基于量子进化支持向量机的模拟电路故障诊断

Fault Diagnosis for Analog Circuits Based on SVM with Quantum-Inspired Evolutionary Algorithm

基于量子进化算法的最小二乘小波支持向量机(LS-WSVM),设计了一种模拟电路故障诊断方法。将量子进化算法应用于多类LS-WSVM分类器来选取正规化参数和核参数,针对从测试点得到的各种故障状态下输出电压信号,采用小波提升变换对其进行分解获取多尺度的小波系数,对经处理的小波系数提取出故障特征量,以此作为样本训练多类LS-WSVM分类器来确定模拟电路故障诊断的模型。采用雷达扫描电路进行了仿真,结果表明,设计的模拟电路故障诊断方法效果良好。

Based on least squares wavelet support vector machines （LS-WSVM） with quantum-inspired evolutionary algorithm （QEA）, a systematic approach for fault diagnosis of analog circuits was proposed. QEA was applied to select the optimal values of the regularization and kernel parameters of the multi-class LS-WSVM classifiers. Also output voltage signals under faulty conditions were obtained from analog circuit test points. Then wavelet coefficients of output voltage signals were gained by wavelet lifting decomposition, and faulty feature vectors were extracted from the coefficients. The faulty feature vectors were used to train the multi-class LS-WSVM classifiers, so the model of the analog circuit fault diagnosis system was built. The simulation results of the scout circuits of radar show the fault diagnosis method of using LS-WSVM with quantum-inspired evolutionary algorithm is effective.