故障诊断方法。首先，利用免疫记忆网络寻找各故障空间的最佳记忆抗体。在免疫记忆网络中根据浓度来选择记忆抗体，以促进记忆抗体在各故障空间的均匀分布。利用克隆和超级变异机制来保证抗体多样性，再利用浓度和期望值对抗体进行促进和抑制，以避免早熟现象的产生；然后，根据所得到的各故障空间的最佳记忆抗体，使用改进的阈值k近邻算法对抗原进行故障分类；最后，以带通滤波器为诊断实例，利用实际电路测试数据和仿真数据作为测试样本进行故障诊断性能评估；实验结果证明该故障诊断方法具有较高的故障诊断率。

Fault Diagnosis Method for Analog Electronic Circuits Based on Immune Memory Network Theory

A method of analog circuit fault diagnosis based on immune memory network theory and k nearest neighbor algorithm is proposed. First, immune memory network is used to search the best memory antibody in fault space. In order to equally distribute the memory antibodies in fault space, the memory antibodies in immune memory network are chosen according to concentration. The mechanism of clone and hyper-variation are used to maintain the diversity of antibody, and methods including stimulating and suppressing antibody by concentration and expectation are applied to avoiding immaturity convergence. Second，an improved threshold KNN (k nearest neighbor) algorithm is used to classify the antigen based on the set of best memory antibody in fault space. At last, the band-pass filter is taken as an example, both of data from real circuit and data from software simulation are provided as testing samples to evaluate the diagnosis performance. The experimental results prove that the proposed method for analog circuit fault diagnosis an increase the diagnosis precision.