一种模拟电路故障诊断方法研究

摘要

The LSSVM algorithm is applied to the analog circuit fault diagnosis model,and its parameters are optimized with particle swam optimization (PSO) algorithm.The circuits of the band-pass fiber and bi-quadratic high-pass filter are taken as the instance of the fault diagnosis to verify the analog circuit fault diagnosis method.The three-layer wavelet packet is used to decompose the output voltage signal to obtain 8 frequency band energy feature vectors.The data samples are acquired with Carlo Monte simulation,which are used to train and test the fault diagnosis model.The results show that the fault diagnosis model's diagnosis accuracy for eight faults is higher than 95％,which is constructed with the improved LSSVM algorithm,and has high fault diagnosis performance.%将LSSVM算法应用于模拟电路故障诊断模型,使用PSO算法对LSSVM算法的参数进行寻优.以带通滤波器电路和双二次高通滤波器电路的故障诊断实例对该文研究的模拟电路故障诊断方法进行验证.使用三层小波包分解输出电压信号,得到8个频带能量特征向量,通过Monte Carlo仿真得到数据样本,用于故障诊断模型的训练和测试.结果表明,该文使用的改进LSSVM算法构建的故障诊断模型针对8种故障的诊断准确率均高于95％,具有较好的故障诊断性能.